Artificial Cognitive Architecture

State of knowledge

Role specialization, working memory, selective activation, controllers that allocate effort, and brain-inspired ideas treated as testable engineering hypotheses, not emulation.

This track draws on 21 published rounds, 14 hypotheses and 33 experiments. 32 reported findings come from published rounds and have not been independently replicated.

Reported findings

• 34 controls; 8 present, 3 partial, 23 absent; 26 critical controls partial or absent; fail-closed verdict BLOCKED. The checker validates the declared manifest, not the correctness of the human code review. (Round 30)
• Frozen snapshots, source versions, hashes, packet spans, model traces and usage telemetry are useful foundations but do not establish root-action fidelity, separation or unresolved structural equivalence. (Round 30)
• Three content probes identify all 36 observable response functions but root provenance in 0% of the 72 structural worlds. Provenance twins are interventionally equivalent under every admissible content probe. Exact diagnostic result, not a population estimate. (Round 29)
• Greedy entropy and minimax splitting identify all behaviors with 2.50 mean probes. Equating strict local response with root independence is wrong in 50% of the deliberately paired worlds. Verified root rotation establishes a prospective boundary, not historical independence. (Round 29)
• Declared-variant model intervals covered exact conditional probabilities in 100.00% of weighted histories under all three authored priors. Held-out hidden-common-origin coverage was 72.08% (uniform), 60.57% (benign), and 65.43% (issuer shift). These are exact constructed results, not production estimates. (Round 28)
• All hidden-common-origin histories remained compatible with the declared set. Passive adequacy AUROC ranged from 0.488 to 0.577. TSAR did not systematically dominate scalar routing at matched coverage; most cells tied. (Round 28)
• A model-set unanimity gate separates verdict safety from scheduling efficiency under fixed verification budgets: four policies using the 116-scenario gate produced no wrong categorical verdict in any of the 3,712 in-model policy-world runs, while a nominal target-entropy policy resolved 100 percent of cases but falsely emitted NO_CHANGE in 11.23 percent of changed cases in one regime. (Round 27)
• An out-of-model common-origin stress shows that extra evidence can increase false confidence: with the hidden_common_origin variant excluded from the planning set, the exact MSAV policy's false-clean rate reached 33.68 percent among changed worlds at budget 9. Myopic adaptivity can underperform a fixed target-first schedule. (Round 27)
• In the declared one-fault universe, SACP leaves eight opposite-target ambiguity pairs; adding one independently rooted external commitment reduces that count to zero. Under two faults, SACP plus external commitment leaves 26 pairs; adding an independently rooted behavior probe reduces that count to zero. These are exact finite-model counts, not prevalence-weighted rates. (Round 26)
• Against three failed roots, four genuinely independent target-sensitive roots identify the target in the declared model. If the witness shares the issuer root, no available set identifies change against three failed roots. Root independence is an assumption. (Round 26)
• On 80 authored traces, SACP alerted on 55 of 60 gap traces and none of the 20 negative controls (trace recall 0.9167, precision 1.0000, claim-weighted recall 0.8944). Revalidate-all achieved 1.0000 recall but alerted on all 20 negative controls and created 400 claim-review tasks, compared with 161 for SACP. A sequence-only policy falsely alerted on all five benign-reordering controls. These numbers show that the implementation conforms to the authored distinctions. They do not estimate production precision, recall, incident prevalence, reliability, cost, or user impact. (Round 25)
• On 23 authored fixtures, the proposed authority-lineage selector preserved every expected claim edge with one conservative extra edge, while repository-only selectors missed every deliberately non-repository fixture. Conformance to an authored model, not evidence of production effectiveness. (Round 24)
• The hybrid selector found all three artifacts labeled relevant in the real interval, including one uniquely added by an independently derived import view. It also selected four irrelevant artifacts and invalidated two claims that adjudication later found unaffected. Design evidence from one interval, not a general validation result. (Round 23)
• On the actual 127-path diff, the measurement-only watchlist selected 0 of the 17 audited critical paths, the filename heuristic 12 of 17 with 25 false positives, retest-all all 127, and the authored CTAG manifest exactly the 17. The 17-path set and tags were manually authored from the same change set, so this is not discovery accuracy or compute savings. (Round 22)
• On 32 authored mutation fixtures CTAG routed 32 of 32 exactly (direct watchlist 9, filename keyword 7, retest all 3). Specification tests on authored fixtures, not evidence of out-of-sample accuracy. (Round 22)
• Two historical claims preserved; five current claims made stale, then restored after direct inspection; two hypotheses left untested. (Round 22)
• Under the current three-write best-effort persistence model, seven of eight possible write states are incomplete yet do not block release; ABMG audit-qualifies none of those seven. Logical state-space result, not a measured production rate. (Round 21)
• Ten envelope-only mutations collide under the current content-only fingerprint, 24 equal-byte different-version source pairs and 24 distinct provider-response pairs collapse under the current records, and five bad stream fixtures are falsely accepted by a development model of the current parser; the ABMG projection separates or rejects all of them. Constructed fixtures, not production results. (Round 21)
• Endpoint and generic operational records miss evidence-specific corruption: A0 detected 2 of 12 mutation families and A1 detected 4 of 12, while content-bound receipts detected all 12 across 96 episodes with zero clean false positives. Constructed-fixture results, not model performance. (Round 20)
• An operator-only digest chain does not survive a privileged rewrite by that operator: after simulated rewrite, operator-only arms detected 0 of 12 families. Receipts bind observable delivery under assumptions; they do not prove source truth, completeness before emission, provider-internal processing, semantic support, or causal evidence use. (Round 20)
• Constructed collision: terminal output plus aggregate usage cannot determine whether the corrective source was delivered. A narrow indistinguishability result over constructed records, not model performance. (Round 19)
• Static audit: 4 of 18 collector-contract requirements present, 3 partial, 11 absent at the required granularity. (Round 19)
• Constructed example: a timestamp-only newest-recorded rule returns a late January correction (60) for a March current query whose correct fixture answer is 75. A counterexample over hand-specified records, not model performance. (Round 18)
• Exact check: 24 temporal-query checks hold across all six arrival orders of the three-record example, plus 12 checks of baseline failure, conflict handling, dependency repair, alternative support, and source integrity. (Round 18)
• Constructed example: a one-bit message that answers the release question perfectly leaves a 3/4 accuracy ceiling on a later test-status question under a stipulated uniform distribution. A possibility result, not model performance. (Round 17)
• Exact enumeration: 5, 2 and 1 of 15 partitions preserve every answer as the question family grows, needing at least 2, 3 and 4 message states. None of 60 deterministic recompressions restores a lost distinction. (Round 17)
• A supported fact does not establish decision sufficiency: the exact fictional policy counterexample leaves both review decisions possible. (Round 16)
• Exact finite-world enumeration yields 3,778 determined and 3,134 underdetermined pairs among 6,912 pairs. These are checker diagnostics, not model performance. (Round 16)
• A valid decision-changing pair establishes a gap within the modeled scope; failed bounded search does not certify completeness. Scope expansion can reopen a decision. (Round 16)
• Behavioral influence does not establish a useful correction. (Round 15)
• Message value depends on the receiver's existing information and on other messages. (Round 15)
• A local communication benefit must still survive a complete-system comparison under measured resources. (Round 15)

Rounds in this track

1. Round 30 · 2026-10-21
   Can We Intervene for Real? A Fail-Closed Readiness Gate for Active Evidence-Lineage Trials

   Can the current Encevra/Noetis workflow execute an active evidence-lineage trial whose causal interpretation is warranted, and what minimum fail-closed protocol is required before E29-B may run?

   Notebook
2. Round 29 · 20 October 2026
   Round 29 - Make the Evidence Move: Active Source Interventions and the Limits of Dependency Discovery

   Under a fixed verification budget, which controlled interventions can distinguish independent evidence roots from shared-root facades in a collaborative reasoning system, and what evidence justifies an independence claim rather than an explicit unresolved-equivalence finding?

   Notebook
3. Round 28 · 19 October 2026
   Round 28 - Confidence About What? Separating Target Probability, Structural Ambiguity, and Model Adequacy

   Under a fixed evidence and compute budget, does separating target probability, structural ambiguity, and model adequacy support safer abstention than a single confidence scalar?

   Notebook
4. Round 27 · 18 October 2026
   Round 27 - Which Check Should Run Next? Model-Set-Safe Verification Under a Fixed Budget

   Under a fixed observation budget, can a sequential verification policy improve correct resolution while avoiding harmful false confidence when the cost, efficacy, and independence of checks are uncertain?

   Notebook
5. Round 26 · 17 October 2026
   Round 26 - What Can the Watchers Ever Know? Minimum Observables for Detecting Omitted Change

   For each omitted-change failure class, which changed and unchanged worlds remain observationally identical, and what minimum independently rooted observable or trust assumption separates them?

   Notebook
6. Round 25 · 16 October 2026
   When Silence Looks Like Stability: Detecting Missing Change Evidence in Collaborative AI Systems

   Can an AI assurance system distinguish a genuinely quiet authority from a broken, delayed, stale, selectively silent, or common-mode observation path?

   Notebook
7. Round 24 · 15 October 2026
   Do Two Watchers Count as Two? Authority Lineage and Common-Origin Failure in Claim Revalidation

   How should Encevra represent the lineage and authority of change evidence so that multiple analyses of one source are not mistaken for independent coverage, and so that changes outside the repository can trigger bounded claim revalidation?

   Notebook
8. Round 23 · 14 October 2026
   Can the Gate Catch Tomorrow's Change? A Prospective Shadow Trial of Claim Revalidation

   Can a prospective gate notice when a genuinely later software change should make a current claim stale, without unnecessarily withdrawing unrelated claims or rewriting history?

   Notebook
9. Round 22 · 13 October 2026
   When Does an Audit Expire? Dependency-Triggered Revalidation for Rapidly Changing Agent Systems

   Can a typed claim-dependency graph automatically mark only the assurance claims affected by code, configuration, data, or external-contract changes as stale, preserve historically valid results, and require the right revalidation?

   Notebook
10. Round 21 · 12 October 2026
    Where Did the Trace Break? An Attempt-Bound, Fail-Closed Measurement Gate for Noetis

    Can a boundary-tapped, attempt-bound, atomic measurement gate reconstruct every Noetis provider attempt and refuse audit-qualified release when the trace is incomplete, at fixed model compute?

    Notebook
11. Round 20 · 11 October 2026
    What Must the Log Reveal? Minimal-Disclosure Receipts for Verifiable Evidence Delivery

    Can salted, ordered, independently witnessed invocation receipts preserve exact application-observable evidence delivery for authorized audit while keeping raw prompts and source text out of routine telemetry, with acceptable leakage, false-alarm, storage, latency, and reconstruction costs?

    Notebook
12. Round 19 · 10 October 2026
    Did the Evidence Reach the Agent? Reconstructable Evidence Lifecycles for Reliable Experiments

    Can an Evidence Lifecycle Observation Contract reconstruct which immutable source version was admitted, what ordered material crossed each model invocation boundary, and how claims and the terminal output were bound to those events, better than final records and generic traces?

    Notebook
13. Round 18 · 9 October 2026
    When Evidence Changes: Versioned Support and Bounded Belief Repair

    At fixed total work and source access, does an append-only record that distinguishes valid time from recorded time and tracks claim dependencies improve current, historical, as-known, and downstream-consequence answers over strong overwrite, chronological-history, and newest-recorded baselines, without increasing false invalidation, unhelpful dispute states, or cost?

    Notebook
14. Round 17 · 8 October 2026
    When the Question Changes: Recoverable Evidence Under a Context Budget

    When a follow-up question changes which facts are decisive, does a compressed handoff that records dependencies and a declared scope improve supported completion over a strong contextualized prose summary, when both can reopen the same sources and all work is charged to the same budget?

    Notebook
15. Round 16 · 7 October 2026
    Before the Answer Closes: Detecting Missing Decision Conditions

    At a fixed total inference and source-access budget, does requiring a validated pair of evidence-compatible scenarios with different decisions reduce unsupported commitment more effectively than a strong missing-information checklist, without reducing useful completion or increasing harmful revision?

    Notebook
16. Round 15 · 6 October 2026
    What makes a message worth sharing?

    Can a bounded mechanism for retaining and combining unresolved evidence improve Noetis after its additional costs and revision damage are measured?

    Notebook
17. Round 11 · 3 October 2026
    When should collaborators spend their next unit of compute?

    Should verification effort go where a specific check is predicted to repair, rather than where uncertainty is highest?

    Notebook
18. Round 10 · October 2026
    Evidence exchange, selective revision, and a testable path

    What communication and revision protocol makes a correction trustworthy enough to reuse?

    Notebook
19. Round 9 · September 2026
    A research agenda for the lab

    Can systems acquire useful procedures from verified experience and revise them when conditions change?

    Notebook
20. Round 8 · September 2026
    Delayed feedback can act on a temporary trace

    How might later feedback modify a temporary trace without destabilising learned behaviour?

    Notebook
21. Round 3 · August 2026
    Hippocampal ripples and compositional inference

    Is replay a useful hypothesis for recombining evidence into new inferences?

    Notebook

Hypotheses

• H22-4Separating historical_frozen from current states will reduce misleading carry-forward while preserving reproducibility and citation stability.Proposed
• H22-6Comparing authored dependencies with runtime or static dependency evidence will catch manifest omissions that either method alone misses.Proposed
• H21-4With model calls held identical, A1 instrumentation adds at most 5 ms median and 20 ms p95 synchronous latency, at most 15 KB median content-free storage per provider call, and no statistically or practically meaningful answer-quality regression.Proposed
• H21-6The boundary tap outperforms an otherwise equivalent post-hoc collector under envelope mutation and fallback.Proposed
• H20-2An independent checkpoint detects at least 0.99 of seeded post-checkpoint operator rewrites with false-alarm rate at most 0.01, outperforming operator-only chains by at least 0.20 absolute detection.Proposed
• H20-4At the synthetic live boundary, p95 receipt creation plus durable checkpoint enqueue stays under the stricter of 5 ms or 5 percent of non-model orchestration latency, with median public receipt size under 2 KiB.Proposed
• H19-3An external-content mode using version, digest, length, locator and access receipt reduces routinely captured sensitive bytes while preserving identity reconstruction.Proposed
• H18-1Bitemporal selection improves historical-now and as-known accuracy over deterministic newest-recorded selection at the frozen budget.Proposed
• H17-1Under the same explicit scope check, a structured record improves changed-question supported completion over strong prose without unacceptable damage or cost.Proposed
• H16-2Scope discovery helps more when a relevant rule is absent from the representation than when only a named value is missing.Proposed
• H12-2Revision state adds information beyond task difficulty.Proposed
• H11-1A repair/damage-predicting controller improves task success over a whole-answer router at a fixed cost ceiling.Proposed
• H11-3Bundled checks help on complementary-evidence tasks after overhead.Proposed
• H11-4Predicted usefulness outperforms uncertainty-first routing on matched pairs.Proposed

Experiments

• E30-BProposed matched-compute shadow trial of the RISE GateProposed
• E29-AExact finite deterministic interventional-lineage diagnosticExecuted (diagnostic)
• E29-BProposed matched-cost live Interventional Lineage TestProposed
• E28-AExact fixed-compute constructed trace replayExecuted (diagnostic)
• E27-AExact finite constructed diagnostic of budgeted verification policiesExecuted (diagnostic)
• E27-BFixed-compute shadow comparison of model-set adaptive verificationProposed
• E26-ADeterministic finite-model identifiability analysisExecuted (diagnostic)
• E26-BProspective fixed-budget observation-sufficiency shadow experimentProposed
• D25-AAdversarial-omission authored conformance diagnostic (D25-A)Executed (bounded diagnostic)
• E25-BProspective fixed-budget multi-authority silence-coverage trial with hidden independent adjudicationProposed
• D24-AAuthority coverage audit and authored conformance diagnostic (D24-A)Executed (bounded diagnostic)
• E24-BProspective multi-authority authority-lineage revalidation experiment with independent adjudicationProposed
• D23-AProspective shadow trial of claim revalidation (D23-A)Executed (bounded shadow diagnostic)
• E23-BProspective multi-commit CTAG shadow evaluation with independent adjudicationProposed
• D22-ADeterministic code-change routing diagnostic (D22-A)Executed (diagnostic)
• E22-BProspective CTAG evaluation on unseen Encevra changes at controlled verification computeProposed
• E21-ADeterministic attempt-bound measurement gate diagnostic (D21-A)Executed (diagnostic)
• E21-BShadow ABMG evaluation on real provider traffic at fixed model computeProposed
• E20-ADeterministic minimal-disclosure receipt development harnessExecuted (diagnostic)
• E20-BHeld-out receipt comparison against strong generic tracesProposed
• E19-ADeterministic evidence-lifecycle validator and static collector auditExecuted (diagnostic)
• E19-BReconstruction under frozen trajectoriesProposed
• E18-AExact deterministic constructed bitemporal and repair diagnosticExecuted (diagnostic)
• E18-BFive-arm versioned evidence study (O0/A0/T0/B0/B1)Proposed
• E17-AExact finite constructed recoverability diagnosticsExecuted (diagnostic)
• E17-BFrozen-handoff question-change study (P0/P1/S0/S1)Proposed
• E16-AExact finite-world sufficiency diagnosticsExecuted (diagnostic)
• E16-BBounded missing-condition studyProposed
• E15-AExact diagnostics on constructed distributionsExecuted (diagnostic)
• E15-BStudy A: support and recommendation fields (2x2)Proposed
• E15-CStudy B: complementary withheld facts (optional)Proposed
• E11-AMarginal-value verification controllerProposed
• E10-AEvidence exchange versus conclusion sharingProposed

Architecture changes in Noetis

• A-01 Conservative role triage with full-panel fallback: Skip optional roles only on confident, valid routing; otherwise run every role. (In Noetis (preview))

Open questions

• Can Round 31 build a sandboxed vertical slice with root identity, a non-destructive root action, independent witness, separation and budget records, and equivalence-aware outcomes before piloting E30-B? (Round 30)
• Can Round 30 execute E29-B in shadow mode with independently verifiable root interventions, receipts, leakage prevention and matched total compute? If prerequisites fail, report the infrastructure gap. (Round 29)
• Can a fixed-cost active intervention discover a missing evidence dependency that passive confidence, disagreement, and surprise cannot detect? (Round 28)
• Does model-set adaptive verification reduce harmful false-clean rates at fixed compute with hidden independent adjudication in E27-B? (Round 27)
• Does OSC reduce harmful false-stability certifications at fixed total cost with hidden independent adjudication in E26-B? (Round 26)
• Does SACP reduce independently adjudicated affected-claim gap misses at fixed total budget in a preregistered prospective multi-authority trial (E25-B)? (Round 25)
• Does authority-lineage revalidation reduce stale-claim escape in a prospectively frozen, independently adjudicated, multi-authority, fixed-budget experiment (E24-B)? (Round 24)
• Does the hybrid reduce stale-claim escape across a preregistered multi-commit window with independent adjudication (E23-B)? (Round 23)
• Does a prospective CTAG shadow gate reduce stale-claim escape under fixed verification budget on unseen real commits? (Round 22)
• Which independent dependency view adds unique catches? (Round 22)
• Can unknown execution paths be caught and historical claims kept immutable in a shadow slice? (Round 22)
• Does ABMG capture at least 99.5 percent of live attempts exactly? (Round 21)
• Does synchronous gate overhead meet budget at fixed model compute? (Round 21)
• Does failure labeling improve reviewer reconstruction, and does the privacy design withstand review? (Round 21)
• Does MDIR improve real audit accuracy at acceptable cost against strong generic traces with independent immutable export? (Round 20)
• Does an independent checkpoint recover detection after a privileged operator rewrite? (Round 20)
• Can reviewer burden and operational overhead stay within the frozen development-gate thresholds? (Round 20)
• Do exposure ledgers improve exact exposure reconstruction over final records and generic traces? (Round 19)
• Does claim lineage improve first-divergence localization without false attribution? (Round 19)
• Can hash, version and locator binding reduce captured sensitive content while preserving identity reconstruction? (Round 19)
• Do bitemporal fields beat deterministic newest-recorded assembly on historical and as-known questions at matched cost? (Round 18)
• Does dependency-directed repair improve downstream consequences without excessive false invalidation? (Round 18)
• Does an explicit disputed state reduce unsupported commitment without collapsing useful coverage? (Round 18)
• Does a structured record beat strong prose under the same explicit scope check at equal total cost? (Round 17)
• Does a scope check recover confident omissions beyond unrestricted discretionary lookup? (Round 17)
• Does reopening help only when it actually exposes usable evidence? (Round 17)
• Does validated alternative generation improve supported task completion over a strong checklist at matched budget? (Round 16)
• Does scope discovery help when a relevant rule is absent from the representation? (Round 16)
• Can decision relevance reduce unsupported closure without needless questions or reduced useful completion? (Round 16)
• Can a bounded mechanism for retaining and combining unresolved evidence improve Noetis after its additional costs and revision damage are measured? (Round 15)
• Do localized checks plus short bundles beat a whole-answer router? (Round 11)
• Can harmful revisions be bounded while spending more on checks? (Round 11)
• Does exchanging evidence outperform exchanging conclusions at matched cost? (Round 10)
• Do procedures learned from verified experience transfer to unfamiliar problems? (Round 9)
• Can credit be assigned to the evidence that changed a specific requirement? (Round 8)
• Which replayed decision points actually change later actions? (Round 3)