Microcosm
This page

Reference

Doctrine reference

Microcosm's public slice includes a compact rule lattice: principles, axioms, anti-principles, concepts, mechanisms, and paper modules projected from public source JSON into one static packet. It is the reference map behind the Doctrine page: a source-backed index and relationship browser, not a second reading body.

This page runs entirely in your browser: no backend, no network calls. It is a read-only reference and changes nothing in the source.

Summary

Principles
20
Axioms
12
Anti-principles
17
Concepts
11
Mechanisms
95
Paper modules
93
Relation rules
37

Route ladder: cluster_flag -> flag -> card -> source_receipt / candidate pressure only not active law

anti-principle: active / 2 linksaxiom: active / 1 linksconcept: active / 3 linksmechanism: active / 4 linkscomponent: active / 7 linkspaper module: active / 6 linksprinciple: active / 3 linksskill: active / 4 linksstandard: active / 2 links

Coverage gaps (2)

Aggregate repair queues from the coverage source. They make missing source work routeable without creating records or links that are not warranted.

Mechanism relation fillOptional relation slots for mechanisms that remain intentionally unfilled.25 open

These mechanism relation links are left empty unless the source warrants them.

Source Source JSON

Component relation fillOptional relation slots for components that remain intentionally unfilled.26 open

These component relation links are left empty unless the source warrants them.

Source Source JSON

Lattice records

Each card is compact on purpose. Axioms, principles, and anti-principles link to their canonical reading cards on Doctrine; paper modules link to their body page. Concepts and mechanisms currently read in place because this lattice card is their complete public representation. In every case, this page keeps the lattice location, relationship context, and source link without duplicating another page's body.

Principles (20)

Operating rules the public slice uses to keep evidence, boundaries, and routing honest.

Recompute, do not echoDo not trust a fixture label, declared verdict, route status, count, or public copy line as proof. Recompute the verdict from lower-level evidence and keep a negative fixture where the cheap lie fails.principle
Lower claim strength to checker strengthThe scope limit is the strongest thing the named checker, validator, registry, or witness route actually computes. If the checker decides only a local contract, do not let prose project global authority.principle
Concentrate trust in small checkersPrefer a small verifier, parser, harness, compiler route, registry contract, or kernel over broad narrative confidence. Producers may be large; the authority boundary should be small enough to inspect and rerun.principle
Possession is not permissionAuthority comes from dereferenced proof, policy, result record, rollback evidence, and current world state. account secrets, role names, admin phrasing, or "trusted session" language cannot authorize mutation by themselves.principle
Cache by content, not by nameA reusable result record, command result, source import, or work-landing attempt must carry its content basis. Drift in source bytes, dirty scoped files, parent SHA, or fixture input invalidates reuse.principle
Status fails closedMissing evidence, policy files, source digests, secret scans, negative cases, or result record self-scans block or demote. A downstream projection can explain a pass; it cannot upgrade a blocked source truth.principle
Track known unknowns without claiming the unknown is mappedCoverage reports name declared domains and materialized gaps. They must not say that unmapped space is safe, complete, exhausted, or irrelevant.principle
Refuse inadmissible computations with typed reasonsWhen preconditions fail, return a reasoned refusal. Do not emit meaningless statistics, proof authority, safety verdicts, or public-readiness status just to keep a green path.principle
Preserve provenance across every boundaryEvery shard crossing from source source, fixture, result record, public copy, provider shape, or private-system adjacency must carry a provenance class and scope limit. If the flow is only declared or endpoint-labeled, say so.principle
Do not land effects without compensationWrites, launch steps, claim launch, source imports, and rollback-shaped operations need ordered transaction evidence. launch locks after durable records, recompute after launch, and block stale parent or same-path conflicts.principle
Bind volatile facts to refresh routesCounts, "current" states, live route totals, CI floors, body-import floors, and readiness signals must cite how they can be re-derived. If they cannot, keep them out of durable prose or mark them as dated snapshots.principle
Make doctrine executable before authoritativeA doctrine surface earns authority through grammar, required fields, result record obligations, scope boundaries, and validator coverage. Prose can orient a reader, but it cannot become system authority without an executable contract.principle
Apply the same floor to meta artifactsMicrocosm artifacts about Microcosm do not get exemptions. Standards, paper modules, ledgers, routes, generated projections, and launch claims must satisfy the same evidence, scope boundary, and refusal floors they impose on other shards.principle
Carry basis and provenance togetherContent basis says which bytes or rows were used; provenance says where they may flow and how strongly they may be claimed. A shard missing either side is not fully routed.principle
Keep projections below source authorityGenerated docs, markdown summaries, route cards, and paper modules may expose a source truth, but they cannot upgrade it. Recompute from source or demote when the source basis, grammar, or status lattice no longer supports the projection.principle
Bind authority to transaction scopeMutation authority is not merely who can touch a file. It is the combination of proof-derived permission, claimed write scope, current parent state, compensation, and landing evidence for this transaction.principle
Anchor graph mutations to unique source rowsBefore adding or removing a lattice edge in a repeated registry, anchor the mutation to the unique source row, target id, and builder route that will consume it. A generated projection, count delta, or nearby repeated key cannot substitute for that row-level basis.principle
Require fan-in before activationA staged law, standard, component, or projection is not active authority until its owner boundary, source row, generated parity, validation result record, and status transition have landed in the same governed transaction or an explicit blocked result record preserves the frontier. A projection generated from source authority held dirty by another live owner is still outside fan-in; request handoff, owner landing, or a blocked result record before treating it as current. Partial admission must remain residual pressure.principle
Classify residual pressure before wiringA residual is a typed pressure route, not an edge. Before wiring a missing neighbour, classify the declared domain, source row, target resolution, fillability, evidence floor, and scope boundary. A candidate route, generated neighbour hint, basename match, singleton match, or stale projection row is still pressure; it becomes an edge only when the current source authority row names the relation and the target resolves under the builder. Bidirectional system representation follows the same floor: principle-to-system edges must be source-derived, and system-to-principle evidence may refine governed ids only when current source rows name the relation. Neither direction is support proof, projection authority, or permission to launder residual pressure into an edge. If the system cannot name the target from source authority, keep the gap residual and make the re-entry computable instead of inventing a relationship or whitening the health card.principle
Bind result records before record authorityA doctrine record is not fully active by projection alone. Bind validator result records, evidence refs, omissions, scope boundaries, and scope limits on the record before treating its JSON, markdown, routing edge, or public copy as current system authority.principle

Axioms (12)

Root commitments admitted by the public slice, with explicit scope boundaries and source refs.

Derivation before assertionFor any claim phi over basis B, admissibility requires a derivation certificate c and checker K such that K(B,c,phi)=accept; strength(phi) <= strength(K(B,c,phi)). Bare assertion has bottom evidence.axiom
Kernelized verificationTrusted claims are decided by a small checker K over certificates c; producers emit c and K decides.axiom
Authority by derivation, not possessionauth(subject,effect)=F(deref(tokens_presented),policy,proof_refs,world_state); ambient identity is insufficient.axiom
Content-addressed determinisma=f(B) and id(a)=H(B); equal B permits reuse; drift(B) forces recompute; missing(B)=bottom.axiom
Fail-closed monotone latticestatus(composite)=meet(status(parts)); no evidence defaults to blocked; later stages may lower but not raise authority without new derivation.axiom
Open-world epistemicsnot_proven(P) does not imply proven(not P); coverage is closed-world only inside declared finite domains.axiom
Typed partiality and refusalPartial computation g is totalized as Result: Ok(y) under Pre(x), otherwise Refusal(reason,evidence).axiom
Provenance propagation and non-interferenceData labels propagate along flows; untrusted labels reach privileged sinks only through declared transforms satisfying sink policy.axiom
Compensable transactional effectsEffect e requires a compensator or declared irreversible boundary; multi-step effects land as saga with CAS and single-writer constraints.axiom
Temporal validity and freshness contractsClaims over live state are cached reads valid only under <value,as_of,basis,rederive> invalidation contracts.axiom
Executable grammar before doctrine authorityauthority(d) implies d in L(G), result record obligations, and scope boundary are present; prose alone is projection.axiom
Reflexive accountability / no privileged meta-layerFor every Microcosm artifact a, any claim phi carried by a must satisfy the same admissibility relation as external claims.axiom

Anti-principles (17)

Named shortcuts the public slice refuses on sight, the negative space that keeps the rules honest.

Fixture-label echoEchoing a fixture verdict, registry label, markdown claim, or model answer instead of recomputing it from lower-level evidence.anti-principle
Producer trustTrusting a producer, persona, route, account secret, or prior success instead of a checker, proof, policy, or dereferenced capability.anti-principle
Rank-as-product-scoreTreating counts, handles, passing validators, or evidence classes as product maturity, launch-scope decision, or whole-system correctness.anti-principle
Cache-across-driftCaching by name, path, route, display label, or producer while basis content has drifted.anti-principle
Unknown-unknown exhaustivenessTreating missing evidence as evidence of absence outside a declared closed domain.anti-principle
Inadmissible number emissionEmitting inadmissible numbers or conclusions instead of typed refusal.anti-principle
Public/private membrane breachLetting untrusted, private, provider, prompt, account secret, or raw-voice material reach a privileged or public sink without provenance and sanitizer transform.anti-principle
Blind irreversible mutationPerforming irreversible mutation without a compensator, rollback result record, CAS/world-version guard, or explicit irreversible boundary.anti-principle
Frozen live factFreezing live facts in prose without `as_of`, basis, and rederive contract.anti-principle
Prose-as-executable-authorityGranting executable authority to prose doctrine without grammar and result record obligations.anti-principle
Meta-artifact exemptionExempting Microcosm's own result records, docs, releases, generated projections, or validators from Microcosm's evidence gates.anti-principle
Synthetic system substitutionUsing synthetic fixtures as substitutes for available system.anti-principle
Generated-result record source inversionTreating generated result records as hand-authored source.anti-principle
Public-authority inflationLetting public docs imply a hosted service, external service access, source-file mutation, financial or trading decisions, deployment posture, affiliation or endorsement, or private-system equivalence that no admissible witness backs.anti-principle
Mechanism theaterUsing field vocabulary such as proof, verifier, information flow, world model, or benchmark integrity when the public mechanism only validates a result record or projection shape.anti-principle
Receiver inflationDisplaying a declared, inferred, or generated downstream target as an observed runtime effect without evidence of the effect relation.anti-principle
Projection-as-sourceLetting a markdown page, generated card, atlas row, or compact result record summary override the executable contract it summarizes.anti-principle

Concepts (11)

Typed vocabulary boundaries that explain why a public specimen matters.

agent reliability and safety validators as bounded public scope limitssafety and reliability claims remain bounded to named public fixtures, validators, and result record rows instead of global agent capability claimsconcept
architecture and navigation route contracts as executable doctrine boundariesnavigation and doctrine surfaces become walkable through source-bound contracts while generated views stay below source authorityconcept
entry and reveal routes as bounded cold-reader readiness evidenceentry evidence shows what a reader can inspect, not that the whole system is ready or correctconcept
standard as schema contract with explicit scope limitinvalid standards are blocked by negative cases such as missing teleology, missing result record expectations, or prose-only authorityconcept
doctrine handles as typed mistake-prevention boundariesruntime first-screen output emits CONCEPTS and MECHANISMS before standards-tree search is requiredconcept
formal math and proof witnesses as bounded public proof-adjacent result recordsproof-related artifacts expose bounded witness status without claiming theorem completeness or provider proof authorityconcept
source import and projection drift controls as provenance-preserving boundariesimported material remains tied to source anchors and drift result records instead of becoming ambient doctrine authorityconcept
research and science replay validators as reproducibility scope limitsresearch claims remain scoped to public replay evidence and known gaps instead of becoming external scientific truth claimsconcept
component-standard-runtime-result record coverage as projection-only evidenceaccepted_organ_count and covered_organ_ids are validated without becoming launch-scope decisionconcept
local pressure rows as typed candidates for owner-surface refinementstatus_counts distinguish refined_existing_surface, workitem_captured, and nothing_to_refineconcept
work landing and continuity controls as transaction-scoped coordination evidencework progress claims stay tied to owned paths, result records, and transaction scope rather than chat status or generated projectionsconcept

Mechanisms (95)

Runnable or inspectable transformations that turn the rule boundary into a checkable effect.

validates public benchmark integrity replayThe agent benchmark integrity anti-gaming replay component validates public benchmark-claim boundaries by checking locked evaluator policy, case roster binding, replay observation fields, file-access refs, contamination refs, trusted-reference score refs, output replay refs, public trace verdict recomputation, copied source-module digests, metadata-only result record policy, and anti-gaming negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates completion evidence claimsThe agent completion faithfulness audit component validates public completion evidence claims by checking fixture commit objects and HEAD with git subprocesses, pytest span execution and explicit pass status with pytest subprocesses, fixture-ledger cap rows, copied source-module digests, and stable overclaim negative cases before writing metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public memory conflict replayThe agent memory temporal-conflict replay component validates public memory projection mechanics by checking ADD/UPDATE/DELETE/NOOP decisions, temporal conflict-edge refs, stale-downgrade refs, metadata-only non-public refs, paired memory-on/off replay evidence, answer-delta result records, source-module manifest boundaries, and memory falsification negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public monitor verdict result recordsThe agent monitor redteam falsification replay component validates public monitor-verdict evidence shape by checking trajectory rosters, suspicious-span refs, adversarial-probe refs, escalation refs, body-omission refs, mitigation refs, cold-replay refs, public trace recomputation, source-module manifest boundaries, and falsification negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public route feedbackThe agent route observability runtime validates public route-feedback and observability fixture bundles by checking actor-axis authority boundaries, route-lease consumption, duplicate trace ids, hook-shadow advisory status, anti-pattern debt retirement, agent-principle-lens compact admission, egress-mirror boundaries, copied source-module digests, and non-public-state exclusion before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public sabotage scheming monitor replayThe agent sabotage scheming-monitor replay validates a public synthetic sabotage-monitor bundle through task episodes, action traces, monitor scores, counterfactual replay, cold replay, source-module digest anchors, negative cases, metadata-only result records, and scope limits without live sabotage, exploit instruction, account secret/account material, private reasoning export, launch, or deployment-risk product claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public sandbox policy traceThe agent sandbox policy escape replay component validates public sandbox-policy projection mechanics by checking action requests, pre-execution policy verdicts, side-effect result records, rollback result records, cold replay rows, public trace spans, source-module manifest boundaries, secret-exclusion scans, and escape negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public agentic vulnerability patch proof replayThe agentic vulnerability discovery patch-proof replay component validates public vulnerability-claim boundaries by checking projection protocol, vulnerability policy, synthetic target refs, issue hypotheses, trace evidence, abstract exploitability refs, patch diff refs, regression tests, verifier result records, sandbox verdicts, false-positive triage, cold replay, public agent-execution trace spans, source-module manifest digests, secret-exclusion scan, metadata-only result record policy, and security-overclaim negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public proof authority runtime bundleThe Set 4 proof, authority, and runtime bundle validates copied public proof-control, formal-math, Codex runtime, completion, bitemporal, taskpolicy, and context-yield source bodies through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting theorem-proof, benchmark, live runtime, source-file changes, public sharing, launch, or whole-system correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public authority systems bundleThe Set 5 authority systems bundle validates copied public source authority/control bodies through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting live external model access, proof success, process signal authority, generated-state mutation, source-file changes, public sharing, launch, private-system equivalence, or whole-system correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public unsurfaced primitives bundleThe Set 6 unsurfaced primitives bundle validates copied public source-primitive bodies through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting raw operator memory, prompt-shelf capture authority, live market data, provider/browser state, media launch, source-file changes, public sharing, launch, or whole-system correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public demo take console bundleThe Set 7 Demo Take Console bundle validates copied public Swift source bodies through deterministic SwiftPM build-witness, recording-state, helper-bridge, recorder-store, hotkey/audio-meter, transcribe-payload, exported-bundle, digest-anchor, negative-case, metadata-only result record, and scope limit checks without granting app launch authority, screen or microphone capture authority, model dispatch, source-file changes, public sharing, launch, private-system equivalence, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public source engines bundleThe Set 7 source engines bundle validates copied public source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting source authority, private-system equivalence, external model access, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public oracle sibling bundleThe Set 7 Oracle sibling bundle validates copied public Oracle source bodies through deterministic subject-index, subject-snapshot, truth-diff, quartet-plan, original-pytest, exported-bundle, digest-anchor, negative-case, metadata-only result record, and scope limit checks without granting Oracle reasoning authority, semantic truth authority, external model access, source-file changes, public sharing, launch, private-system equivalence, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public secondary runtime bundleThe Set 7 secondary runtime bundle validates copied public runtime, graph, cartography, stockgrid, and Polymarket source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting browser/session export, wallet authority, live market data, investment-related actions, source-file changes, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public audio level rms portThe Set 8 audio level RMS port validates a source-faithful public projection of AudioLevelMonitor normalized-level RMS behavior by running deterministic fixture arrays, malformed negative exercises, source-module digest checks, metadata-only result records, and scope limits without starting audio capture or claiming device, launch, public sharing, or domain-correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public compliance pipeline bundleThe Set 8 compliance pipeline bundle validates a bounded public compliance/pipeline import by exercising the compliance adapter registry, bounded no-write checks, baseline companion scans, digest normalization, observe-plan helper behavior, dispatch/process boundaries, source-module digests, six negative cases, metadata-only result records, and scope limits.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public policy engines bundleThe Set 8 policy engines bundle validates copied public policy-engine bodies by exercising lab contract audit, market fusion readiness, campaign transition adjudication, source-module digest anchors, three negative cases, metadata-only result records, and scope limits without live campaign execution, model/external model access, launch, public sharing, or source-file changes.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public structural theses bundleThe Set 8 structural theses bundle validates a copied public structural-theses finance body by running synthetic winner, loser, and control exercises, digest and anchor checks, three negative cases, metadata-only result records, and scope limits without live market data, investment-related actions, portfolio action, external model access, launch, or publishing-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public tools tail primitives bundleThe Set 8 tools-tail primitives bundle validates four copied public tools-tail source modules by exercising observer set diffs, JSON patch interpretation, stable ledger-id hashing, shadow-envelope parsing, source-module digest anchors, four negative cases, metadata-only result records, and scope limits without live oracle/provider/source-file changes/launch lanes.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public validator checker bundleThe Set 8 validator checker bundle validates an exact copied public validators.py body by exercising policy/status judging, private-boundary scanning, specimen checks, launch-gate checks, validate-entrypoint behavior, source-module digest anchors, six negative cases, metadata-only result records, and scope limits.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public source engines bundleThe Set 9 source engines bundle validates copied public source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting source authority, private-system equivalence, external model access, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public cold eval honesty bundleThe Set 10 cold-eval honesty bundle validates copied public source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting source authority, private-system equivalence, external model access, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public governance compilers bundleThe Set 10 governance compilers bundle validates copied public source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting source authority, private-system equivalence, external model access, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public live source drift bundleThe Set 10 live-source drift bundle validates copied public source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting source authority, private-system equivalence, external model access, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public saturation engines bundleThe Set 11 saturation engines bundle validates copied public source-body behavior through deterministic fixture and exported-bundle exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without granting source authority, private-system equivalence, external model access, public sharing, launch, or whole-system correctness.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public market dashboard read model bundleThe Set 12 market dashboard read-model bundle validates copied public read-model helpers over synthetic fixtures through market-dashboard import stubs, freshness classification, related-situation scoring, source-module digest anchors, negative cases, metadata-only result records, and scope limits without market-level conclusions, investment-related actions, external model access, launch, public sharing, or whole-system correctness claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public prediction market board bundleThe Set 12 prediction market board bundle validates copied public prediction-board and quant-mart diagnostics over synthetic fixtures through event join and dedupe, provider drift flags, missingness classification, previous-green deltas, source lifecycle enrichment, source-module digest anchors, negative cases, metadata-only result records, and scope limits without market/provider truth, investment-related actions, external model access, launch, public sharing, or whole-system correctness claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public launch claim language gateThe Set 12 launch-claim language gate component validates launch-claim fixture generation, claim-language blocking, assert-clear exits, source-module digest anchors, negative cases, metadata-only result records, and scope limits without authorizing open-source deployment posture, public-sharing claims, launch status, or source-file changes.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public belief state process reward replayThe belief-state process reward replay component validates public belief summaries, verifier-feedback observations, process and outcome reward rows, reward-hacking negative cases, source-module digest anchors, metadata-only result records, and scope limits without exporting hidden reasoning, using hidden gold labels, relying on neural-judge-only labels, claiming benchmark performance, running live RL, calling providers, mutating source, or granting launch control.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public bounded autonomy campaign packetThe bounded-autonomy campaign packet component validates campaign policy, failed-campaign digest handling, source-write refusal, source-module digest anchors, negative cases, metadata-only result records, and scope limits without authorizing autonomous source-file changes, campaign execution, public sharing, or launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates synthetic bridge continuityThe bridge phase continuity runtime validates public synthetic observe/apply bridge continuity by checking disk-first continuation packets, heartbeat liveness boundaries, resource-pressure dispatch blocks, resume-once semantics, duplicate-resume rejection, worker-skip dedupe, copied observe-runtime source-module digests, tracked result record-write gating, non-public-state scans, and scope limits before writing bounded metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public certificate kernel executionThe certificate kernel execution lab component validates public proof-adjacent execution boundaries by checking a Lean/Lake certificate-kernel fixture, generated certificate rows, analyzer metadata, transition traces, typed CP2 action translations, bounded Evolve reruns, source-module manifest digests, copied Lean/tool/profile bodies, metadata-only result record policy, authority counters, and negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public operator contractThe cognitive operator registry component validates public reusable-cognition system by checking operator-shape fields, active-operator dogfood result records, cognition-delta evidence, anti-sprawl accretion decisions, operator-voice and authority-overclaim rejection, copied source registry/standard/tool body digests, and secret/non-public-state exclusion before writing bounded metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public source root bootstrapThe cold-clone probe validates source-root public bootstrap mechanics by importing the package from src, running the secret-exclusion scan, executing the first-wave pattern-binding fixture, mirroring the declared public result record refs when missing, and writing an ignored local result record without claiming launch, hosted-product, private-system, provider-call, source-file changes, or whole-system correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public first run route mapThe cold-reader route-map component validates public first-run route projections by checking route-row command refs, public docs refs, route-to-result record bindings, ordinal first-run sequencing, front-door commands, copied cold-entry source-module digests, metadata-only result record boundaries, negative cases, secret/non-public-state exclusion, and scope limits before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public concurrency mission controlThe concurrency mission-control component validates copied public mission-control builder and bridge artifacts through fixture failure classes, work log seed-speed topology, source-module digest anchors, negative cases, metadata-only result records, and scope limits without becoming a live scheduler, external model service, hosted orchestrator, production concurrency proof, launch, or publishing-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public corpus readiness boundaryThe corpus readiness Mathlib absence gate component validates public formal-math corpus readiness boundaries by checking copied PROVER smoke-run corpus readiness rows, Lean/Std toolchain probe rows, Mathlib absence status, consumer-gate decisions, absent-corpus blocking, source-module manifest digests, metadata-only result record policy, scope limits, and negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public mathlib absence boundaryThe corpus readiness Mathlib absence gate validates recorded corpus and toolchain readiness accounting, Mathlib absence boundaries, consumer gate cases, source-module digests, leakage guards, and metadata-only public result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public doctrine fact claim auditThe doctrine fact-claim audit component validates fact assertions, numeric claim bindings, DAG references, code-locus anchors, source-module digest anchors, negative cases, metadata-only result records, and scope limits without authorizing unsupported truth claims, source-of-record flips, public sharing, or launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public work landing replay contractThe durable agent work-landing replay component validates public work-landing replay rows by checking owned-path claim evidence, owner-native validation-before-commit ordering, HEAD-advance evidence for landed language, metadata-blocked completion capture, work log finalizer refs, copied source source-module digests, and metadata-only result record boundaries before writing bounded replay result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public reference knowledge routerThe Engine Room reference knowledge router mechanism validates explainable tiered routing over sanitized reference catalog fixtures by scoring structured routing fields, family text, open-first summaries, and curated notes while rejecting domain-mismatch and empty-query cases without claiming BM25, TF-IDF, embeddings, repository cloning, license authority, private reference corpus access, launch, or private-system authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public command run singleflightThe Engine Room command-run singleflight mechanism validates content-addressed subprocess run keys, fcntl-backed leader/follower collapse, completed-run reuse, scoped dirty/content fingerprint invalidation, captured stdout/stderr replay, and empty-command refusal over public fixtures without claiming scheduler, daemon, live command_runs export, distributed-lock, launch, or private-system authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public engine room demoThe Engine Room demo component validates the staged public Engine Room composition over bounded fixtures, controller audits, missing-target negative cases, metadata-only result records, and scope limits without claiming deployment posture, private-system equivalence, frontier theorem proving, complete security proof, public sharing, launch, external model access, or source-file changes.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public derived fact provider engineThe Engine Room derived fact provider engine mechanism validates registry-backed fact resolution over public fixture roots by resolving JSON pointers, glob counts, and git-backed callable facts, then turning provider failures into repairable error rows without claiming doctrine truth auditing, full source fact registry export, semantic claim validation, launch, or private-system authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public egress self compliance gateThe Engine Room egress self-compliance gate mechanism validates phrase-membership policy over public agent-output fixtures by detecting permission ceremony without a real blocker, self-error language without durable capture, and command displacement without execution evidence while accepting explicitly bounded blocker or result record language without claiming taint analysis, prompt-injection defense, sandboxing, information-flow proof, launch, or private-system authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public generated projection drift gateThe Engine Room generated projection drift gate validates owner-routed generated artifact freshness over public fixtures by selecting projection owners from changed paths, fingerprinting declared source and artifact files, accepting source-hash cache hits only when source hash, artifact hash, check command, and artifact presence match, and failing planted-byte or missing-artifact cases without claiming semantic drift proof, repair authority, launch-scope decision, or full source registry validation.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public lean proof search labThe Engine Room Lean proof-search lab mechanism validates bounded public proof-search fixtures by running tiny Lean statements through symbolic tactic search, statement-only candidate checking, problem-id ablation, oracle-body forward-firewall rejection, and axiom cleanliness checks without claiming neural theorem proving, frontier-scale automation, private source prover run export, oracle body solving, launch, or private-system authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public navigation fitness benchmarkThe Engine Room navigation fitness benchmark mechanism validates public route-packet benchmark fixtures by checking expected stable-id recall, packet precision, forbidden first routes, latency budgets, scent terms, and debt-candidate summaries without running the private kernel, validating embeddings, claiming universal navigation benchmark authority, launch, or private-system authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public projection leak gateThe Engine Room public projection leak gate validates rendered public projection roots by scanning file content, path names, symlink targets, policy exceptions, and optional gitleaks output for account secret-shaped or private-system leakage, returning bounded hash-only result records without copying sensitive payloads or granting launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public doctrine grammar bundleThe executable doctrine grammar component validates public standards and paper-module grammar fixtures by checking required standard fields, paper-module teleology/governing-standard/result record/scope boundary sections, duplicate slugs, prose-runtime authority claims, doctrine-completeness overclaims, copied executable-grammar and standards/type-plane source-module digests, source-open body-import accounting, and non-public-state exclusion before writing bounded metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public finance forecast evaluation spineThe finance forecast evaluation spine validates copied public finance-evaluation helpers over synthetic market-shaped fixtures through Diebold-Mariano, HLN refusal, SPA/reality-check bootstrap, stationary-bootstrap and MCS exercises, source-module digest anchors, negative cases, metadata-only result records, and scope limits without live market data, investment-related actions, track-record claims, optimizer mutation, launch, or publishing-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public first screen composition rootThe first-screen composition root validates the public one-screen entry card by checking reader-route ids, shared first commands, behavior-proof refs, evidence-accounting frames, doctrine-effect handles, omission result records, README entry order, observatory landing refs, text projection bounds, and scope limits without becoming launch, hosted-public sharing, provider-call, source-file changes, private-data-equivalence, score-based-progress, or whole-system-correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public evidence cell anchor resolutionThe formal evidence cell anchor resolver validates proof-language evidence boundaries by resolving public paper claims to evidence-cell ids, requiring source-anchor refs and machine-anchor classes, checking copied source-module digests and metadata-only result record policy, anchoring verifier-trace cells to real Ring2 result records, and rejecting proof-body, private-ref, human-approval, theorem-correctness, missing-cell, and missing-anchor overclaims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public evidence cell anchorsThe formal evidence cell anchor resolver validates claim-to-evidence-cell resolution, public source anchors, permitted claim strength, copied source-module manifests, leakage refusals, and metadata-only evidence anchor result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public lean lake witnessThe formal math Lean proof witness component validates a bounded public Lean/Lake witness by copying a declared toy Lake project into a temporary workspace, probing local Lean and Lake, running lake build, checking copied public source-module digests and anchors, recording declaration/source metadata, and observing forbidden-import, private-source-ref, proof-body, and invalid-proof negative cases before writing redacted result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public lean witnessThe formal math Lean proof witness validates a bounded public toy Lean/Lake witness by checking tool availability, temporary-workspace build status, source-module manifests, declaration metadata, redacted result records, and leakage/overclaim negative cases.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public premise retrieval projectionThe formal math premise retrieval component validates public retrieval metadata, premise-index references, strategy cases, retrieval queries, context-budget limits, copied index material, negative-case refusals, and metadata-only retrieval result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public premise retrieval sliceThe formal math premise retrieval component validates a formal-math retrieval slice by checking copied Lean/Std premise descriptors, retrieval query scoring, context recipe byte budgets, strategy gates, source-module/body-floor provenance, card freshness, metadata-only result record policy, and proof/oracle/test-split/strategy negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public formal math readiness bundleThe formal math readiness gate component validates public formal-math readiness evidence by checking declared corpus and Mathlib readiness, tactic probe result records, proof-metadata-only premise indexes, target-shape route admissibility, provider context budgets, formal_math_readiness_extensions intake refs, copied PROVER probe artifacts, public component source body imports, secret exclusion, and negative cases before writing bounded readiness result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public readiness boundaryThe formal math readiness gate validates declared readiness metadata, tactic availability references, premise-index boundaries, target-shape routing references, provider-context recipe budgets, source-module manifests, and consumer gate cases before writing bounded public result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public verifier trace repair bundleThe formal math verifier-trace repair loop component validates public proof-lab repair evidence by checking copied Ring2 run refs and digests, verifier attempts, trace grades, repair actions, promotion gates, copied source-module manifests, toy rerun result records, secret exclusion, and seven proof/provider/oracle/human-approval negative cases before writing bounded metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public indirect prompt injection information flow policy replayThe indirect prompt-injection information-flow policy replay component validates public source-trust rows, taint-flow edges, policy verdicts, sanitized outputs, cold replay, public trace spans, negative cases, source-module digest anchors, metadata-only result records, and scope limits without using real accounts, raw prompts, account secrets, hidden system messages, live tools, model-output data, benchmark claims, source-file changes, or launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public lean std premise catalogThe Lean/Std premise index component validates a copied Lean/Std premise descriptor catalog and Ring2 premise-retrieval source body bundle by checking projection protocol refs, namespace coverage, source refs, copied body-module digests, metadata-only result record policy, negative cases, and scope limits before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public lean std premise indexThe Lean Std premise index validates premise metadata, Lean/Init source refs, copied public source manifests, forbidden proof/oracle fields, split boundaries, and metadata-only premise-index result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public source projection importsThe source projection import protocol component validates fixture and exported projection bundles by checking source refs, public target refs, content digests, per-slice source-module manifests, omission result records, scope limits, intake cell statuses, validation refs, and secret-exclusion scans before writing bounded public result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public materials lab safety replayThe materials chemistry closed-loop lab-safety replay component validates public lab-safety claim boundaries by checking candidate material refs, safety-screen refs, simulator-only assay rows, active-learning decisions, failure taxonomy refs, cold replay refs, Lab/Evolve replay graph evidence, source bundle hashes, source-module manifest digests, secret-exclusion scan, metadata-only result record policy, scope limits, and lab-safety overclaim negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public strategy hypothesis projectionThe mathematical strategy atlas hypothesis scorer validates pre-oracle strategy selection, feature-overlap routing, source-artifact consistency, copied source-module digests, unknown-strategy refusals, and metadata-only strategy result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public mcp tool authority replayThe MCP tool authority replay component validates public tool manifest scope, call metadata, approval token refs, side-effect ledger refs, rollback and cold-replay result records, untrusted-output instruction/data separation, source-module digest anchors, negative cases, metadata-only result records, and scope limits without accessing live MCP accounts, exporting account secrets or model-output data, obeying tool output as instruction, claiming benchmark safety, mutating source, or granting launch control.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public mechanistic interpretability circuit attribution replayThe mechanistic interpretability circuit-attribution replay component validates public toy-transformer attribution rows, machine-readable graph edges, causal inhibition and injection deltas, sufficiency and faithfulness limits, source-module digest anchors, negative cases, metadata-only result records, and scope limits without exporting private model weights, raw activation dumps, proprietary prompts, hidden chain-of-thought, model-output data, private model internals, benchmark claims, hosted-public claims, public sharing, or launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public axiom support boundaryThe Microcosm axiom system support-cover evaluator projects public axiom support cases, support frontiers, anti-axiom rejection mappings, principle support inheritance, and strong-gate pressure from routing, standards, doctrine, and result record evidence without proving axioms, promoting candidate law, authorizing source-file changes, or raising launch/public sharing/runtime-correctness authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public mission transaction bundleThe mission transaction work-spine component validates public work-landing and completion metadata by checking fixed Work item, claim, dependency, transaction, result record-drain, completion, scoped mutation, and checkpoint-lane fixtures, exact copied work log/work log/checkpoint/mission-control source modules, secret-exclusion boundaries, negative cases, and scope limits before writing bounded metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public route plane bundleThe navigation hologram route-plane component validates public route-plane fixture rows and exported bundle inputs by checking route projection contracts, source-coupling fingerprints, copied source-module digests and anchors, route-lease policy, entry-packet floors, affordance-passport selection, code-architecture projection packets, and secret/non-public-state scan boundaries before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public pattern assimilation stepThe pattern-assimilation step component validates refinement, nothing-to-refine, stewardship, re-entry, source-module manifest, negative-case, metadata-only result record, and scope limit contracts without promoting local lessons into broader doctrine outside their owning lanes or claiming source source authority.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public pattern bindingsThe pattern-binding contract component validates public pattern rows, source bundles, reference bundles, authority handles, exported system bundles, and route-readiness selector bundles before writing bounded result records that keep mined rows component-first and fixture-bound.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public prediction oracle reconciliationThe prediction oracle reconciliation component validates synthetic prediction packets through CP1 fork preservation, CP2 target-universe checks, pre-target evidence limits, oracle-diff grading, numeric reconciliation rows, source-module import checks, negative cases, metadata-only result records, and scope limits without forecasting correctness, investment-related actions, live market data, external model access, public sharing, launch, or performance-track-record claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates synthetic governed mutation authorizationThe proof-derived governed-mutation authorization component validates public synthetic mutation-authority proposals by checking proof-cell validator refs and evidence-chain hashes, visible pre-execution policy verdicts, ephemeral execution identity refs, logged side-effect diffs, rollback result records, cold replay result records, copied source source-module digests, non-public-state scans, and scope limits before writing bounded metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates ring2 diagnostic evidence membraneThe proof diagnostic evidence spine component validates proof-adjacent public evidence by checking Ring2 diagnostic result record refs, copied runtime artifact digests, verifier-trace and evidence-cell result record anchors, model-output data policy rows, stale source coupling, negative cases, and metadata-only result record boundaries before writing bounded diagnostic result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public context budget boundaryThe provider context recipe budget policy validates byte-bounded context recipe projection, ordered section fill, omitted-section manifests, deliverable routing, copied standard/source-module digests, negative-case refusals, and metadata-only budget result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public reveal walkthroughThe public reveal walkthrough component validates public entry material by checking reveal-step density, runnable command refs, evidence refs, claim-floor phrases, source-module manifest digests and anchors, secret-exclusion boundaries, runtime exported-bundle shape, metadata-only result records, and launch/private-equivalence/marketing negative cases before writing bounded public result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public research replication replayThe research replication rubric-artifact replay component validates public research-replication claim boundaries by checking contribution decomposition refs, rubric trees, allowed public input refs, scratch scaffolds, experiment DAG refs, metric scripts, declared artifact-hash rosters, grader reports, budget refs, ablation diffs, failure taxonomies, cold-rerun result records, public agent-execution trace spans, source-module manifest digests, metadata-only result record policy, and replication-overclaim negative cases before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public premise retrieval attributionThe Ring2 premise retrieval precision/recall harness validates copied retrieval rankings, needed-premise attribution labels, aggregate hit and recall counts, source-artifact digests, leakage guards, metric-overclaim refusals, and metadata-only retrieval-attribution result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public routing anti patterns registryThe routing anti-patterns registry component validates public routing anti-pattern rows, source-module digest anchors, private-leak rejection, negative cases, metadata-only result records, and scope limits without claiming whole-system routing correctness, route-policy mutation authority, private source authority, or launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public self ignorance coverage ledgerThe self-ignorance coverage ledger component validates known Kind Atlas coverage-debt fixtures through declared gap rows, missing-category checks, source-module digest anchors, negative cases, metadata-only result records, and scope limits while refusing unknown-unknown omniscience, absence proof, total-search proof, source-file changes, launch, public sharing, or whole-system correctness claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public sleeper memory poisoning quarantine replayThe sleeper memory poisoning quarantine replay component validates metadata-only public memory-security policy projections, poisoned-source metadata, provenance-bound write proposals, quarantine verdicts, retrieval influence gates, rollback and cold rerun result records, source-module digest anchors, negative cases, and scope limits without exporting private memory bodies, raw transcripts, live user memory, trusted promotion from untrusted context, external model access, benchmark claims, source-file changes, or launch-scope decision.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public spatial world model counterfactual simulation replayThe spatial world-model counterfactual simulation replay component validates synthetic scene-state transitions, counterfactual replay rows, source-module digest anchors, negative cases, metadata-only result records, and scope limits without claiming real-world geographic accuracy, robot operation, generated-video authority, benchmark performance, launch-scope decision, or private sensor access.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public standards meta diagnosticsThe standards meta diagnostics component validates public projection-only diagnostics over accepted-component standards inventory, runtime contracts, result record refs, source-module digest anchors, negative cases, metadata-only result records, and scope limits without becoming source authority for standards_registry, authorizing source-file changes, external model access, launch, public sharing, or whole-system correctness claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public tactic availability projectionThe tactic portfolio availability probe validates recorded tactic compile-status rows, captured probe source digests, unavailable-tactic routing pressure, negative-case refusals, and metadata-only tactic availability result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public tactic routing boundaryThe target-shape tactic routing gate validates pre-execution tactic allow/reject decisions against target shape, recorded tactic availability, source artifacts, bundle manifests, negative-case refusals, and metadata-only routing result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public tool server pressure inventoryThe tool-server pressure inventory component validates public helper-process pressure fixtures through synthetic process rows, active-owner descendant classification, owner-launch pressure rows, redaction checks, source-module digest anchors, negative cases, metadata-only result records, and scope limits without live process reads, process signalling, host mutation, external model access, launch, public sharing, private-data equivalence, or whole-system correctness claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public symbol boundaryThe undeclared library prior symbol classifier validates symbol-boundary observations against allowed premise ids, classifier policy, source-module manifests, private/proof-body exclusion, route decisions, and metadata-only symbol-boundary result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public verifier transition witnessThe verifier lab execution spine validates bounded public Lean transition rows by running the local checker on a temporary fixture, preserving accept/reject and residual-retry buckets, safety counters, source-module manifests, and redacted metadata-only result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

composes public formal math result recordsThe verifier lab kernel composes public formal-math component result records into one leak-proof aggregate result record, preserving verifier, oracle, provider, retrieval, CP2, Evolve, and contract-rejected buckets without exporting proof/provider/oracle bodies.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public voice to doctrine self improvement loopThe voice-to-doctrine self-improvement loop component validates lesson propagation through projection protocol, policy, owner-surface checks, lesson rows, source-module imports, negative cases, metadata-only result records, and scope limits without exporting source notes or private bodies, granting source/doctrine edits, live work log mutation, global-promotion authority, external model access, launch, public sharing, or whole-system correctness claims.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

validates public projection drift control boundaryThe world-model projection drift control room component validates public metadata-only projection-drift rows and copied world-model/view-quality source-module bodies by checking source refs, repair routes, validation refs, target refs, source-module digests, anchor evidence, metadata-only result record policy, negative cases, and scope limits before writing bounded result records.mechanism

Scope limit This mechanism JSON seed does not flip source authority away from core/mechanism_sources.json. Resolved code-locus paths prove filesystem grounding only, not runtime correctness or launch-scope decision.

Source Source JSON

Paper modules (93)

Longer public reference objects; bodies stay on the dedicated paper-modules page.

Verifier Lab KernelVerifier Lab Kernel is the public result record compiler for the formal-math fixture cohort. It runs or consumes named component result records, classifies proof-lab rows by authority class, preserves scope boundaries, and excludes proof/provider/oracle bodies from exported result records.paper module
Navigation Hologram Route PlaneNavigation Hologram Route Plane is the public route-surface validator for moving from a Microcosm-local control entry into browsable route projections. It checks route rows, source-coupling fingerprints, copied source-module anchors and hashes, route-lease policy, entry-packet floors, affordance-passport selection, and code-architecture projection packets while keeping full source bodies out of result records.paper module
Agent Route Observability RuntimeAgent Route Observability Runtime is the public evidence membrane for recorded agent route feedback. It checks actor-axis boundaries, selected and replacement routes, route-lease consumption, duplicate trace ids, hook-shadow advisory status, anti-pattern debt retirement, agent-principle-lens admission, egress-mirror boundaries, source-module manifests, and non-public-state exclusion while keeping transcript, provider, browser, HUD, account, account secret, and live-hook bodies out of result records.paper module
Agent Benchmark Integrity Anti-Gaming ReplayAgent Benchmark Integrity Anti-Gaming Replay is the public benchmark-claim boundary for Microcosm. It checks locked evaluator ids and config hashes, declared benchmark case rosters, replay rows, file-access and contamination refs, trusted-reference score refs, output-replay refs, computed-vs-declared integrity verdicts, three copied source pattern provenance bodies, and eleven anti-gaming negative cases while keeping private issue, oracle patch, hidden-gold, provider, raw patch, and score payload bodies out of result records.paper module
Research Replication Rubric Artifact ReplayResearch Replication Rubric Artifact Replay is the public research-replication claim boundary for Microcosm. It checks contribution decomposition refs, rubric trees, allowed public inputs, scratch repo scaffolds, experiment DAG refs, metric scripts, declared artifact-hash rosters, artifact hashes, grader reports, compute/runtime budgets, ablation diffs, failure taxonomies, cold-rerun result records, public agent-execution trace spans, four copied source modules, and eight replication-overclaim negative cases while keeping private paper/data bodies, hidden rubrics, model-output data, original-author code bodies, benchmark claims, and public-sharing claims out of result records.paper module
Agentic Vulnerability Discovery Patch-Proof ReplayAgentic Vulnerability Discovery Patch-Proof Replay is the public security-claim boundary for Microcosm. It checks projection protocol, vulnerability policy, synthetic target refs, issue hypotheses, trace evidence, abstract exploitability refs, patch diff refs, regression tests, verifier result records, sandbox verdicts, false-positive triage, cold replay, public agent-execution trace spans, secret-exclusion scan, nine copied source/control/standard/tool bodies, source-module manifest digests, metadata-only result record policy, and eight security-overclaim negative cases while keeping live targets, real CVE exploitation, weaponized payloads, account secrets, network exfiltration steps, actionable exploit instructions, model-output data, raw issue or patch bodies, benchmark claims, and source-file changes out of result records.paper module
Materials Chemistry Closed-Loop Lab-Safety ReplayMaterials Chemistry Closed-Loop Lab-Safety Replay is the public lab-safety claim boundary for Microcosm. It checks candidate material refs, safety-screen refs, simulator-only assay refs, active-learning decisions, failure taxonomy refs, cold replay refs, source bundle hashes, Lab/Evolve replay graph evidence, copied source/control/result record/standard bodies, metadata-only result record policy, and eight lab-safety overclaim negative cases while keeping wetlab protocols, hazardous synthesis steps, reagent quantities, controlled or bioactive targets, live lab account secrets, robot commands, private lab notebook bodies, live assay data, discovery claims, benchmark claims, model-output data, source notes, and launch-scope decision out of result records.paper module
Certificate Kernel Execution LabCertificate Kernel Execution Lab is the public proof-adjacent execution boundary for Microcosm. It checks a Lean/Lake certificate-kernel fixture, generated certificate rows, analyzer metadata, transition traces, typed CP2 action translations, bounded Evolve reruns, source-module manifest digests, copied Lean/tool/profile bodies, metadata-only result record policy, and four negative cases while keeping proof bodies, raw tactic scripts, model-output data, oracle ideal answers, oracle-needed premise ids, private source paths, stdout/stderr bodies, account secrets, private Erdos #257 proof bodies, launch-scope decision, benchmark solve-rate, and general theorem-proof authority out of result records.paper module
Corpus Readiness Mathlib Absence GateCorpus Readiness Mathlib Absence Gate is the public formal-math corpus readiness boundary for Microcosm. It checks copied PROVER smoke-run corpus readiness rows, Lean/Std toolchain probe rows, Mathlib absence status, consumer-gate decisions, absent corpus blocking, source-module manifest digests, metadata-only result record policy, and five negative cases while keeping proof bodies, model-output data, non-public source refs, benchmark-completeness claims, launch-scope decision, and Mathlib proof authority out of result records.paper module
Pattern Binding ContractPattern Binding Contract is the public system membrane for mined pattern rows. It validates binding fields, source bundles, reference bundles, authority-chain handles, secret-exclusion scans, exported system bundles, and route-readiness selector overlays, then writes bounded result records that keep private bodies out and prevent individual pattern rows from becoming standalone public leaves.paper module
Bridge Phase Continuity RuntimeBridge Phase Continuity Runtime is the public observe/apply continuity membrane for detached work. It consumes synthetic transport fixtures, validates copied observe-runtime body digests, writes five metadata-only result records, checks seven negative-case classes, and keeps heartbeat/resume evidence below work-landing, provider, UI, source-file changes, and launch-scope decision.paper module
Cognitive Operator RegistryCognitive Operator Registry is the public evidence membrane for reusable cognition as typed system. It validates public operator rows, dogfood result records with cognition-delta evidence, negative cases for missing fields, missing dogfood, sprawl, operator-voice claims, authority overclaims, and private-source leakage, then checks copied source registry, standard, and validator bodies by digest while keeping bodies out of result records.paper module
Agent Completion Faithfulness AuditAgent Completion Faithfulness Audit is the public fixture witness for completion evidence language. It builds a fixture repo, verifies commit and HEAD evidence with git subprocesses, runs pytest for the declared span, checks cap claims against a fixture ledger, validates a copied source-module manifest for agent experience diagnostics, and writes bounded result records that keep source bodies out.paper module
Cold-Reader Route MapCold-Reader Route Map is the public first-run route membrane. It validates route rows, route-to-result record bindings, ordinal first-run sequencing, command/docs/result record refs, launch/provider/private-source overclaim rejection, exact copied source cold-entry source modules, and metadata-only result records so a cold agent can see what to run first and what proof bounds each row.paper module
Proof Diagnostic Evidence SpineProof Diagnostic Evidence Spine is the public evidence membrane before formal proof authority. It validates Ring2 failure-taxonomy and graph-update artifacts, verifier-trace repair and evidence-cell result record refs, copied runtime artifact digests, model-output data policy rows, negative cases, and a copied public component source-body floor while keeping proof bodies and provider output bodies out of public result records.paper module
Proof-Derived Governed Mutation AuthorizationProof-Derived Governed Mutation Authorization is the public mutation-authority replay contract. It checks three synthetic proposals, proof-cell validator refs, visible policy verdicts, side-effect logs, rollback result records, cold replay, eight negative cases, and six exact copied source pattern/result record/internal control bodies while keeping account secrets, proof bodies, model-output data, account refs, source-file changes, and launch-scope decision out of result records.paper module
Durable Agent Work-Landing ReplayDurable Agent Work-Landing Replay is the public work-spine replay contract for agent landing claims. It checks claimed paths, owner-native validation refs, commit-attempt order, HEAD-before/after evidence, metadata-blocked rows, work log finalizer evidence, nine negative cases, and six exact copied source source bodies while keeping raw diffs, non-public paths, model-output data, and source bodies out of result records.paper module
Work Landing Control SpineWork Landing Control Spine is the public source-open import for work-landing internal control bodies. It validates copied work_landing, work_landing_status, mission transaction preflight, landing preflight, and scoped-commit source modules by manifest digest, required anchors, no-live-mutation contract flags, secret-exclusion scan, and metadata-only result record policy while keeping live Git, work log, work log, claim launch, shared-index mutation, private-index execution, external model access, public sharing, and launch-scope decision out of scope.paper module
Executable Doctrine GrammarExecutable Doctrine Grammar is the public grammar membrane for doctrine-shaped runtime fixtures. It validates standard row fields, paper-module teleology and result record sections, duplicate-slug and overclaim negative cases, exact copied executable-grammar, standards-registry/type-plane, lattice, kind-atlas, and standards option-surface bodies, then emits metadata-only result records with source refs, digests, counts, and scope limits.paper module
Source Projection Import ProtocolSource Projection Import Protocol is the public import membrane for source-backed Microcosm growth. It validates fixture and exported projection bundles by checking source refs, public target refs, content digests, source-to-target relations, per-slice source-module manifests, validation refs, omitted-material result records, metadata-only result record policy, secret-exclusion scans, projection cell statuses, and negative cases while keeping true private bodies, model-output data, launch material, and static count claims out of public authority.paper module
Mission Transaction Work SpineMission Transaction Work Spine is the public replay membrane for Microcosm work-landing discipline. It checks fixed Work item, claim, dependency, transaction, result record-drain, completion, scoped mutation, and checkpoint-lane rows; validates copied work log, work log, checkpoint, scoped-commit, and mission-preflight source modules by manifest; and writes metadata-only result records with secret-exclusion and scope limits.paper module
Formal Math Readiness GateFormal Math Readiness Gate is the public readiness membrane before downstream proof work. It checks declared Mathlib and corpus readiness, tactic probe result records, proof-metadata-only premise indexes, target-shape routing, provider context budgets, formal_math_readiness_extensions intake rows, copied PROVER smoke-run artifacts, public component source body imports, digest manifests, secret exclusion, and negative cases, then emits readiness boards rather than theorem evidence.paper module
Formal Math Lean Proof WitnessFormal Math Lean Proof Witness is the public runtime crossing from readiness metadata into a real local Lean/Lake subprocess witness. It copies a bounded public Lake project, records tool availability, Lake build status, source hashes, declaration names, line counts, source-module manifest verdicts, a Mathlib-blocked debt row, and four leakage/invalid-proof negative cases while keeping proof bodies and command output bodies out of result records.paper module
Formal Math Verifier Trace Repair LoopFormal Math Verifier Trace Repair Loop is the public evidence membrane for proof-lab repair mechanics. It checks copied Ring2 run refs and digests, verifier attempts, trace grades, repair actions, promotion gates, source-module manifests, secret exclusion, and seven leakage or overclaim negative cases, then writes metadata-only result records that keep proof bodies, oracle premise ids, model-output data, Lean/Lake execution, and theorem-correctness claims out of scope.paper module
Formal Evidence Cell Anchor ResolverFormal Evidence Cell Anchor Resolver is the evidence-legibility membrane for Microcosm's formal math claims. It resolves three paper claims to public evidence-cell ids, checks source-anchor and machine-anchor metadata, anchors the verifier-trace cell to real Ring2 verifier-trace repair result records, validates six copied source-open body modules, observes seven proof/private/human-approval/theorem-correctness negative cases, and emits metadata-only result records that make proof-language boundaries inspectable without becoming proof authority.paper module
Formal Math Premise RetrievalFormal Math Premise Retrieval is the source-backed retrieval slice between the Lean/Std premise catalog and proof-witness boundary. It validates eleven public premise descriptors, four retrieval queries, forty-four considered candidates, exact and source-faithful source body imports, context recipe byte budgets, strategy ids, card freshness, and five leakage/overclaim negative cases while keeping proof bodies, oracle premise ids, model-output data, Lean/Lake execution, and launch claims out of result records.paper module
Lean/Std Premise IndexLean/Std Premise Index is the source-open formal-math catalog component for Microcosm. It imports a premise descriptor index, validates eleven Lean/Std premise rows across Nat, Bool, List, and Iff namespaces, checks six copied body modules through a source-module manifest, observes Mathlib/proof-body/oracle/test-split/source-ref negative cases, and writes metadata-only result records that make premise system inspectable without turning metadata into proof authority.paper module
World-Model Projection Drift Control RoomWorld-Model Projection Drift Control Room is the public projection-drift boundary for Microcosm. It validates eight drift rows, source refs, repair routes, validation refs, target refs, source-module digest evidence, copied world-model and view-quality source bodies, secret-exclusion policy, and eight negative cases while keeping private runtime bodies, model-output data, live repair, source-file changes, automatic doctrine changes, launch, public sharing, and source-authority claims out of scope.paper module
Public Reveal WalkthroughPublic Reveal Walkthrough is the source-backed public-entry membrane for Microcosm. It checks the declared reveal steps, runnable command set, evidence refs, claim-floor phrases, secret-exclusion scan, source-open body import manifest, runtime-bundle shape, and four overclaim negative cases while keeping copied bodies out of result records and launch/provider/private-equivalence claims out of scope.paper module
Standards Meta DiagnosticsChecks accepted adapter-backed components against standards_inventory/organ_runtime_contracts/diagnostic_policy; rejects 5 boundary failures (missing standard_id/standard_ref, missing inventory row, missing result record ref, launch/provider/public sharing overclaim, private-body leak); secret_exclusion_scan with body_in_receipt:false and synthetic_receipt_standin_allowed:false.paper module
Finance Forecast Evaluation SpineRuns admissible forecast-evaluation statistics (Diebold-Mariano loss-differential, Harvey-Leybourne-Newbold small-sample correction, Hansen SPA with recentering, Politis-Romano stationary bootstrap, Bartlett HAC long-run variance, purged/embargoed CV) over synthetic market-shaped fixtures and copied source bodies; refusal discipline returns typed refusals (horizon>=sample length, too-small samples, leakage-prone splits, missing SciPy, advice-shaped claims) instead of crashing; computed-statistic and refused-because-inadmissible are both valid validator outcomes.paper module
Engine Room DemoWraps the bundles under microcosm_core.engine_room, verifies the 14 controller-selected jewel targets, checks each owned staged bundle surface (module source, fixture input, fixture manifest, paper module, standard, tests), executes the staged demo through the public fixture chain, and observes a negative fixture where an expected target is intentionally absent.paper module
Agent Memory Temporal-Conflict ReplayPublic Microcosm projection of an agent-memory honesty contract. Replays synthetic episodes (a scoped preference later contradicted) and validates temporal-conflict resolution, negative cases, non-public-state exclusion, and scope limits with metadata-only result records.paper module
Agent Monitor Redteam Falsification ReplayPublic Microcosm regression drilldown for a monitor/redteam honesty contract. Replays synthetic monitor traces and validates redteam-falsification behavior, negative cases, non-public-state exclusion, and scope limits with metadata-only result records.paper module
Agent Sabotage Scheming-Monitor ReplayDrilldown-only regression contract for synthetic sabotage/scheming monitor claims. Checks projection_protocol, scheming_monitor_policy, task_episodes, action_traces, monitor_scores, counterfactual_replay, and cold_replay against negative cases and scope limits.paper module
Agent Sandbox Policy-Escape ReplayValidator-backed public refactor of the source agent_execution_trace system for sandbox/security claims. Computes metadata-only trace spans from action requests, pre-execution policy verdicts, side-effect diff result records, and rollback against negative cases and scope limits.paper module
Belief-State Process Reward ReplayPublic Microcosm projection of a belief-state process-reward claim contract. Backed by the public agent-execution trace refactor lane plus copied source source bodies; validates trajectory groups, cold replay result records, negative cases, and scope limits.paper module
Sleeper Memory Poisoning Quarantine ReplayPublic Microcosm projection of a persistent-memory security claim contract. Replays synthetic memory-poisoning episodes and validates quarantine behavior, audit refs, rerun result records, negative cases, and scope limits with metadata-only result records.paper module
Indirect Prompt-Injection Information-Flow Policy ReplayValidator-backed public claim contract for indirect prompt-injection information-flow policy. Admits one narrow claim: a source-faithful trace refactor separated trusted instructions from untrusted web/tool/browser text before any privileged action or answer, checked against negative cases and scope limits.paper module
MCP Tool Authority ReplayPublic Microcosm projection of a tool-authority claim contract. Replays a synthetic MCP-like tool-authority scenario and validates replay result records, negative cases, and scope limits with metadata-only result records.paper module
Tactic Portfolio AvailabilityTactic Portfolio Availability Probe validates copied Lean/Std tactic affordance rows before downstream routing can treat a tactic as usable. It checks compile status, Mathlib absence handling, probe portfolio membership, negative cases, source digests, and metadata-only result records while keeping proof bodies, model-output data, benchmark claims, and launch-scope decision out of scope.paper module
Target Shape Tactic RoutingTarget Shape Tactic Routing is the pre-execution gate between tactic availability and proof attempts. It validates Ring2 problem-domain, failure-class, graph-update, and tactic-probe references, rejects unavailable or unprobed tactics, and records metadata-only route decisions before any Lean/Lake proof authority is claimed.paper module
Ring-2 Premise Precision RecallRing-2 Premise Precision Recall validates copied Ring2 retrieval rankings against after-the-fact metric labels. It computes precision/recall classes, rejects oracle-label leakage and tuning shortcuts, and keeps proof bodies, model-output data, benchmark claims, and theorem-correctness claims outside the public result record boundary.paper module
Mathematical Strategy AtlasMathematical Strategy Atlas scores public problem features into explicit pre-oracle strategy hypotheses before retrieval or proof execution. It validates strategy ids, copied public source tool bodies, retrieval-term effects, oracle-label exclusion, negative cases, and metadata-only result records while keeping proof and provider authority out of scope.paper module
Verifier Lab Execution SpineVerifier Lab Execution Spine records bounded public Lean transition execution evidence: command intent, tool facts, return codes, result record refs, omitted dangerous payload fields, negative cases, and source-open body imports. It separates real execution evidence from formal-result correctness, provider text, oracle answers, proof-body exposure, source-file changes, and launch-scope decision.paper module
Bounded Autonomy Campaign PacketBounded Autonomy Campaign Packet validates public campaign packet fixtures: proposed gaps, policy gates, repeated-failure digests, negative cases, source-open body imports, and scope limits. It keeps campaign proposals separate from self-repair, source writes, live scheduling, external model access, launch-scope decision, public sharing, and whole-system correctness.paper module
Computer-Use Action Trace ReplayComputer-Use Action Trace Replay validates a synthetic computer-use episode through visible observations, affordances, action rows, authority verdicts, state-transition and recovery result records, cold replay rows, public trace spans, source-module manifests, negative cases, and metadata-only result records. It is a reader-facing contract under Agent Route Observability Runtime, not live browser or desktop control.paper module
Concurrency Mission ControlConcurrency Mission Control validates the public concurrency mission-control membrane: copied source-builder digests, bridge artifacts, failure classes, work log seed-speed topology, heartbeat and claim-collision anchors, negative cases, source-open body imports, and metadata-only result records. It separates coordination evidence from hosted orchestration, external model access, live scheduling, private-system equivalence, source authority, launch, public sharing, and production concurrency guarantees.paper module
Doctrine Fact Claim AuditDoctrine Fact Claim Audit validates public doctrine fact assertions against declared sections, numeric claim gates, code-locus anchors, route DAG fixtures, negative cases, source-open body imports, and scope limits. It lowers claim strength to fixture truth: fact assertion, code-loci, and DAG evidence are checked, but the component does not become a comprehension engine, minimum-read graph, doctrine saturation proof, source-file changes lane, or launch-scope decision.paper module
Self-Ignorance Coverage LedgerSelf-Ignorance Coverage Ledger validates a public known-debt coverage fixture: declared Kind Atlas gaps, missing coverage categories, negative cases, source-open body imports, and scope limits. It records what the system knows it has not covered without claiming omniscience, absence proof, total search, source-file changes, public sharing, launch-scope decision, or whole-system correctness.paper module
Tool Server Pressure InventoryTool Server Pressure Inventory validates the public tool-server pressure membrane: synthetic process rows, active-owner descendants, over-budget owner launch requests, redaction findings, source-module digests, metadata-only result records, negative cases, and scope limits. It treats pressure inventory rows as fixture evidence, not live process control, process signalling, host mutation, provider authority, launch-scope decision, public sharing, or whole-system correctness.paper module
Mechanistic Interpretability Circuit Attribution ReplayMechanistic Interpretability Circuit Attribution Replay checks that public circuit-attribution replay rows carry feature-to-edge links, intervention deltas, sufficiency and faithfulness limits, target/source refs, source-module digest evidence, secret-exclusion scans, negative cases, and scope limits. It validates the result record contract only, not live model transparency, private weights, raw activations, proprietary prompts, hidden reasoning, external model access, benchmark claims, launch, public sharing, or whole-system correctness.paper module
Spatial World Model Counterfactual Simulation ReplaySpatial World Model Counterfactual Simulation Replay validates public synthetic counterfactual rows: scene-state refs, action traces, predicted-state refs, transition diffs, oracle-check refs, public sensor-packet refs, limitation labels, source-module digest evidence, negative cases, and scope limits. It keeps generated-video and metadata evidence below real-world geographic accuracy, robot or AV operation, simulator product claims, benchmark claims, external model access, hosting, launch, public sharing, and whole-system correctness.paper module
Prediction Oracle ReconciliationPrediction Oracle Reconciliation validates synthetic prediction packets through CP1 fork preservation, CP2 target-universe checks, pre-target evidence limits, oracle-diff grading, bounded dossier edits, numeric reconciliation rows, source-module imports, negative cases, and scope limits. It is a projection-mechanics replay, not a forecasting correctness claim, investment or trading decisions, live market data call, external model access, private-data equivalence, public sharing, launch, or whole-system correctness.paper module
Provider Context Recipe BudgetProvider Context Recipe Budget validates provider-context recipe mechanics: fixed byte ceilings, ordered section fill, omitted-section manifests, deliverable routing, digest-checked source-body imports, forbidden-body rejection, negative cases, and scope limits. It emits context metadata and verdicts only, without provider/API authorization, Lean/Lake execution, proof or oracle truth-side material, formal-result correctness, domain-level conclusions, launch, public sharing, or whole-system correctness.paper module
Undeclared Library Prior ClassifierUndeclared Library Prior Classifier validates copied Lean/Std premise rows and pre-extracted symbol observations, classifying undeclared library priors and premise-budget violations with route outcomes, source-module digest checks, secret-exclusion scans, negative cases, and scope limits. It does not read proof source, run Lean or Lake, prove formal-result correctness, treat the whole standard library as an implicit allowlist, claim Mathlib availability, use external model services, launch, publish, or prove whole-system correctness.paper module
Voice to Doctrine Self-Improvement LoopVoice to Doctrine Self-Improvement Loop validates whether declared lessons refined a named owner surface with validation or were captured with a re-entry condition. It checks projection protocol, policy, owner surfaces, lesson rows, negative cases, source-open body imports, and scope limits while rejecting source notes export, private thread bodies, model-output data, direct doctrine-node edits, unvalidated global promotion, live work log mutation, public sharing, launch, and whole-system correctness.paper module
Routing Anti-Patterns RegistryRouting Anti-Patterns Registry validates the public routing anti-pattern registry contract: kind/version, unique row ids, text fields, required navigation anchors, source-module digest evidence, negative cases, and scope limits. It treats the registry as a checked public artifact, not route source authority, route mutation authority, private routing-note export, provider authority, launch, public sharing, or whole-system correctness.paper module
Set 8 Audio Level RMS PortSet 8 Audio Level RMS Port ports the Swift AudioLevelMonitor normalizedLevel RMS calculation into a bounded Python component and checks float, int16, clamp, empty-buffer, and unsupported-format cases over public synthetic sample arrays. It carries source-module refs, digests, anchors, sample counts, parity verdicts, negative cases, and an scope limit while excluding AVCaptureSession startup, microphone permission, recorded audio, device state, UI readiness, source-file changes, launch, public sharing, and whole-system correctness.paper module
Set 8 Compliance Pipeline BundleSet 8 Compliance Pipeline Bundle imports compliance scanner registry, bounded compliance ledger builder, and observe-loop pipeline helper bodies into a runnable component. It checks registry shape, bounded no-write compliance checks, baseline scanner truth accounting, pure pipeline helper behavior, source-module digests, negative cases, and scope limits while excluding full compliance-ledger refresh, bridge/external model access, source note mutation, repository mutation, launch, public sharing, and complete compliance proof.paper module
Set 8 Policy Engines BundleSet 8 Policy Engines Bundle imports Lab contract audit red/green gating, market-fusion fail-closed claim preflight, and campaign dispatch transition adjudication as exact copied source bodies with bounded public exercises. It checks source-module manifests, stable negative cases, exercise outcomes, source digests, and scope limits while excluding live campaigns, external model access, repository mutation, private artifact export, market-level conclusions, launch, public sharing, and whole-system safety.paper module
Set 8 Structural Theses BundleSet 8 Structural Theses Bundle imports tools/finance/structural_theses.py as exact copied source source and exercises CP1/CP2 thesis-family validation over public synthetic winner, loser, and control rows. It checks source digest parity, anchors, public family evidence, loser evidence, negative controls, survivor-only rejection, forward-gate-breach rejection, control-leak rejection, runtime verdicts, and scope limits while excluding financial decisions, investment recommendations, live market data, external model access, portfolio action, launch, public sharing, and whole-system correctness.paper module
Set 8 Tools-Tail Primitives BundleSet 8 Tools-Tail Primitives Bundle imports observer set diffing, JSON patch interpretation, ledger identity hashing, and shadow envelope parse coverage as exact copied source source bodies with bounded public exercises. It checks source-module manifests, stable negative cases, exercise outcomes, mechanism rows, digests, and scope limits while excluding GodMode execution, external model access, live bridge work, repository mutation, private lab artifact export, oracle truth, launch, public sharing, and whole-system correctness.paper module
Set 8 Validator Checker BundleSet 8 Validator Checker Bundle imports the real idea_microcosm validators body and exercises policy well-formedness, status transition judging, private-boundary scanning, zero-failure, specimen, launch-gate, source-bundle, source-shuttle, concurrency, native-guard, launch-root compiler, and no-write validate entrypoint groups. It carries source anchors, public runtime-only evidence, negative cases, and scope limits while excluding launch-scope decision, hosted-public proof, source-file changes, full validator-suite proof, external model access, public sharing, and whole-system correctness.paper module
Set 12 Market Dashboard Read-Model BundleSet 12 Market Dashboard Read-Model Bundle runs market-dashboard read-model over public synthetic fixtures. It validates market dashboard import stubs, validator-case derivation, runtime feed freshness overlays, related-situation rows, source anchors, digest checks, negative cases, and scope limits while excluding launch-scope decision, external model access, private-system equivalence, live market-level conclusions, investment-related actions, public sharing, and whole-system correctness.paper module
Set 12 Prediction Market Board BundleSet 12 Prediction Market Board Bundle runs prediction-market board and quant-mart diagnostics over public synthetic fixtures. It validates prediction-market joins, Polymarket identity by slug, provider drift monitors, missingness boards, prior green deltas, source lifecycle vintage enrichment, source-module digests, negative cases, and scope limits while excluding launch-scope decision, external model access, private-system equivalence, market-level conclusions, provider truth, investment-related actions, public sharing, and whole-system correctness.paper module
Set 12 launch claim-Language GateSet 12 launch claim-Language Gate runs launch claim-language over public fixtures. It classifies phrases against evidence class and scope limit, checks typed ordinal evidence ranks, real-system flags, fail-closed defaults, boundary-context negation, main --assert-clear behavior, source digests, negative cases, and scope limits while excluding launch-scope decision, external model access, private-system equivalence, market-level conclusions, investment-related actions, public sharing, and whole-system correctness.paper module
Set 10 Cold Eval Honesty BundleSet 10 Cold Eval Honesty Bundle imports the real cold_eval.py source body and runs its route-quality simulator over a synthetic public workspace. It audits the all-B idea-first scorecard shape, expected-ref injection policy, private fixture refs, missing-task refusals, negative cases, and scope limits while excluding live benchmark results, navigation truth, hosted readiness, launch-scope decision, external model access, source-file changes, and whole-system correctness.paper module
Set 10 Live Source Drift BundleSet 10 Live Source Drift Bundle imports exact current internal control Python bodies after source source drift. It validates stale-versus-current digest rows, copied-source compileability without import execution, required behavioral anchors, source-manifest boundaries, negative cases, and scope limits while excluding route authority, work log or work log mutation authority, mission execution, git approval, source-file changes, launch, public sharing, external model access, and non-public runtime export.paper module
Set 7 Source Engines BundleSet 7 Source Engines Bundle binds the accepted batch7_macro_engines_capsule component to its public source-open bundle. It checks copied trace parser, codemap layout, DAG scheduling, launch-root, source-surgeon, clean-clone, calculator, PageRank, and regression-selection witnesses, negative cases, digest boundaries, and scope limits while excluding launch-scope decision, private-system equivalence, semantic truth, investment-related actions, sandbox completeness, and selected-test sufficiency proof.paper module
Set 9 Source Engines BundleSet 9 Source Engines Bundle binds the accepted batch9_macro_engines_capsule component to its public source-open bundle. It checks thirteen copied source engines for provenance lineage, approval adjudication, Python AST indexing, finance headline clustering, mission graph compilation, dependency pin drift, config authority audit, heterogeneous edge extraction, WorkAtlas aggregation, host-pressure admission, doctrine enrichment, worker job budget gating, and milestone-relative quality accounting while excluding live lineage truth, approval authority, market/news truth, host-state truth, work log truth, external model access, source-file changes, public sharing, and launch-scope decision.paper module
Pattern AssimilationPattern Assimilation binds the accepted pattern_assimilation_step component to the public sign-off validator, first-wave fixture, exported assimilation bundle, source-module manifest, standard row, and metadata-only result records. It checks same-lane completion decisions, owner-surface refinement evidence, stewardship and re-entry fields, duplicate result record rejection, local-lesson scope limits, source note exclusion, copied body imports, and public-relative result record paths while excluding live ledger mutation, source notes ingestion, model-output data, global doctrine changes, launch, public sharing, behavior-change proof, and private-data equivalence.paper module
Set 10 Governance And Compilers BundleSet 10 Governance And Compilers Bundle binds the accepted batch10_governance_compilers_capsule component to a refreshed source-open bundle. It exercises governed-mutation intent, observe/apply compilation, public-proof review, launch blocker triage, public sharing path contracts, result record reuse, no-lookahead horizons, session-wave execution, claim-conflict wait tax, role-aware DAG blocking, frontend table shaping, reference grouping, recent-change coalescing, and the deferred Set-9 lane-width repair while preserving copied source digests, negative cases, and scope limits.paper module
Set 11 Saturation Engines BundleSet 11 Saturation Engines Bundle binds the accepted batch11_saturation_engines_capsule component to a refreshed source-open bundle. It exercises run-affinity scoring, calculator cluster insight derivation, std_python delta gating, exogenous navigation grading, portability supersession rollup, shard browse priority, holographic evidence selection, projection secret scanning, stockgrid flow normalization, source-regime board bucketing, frontend wayfinding, agent-session diagnostic lenses, and demo-take coverage auditing while preserving copied source digests, computed negative probes, and scope limits.paper module
Set 4 Proof, Authority, and Runtime BundleSet 4 Proof, Authority, and Runtime Bundle binds the accepted batch4_proof_authority_runtime component to a refreshed source-open bundle. It exercises Lean strategy-control and prover-skill witnesses, VeriSoftBench harness and calibration rows, Erdos #257 certificate-kernel static checks, Lean packet integrity, reasoning grant and plan authority fences, forward-integration policy, completion executor deferral, Codex driver and idle heartbeat diagnostics, metabolism claim logs, taskpolicy passthrough, and context-yield attribution while preserving copied source digests, bounded negative cases, and scope limits.paper module
Set 6 Unsurfaced Primitives BundleSet 6 Unsurfaced Primitives Bundle binds the accepted batch6_unsurfaced_primitives_capsule component to source-open primitive exercises. It checks source note keyphrase scoring, schema-loose distillation, operator handoff linkage, observed-turn window merging, market situation graphs, finance numeric assurance, fail-closed policy judgment, clone-local concurrency, market-clock scheduling, provider-recovery scoping, and demo-take temporal remapping while preserving public fixture inputs, exact-source digest expectations, negative cases, and scope limits.paper module
Engine Room Public Projection Leak GateEngine Room Public Projection Leak Gate is a DLP-style projection boundary. It scans rendered public projection files and paths, checks symlink escapes, records policy-exception hits as hash-only evidence, reports optional gitleaks status, and validates two positive plus three negative fixture cases without copying sensitive payloads, approving launch, or claiming general security, prompt-injection, sandbox, or information-flow authority.paper module
Set 5 Authority and Systems BundleSet 5 Authority and Systems Bundle binds the legacy Markdown projection, Set 5 runnable source locus, exported copied-source bundle, source-module digests, synthetic negative exercises, metadata-only result records, and scope limits to a mechanism-backed JSON bundle. It covers post-execution result record validation, reasoning replay scope and lineage, verifier-gated Lean repair harnessing, process orphan classification, generated-state fixpoint settlement, trace-tape compaction, code blast radius, and doctrine graph compilation while preserving fixture boundaries.paper module
Set 7 Oracle Sibling BundleSet 7 Oracle Sibling Bundle binds the runnable Oracle sibling source locus, exported copied-source bundle, source-module digests, original pytest witnesses, deterministic subject-index/snapshot/truth-diff/quartet-plan exercises, negative cases, metadata-only result records, and scope limits to a mechanism-backed JSON bundle without claiming accepted-component authority or semantic truth authority.paper module
Set 7 Demo Take Console BundleSet 7 Demo Take Console Bundle binds the runnable Demo Take Console source locus, exported copied Swift source bundle, source-module digests, SwiftPM build-witness posture, deterministic recording-state/helper-bridge/recorder-store/hotkey-audio-meter/transcribe-payload exercises, negative cases, metadata-only result records, and scope limits to a mechanism-backed JSON bundle without claiming accepted-component authority, app launch authority, or recording authority.paper module
Engine Room Generated Projection Drift GateEngine Room Generated Projection Drift Gate is a generated-artifact freshness bundle. It validates projection owner selection from changed paths, declared source and artifact fingerprints, no-write check return codes, source-hash cache reuse, planted-byte detection, and missing-artifact failure over four public fixtures while keeping semantic drift proof, repair authority, full source registry validation, launch, and private-system claims out of scope.paper module
Engine Room Command-Run SingleflightEngine Room Command-Run Singleflight is a subprocess singleflight bundle. It validates content-addressed command keys, scoped dirty/content fingerprints, fcntl leader/follower election, completed-run reuse, captured output replay, and two negative boundaries over fixture commands while keeping scheduler, daemon, distributed-lock, live-state export, launch, and private-system claims out of scope.paper module
Engine Room Metabolism RuntimeEngine Room Metabolism Runtime explains the metabolism runtime component inside the accepted Engine Room demo. It exercises synthetic SQLite queue state, lease recovery, blackboard claim projection, and cold-start reconciliation fixtures without exporting private runtime state or dispatching providers.paper module
Engine Room Bridge Campaign DAGEngine Room Bridge Campaign DAG binds the staged pre-dispatch campaign validator to the accepted Engine Room demo mechanism. It validates typed probe/reducer/synthesis graphs, rejects cycles, requires synthesis nodes to trace back to probe evidence, checks provider parallelism ceilings, and emits public fixture result records without dispatching providers or proving campaign execution safety.paper module
Engine Room Reference Knowledge RouterEngine Room Reference Knowledge Router binds the staged reference-routing bundle to a concrete mechanism. It scores structured routing metadata, family text, open-first summaries, and curated notes over public fixtures, then rejects domain-mismatch and empty-query cases without cloning repositories, exporting private reference material, or claiming BM25, TF-IDF, embedding, license, launch, or private-system authority.paper module
Engine Room Derived Fact Provider EngineEngine Room Derived Fact Provider Engine binds the staged derived-fact bundle to a concrete mechanism. It resolves JSON-pointer, glob-count, and git-backed callable fact rows over public fixture roots, records provider errors as repairable data, and keeps derived-fact availability below truth-audit, semantic-claim-validation, full source registry, launch, and private-system authority.paper module
Engine Room Egress Self-Compliance GateEngine Room Egress Self-Compliance Gate binds the staged egress bundle to a concrete mechanism. It detects permission ceremony without a real blocker, self-error statements without durable capture, and command handoff language without execution evidence over public fixtures, while accepting bounded blocker or result record language and refusing taint-analysis, prompt-injection-defense, sandbox, information-flow, launch, and private-system claims.paper module
Engine Room Lean Proof Search LabEngine Room Lean Proof Search Lab binds the staged proof-search bundle to a concrete mechanism. It runs tiny public Lean statements through symbolic tactic search, statement-only candidate scoring, problem-id ablation, forward oracle-body rejection, and axiom cleanliness checks, while keeping private source run state, oracle proof bodies, neural theorem proving, frontier-scale automation, launch, and private-system authority out of scope.paper module
Engine Room Navigation Fitness BenchmarkEngine Room Navigation Fitness Benchmark binds the staged navigation-fitness bundle to a concrete mechanism. It evaluates public route-packet fixtures for expected stable-id recall, precision, forbidden first routes, latency budgets, scent terms, and debt candidates without running the private kernel, validating embeddings, claiming universal benchmark authority, or upgrading launch/private-system status.paper module
Cold Clone ProbeCold Clone Probe is the public source-root bootstrap membrane. It binds bootstrap.sh, src/microcosm_core/cold_clone_probe.py, the first-wave pattern-binding fixture, the secret-exclusion scan, public relative result record refs, and focused tests so a fresh checkout has one bounded proof of first-run mechanics before install, CI, hosted launch, or full component inventory review.paper module
First-Screen Composition RootFirst-Screen Composition Root is the public entry-card contract for Microcosm. It binds the package card helper, CLI emitter, standard, README entry order, reader branch ids, doctrine-effect frame, omission result record, observatory landing refs, text projection, and focused tests so a cold reader sees what to inspect first without treating counts as maturity scores or route cards as launch, hosted-public sharing, provider, source-file changes, private-equivalence, or whole-system proof.paper module
Set 7 Secondary Runtime BundleSet 7 Secondary Runtime Bundle binds the accepted batch7_secondary_runtime_capsule component to copied runtime view-model, lane-progress, graph-lens, graph-projection, cartography, stockgrid, and Polymarket source bodies. It exercises eight fixture engines, source digest anchors, required anchors, UI witness metadata, synthetic runtime packets, synthetic market rows, negative cases, and scope limits while excluding browser/session export, wallet authority, live market data, investment-related actions, external model access, launch-scope decision, private-system equivalence, semantic truth, and complete UI or ranking coverage.paper module
Microcosm Axiom SystemMicrocosm Axiom System is the public doctrine/routing boundary for axiom support. Its bundle binds the authored paper-module projection to the axiom support-cover mechanism and validator locus, with source refs to AXIOMS.md, PRINCIPLES.md, ANTI_PRINCIPLES.md, core/axiom_organ_routing.json, standards/std_microcosm_axiom.json, and focused tests. The validator computes support cases, anti-axiom rejection mappings, candidate pressure, and strong-gate pressure as a read-only projection.paper module