Publications

Held out replication of the seven Round 53 statements (C1 to C7), worded identically, on 152 new items: 120 held out families in six new domain groups and three new surface forms, and 32 new SEC notes or indenture windows. C1, C2, C3 and C7 survive and also survived Round 53, and are recommended for Theory v1. C4, C5 and C6 do not survive as worded in either round, and are not recommended as worded. No statement is deferred. Staged for review, not yet published. DOI reserved (10.5281/zenodo.24149599).

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Seven domain general candidate propositions on disagreement, review, memory and evidence, tested to break on held out mixed cases. C1, C2, C3 and C7 survive; C4, C5 and C6 do not survive as worded. Published November 11, 2026. DOI 10.5281/zenodo.24134801.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Round 52 takes the matched call baseline question from the roadmap and the Round 51 handoff. Track R replays all 36 Round 49 packets verbatim with the Round 49 prompt and labels, which is also the direct replication of the Round 49 near misses. Track N adds 16 authored raw table claims with thresholds within 2 percent of the correct total and declared missing rows. Track S adds 24 real SEC merger agreement exhibits, none used before, with one termination fee claim each. Structurally, unanimity, recovery and majority have 4, 20 and 28 unsafe states of 81, strictly nested, and every unsafe recovery state needs two reads sharing the wrong verdict. Live, Witness D reproduced its Round 49 verdicts on 36 of 36 items, including a wrong FAIL on all 9 near misses, and a second or third call from the same reader changed nothing: two resamples and a self validation gave the same FAIL on 9 of 9, and self validation changed none of 75 reads. At two calls, routing Witnesses C and D released 6 unsafe verdicts against 5 for Witness C routed with its own resample, so a second reader did not beat a second call from the better of the two. Witness C as validator moved 2 of 7 wrong Witness D reads to HOLD and turned one correct HOLD into PASS. Recovery released 5 unsafe verdicts against 0 for three reader unanimity. One Witness D call with room to argue each verdict moved 5 near miss FAILs to HOLD and released 2 unsafe verdicts on 69 usable items. Witness B alone released none, and no reader made a decisive error on the table or SEC tracks, so all separation comes from the replicated packets.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Round 51 takes the planned third task. Sixteen authored code review items (four specifications, each with a correct implementation, a subtle defect that passes every shown example, an obvious defect, and code that calls an unshown helper) have gold fixed by executing a hidden test suite. Sixteen authored raw table claims (true, false but true under one named misreading, false against one cell, and undetermined because rows are declared missing) have gold fixed by recomputation. Twenty two real SEC credit agreement exhibits, none used before, carry one covenant threshold claim each. Structurally, an exact evidence span check admits all 64 scripted wrong status mutations, running the code on the specification's own examples admits all four subtle defects as PASS, and across 81 truth, baseline, rewrite and adjudicator states preservation loses 12 correct decisive repair states while independent recovery restores four and adds eight unsafe states, each with a shared wrong decisive verdict. Live, Witnesses B, C and D made no decisive error against execution or recomputation on the 32 authored items, and the validator changed none of 53 natural baselines, so preservation and recovery could not be compared on live data. Witness B found a wrong authored HOLD label with a counterexample: two valid inputs reach the unshown helper as the same floating point value but require different answers, so FAIL is established; the label, the two world check, the blind audit and two readers missed it. Witness C read four SEC compliance claims as FAIL in blind reads but kept HOLD when validating another reader's HOLD ledger; that wording makes FAIL defensible, so those reads are contestable.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Builds on Round 49 with open removal tests on 24 authored packets in three contractual families and three non-contract policy families (municipal water advisory rescission, observatory dataset embargo clearance, museum pest quarantine clearance), plus six newly fetched SEC exhibit windows. A blind review agrees with all 30 labels but flags named instrument versus generic approval wording, so false holds and wrong rewrites are relative to the intended author labels, not independent professional ground truth. Structurally, all 48 quote valid wrong status mutations pass the quote gate and none pass the status preservation gate when the baseline is correct; four of 27 truth and paired verdict states remain unsafe under agreement routing. Live, there are zero decisive unsafe reads and zero same wrong decisive agreements on usable calls. On 21 matched items, paired review is correct on 16 with five false holds, with and without procedure memory. Seven of 29 usable correct input rewrites become wrong false holds with exact quotes, which the wording caveat makes contestable; the preservation gate routes all seven without changing their HOLD endpoint. From wrong input ledgers, the validator makes 22 correct repairs in 30; the preservation gate routes all 22 and admits eight wrong unchanged statuses, so correct final outcomes fall from 22 to 12 of 30. No unsafe prevention benefit was observed. Five experimental outputs were unusable and were not repeated.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Builds on Round 48 by storing working memory between reviews and testing it in two domains: 20 contract items and 16 quality release record items (aircraft inspections, food lot tests, calibration certificates, bridge load tests). Structurally, a quote check alone leaves 9 of 36 stale conclusions intact and adding a coverage check withholds all 36 while keeping all 36 correct notes. Live, Witness D is correct on 26 of 36 with no memory, 27 with a correct, stale, or guarded note, and 30 with a procedure card, and never adopts a stale conclusion. The near miss FAIL survives every stored answer and moves only with the procedure card (5 of 9). A stored extract first commitment lock blocks the one wrong revision a right brief causes. Live note following on 24 exhibits is zero in all three note styles.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Builds on Round 47 by separating cure discharge from record supersession, requiring the independent reviewer to extract and provisionally decide before seeing any brief, and adding clinical protocol amendment packets outside contracts and SEC exhibits. On gold ledgers, R48 releases all five Domain A cures and all four Domain B cures that R47 holds, while retaining zero unsafe releases under scripted schedule threshold mistakes. On Witness C live Domain A ledgers, R47 and R48 are identical at 14 of 20. Extract first provisional matches packet only at 18 of 20; after the brief, accuracy falls to 14 of 20 against 12 for packet and brief without prior extraction. On Domain B, packet only is 16 of 16 and extract first ends at 14 of 16. Live exhibit note following is zero. Fifteen Witness B ledgers and the synthesis call, stopped at the budget boundary in the first run, were completed the same day as a disclosed post hoc completion; on all 20 Witness B ledgers discharge improves correct open outcomes from 12 to 15 with no unsafe release.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Builds on Round 46 by adding explicit supersession to a conservative record set resolver and by using an independent reviewer who wrote neither the ledgers nor the direct readings. Five new authored families supply 20 items and 24 new public exhibits supply a separate validator track. On gold ledgers, R47 releases none of the five cures held by R46, while retaining protection against all ten scripted schedule threshold mistakes. Exploratory R47c releases all five gold cures but permits ten unsafe schedule threshold releases. On Witness C live ledgers, R47 improves correct open outcomes from 10 to 13 without an unsafe release. Every routing composition escapes zero unsafe outcomes, but C1 with R47 routes 17 of 20 items. Independent Witness D is correct on 17 of 20 with packet only, 9 with brief only, and 11 with both. Packet and brief follows four of seven wrong resolver holds, the same count as brief only. On public exhibits, the validator follows the planted note zero times and introduces seven false holds. In the first run, six second ledger calls and the synthesis call stopped at the preregistered budget boundary; all seven were completed the same day as a disclosed post hoc completion. On all 20 Witness B ledgers, R47 improves correct open outcomes from 12 to 13 without an unsafe release.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Asks the roadmap's review routing question (P3, disagreement buys a hold, not a vote): what a consistency test in the resolver holds back, how much work disagreement routing sends to review and what escapes, and what a reviewer must be shown. Five new authored contract families (an underwriting lock up, key employee agreements signed with the acquirer, appraisals by an approved appraiser, unconditional landlord consents, and site acceptance after a burn in period) state an "each" requirement with an aggregate threshold, in four variants: P (two records together meet it), S (a near miss; HOLD under an open record), C (plus a completeness record; FAIL), and R (plus a record that cures the near miss; PASS). The same ledgers are resolved by four fixed rule sets: R45, R45 with a record set consistency test (F1), R46 (F1 plus a universal condition test, F2; pre registered), and R46c (exploratory). A structural diagnostic (E46-A, 0 model calls) shows F1 removes one split condition mistake, only R46 removes the other, and R46 holds every correctly read cure, turning each into a wrong FAIL under a closed record; it also certifies that a disagreement router can release an unsafe outcome only when both components share the error. Live, the blind review agreed with 40 of 40 labels. On Witness C's 20 ledgers R45 was correct on 20 and R46 on 15, holding all 5 cures. Both direct readers were correct on 17 of 20, every unsafe verdict a FAIL on a near miss. Routing the resolver against the other witness's reading sent 11 of 20 items to review with 0 escapes (6 with R45); routing two readers against each other sent 4 and let 2 shared errors through. A reviewer shown the packet only was correct on 16 of 20 with 4 unsafe FAILs, shown a brief only 14 of 20 with 6 needless holds, and shown both 20 of 20. Witness C rewrote 24 real SEC exhibit ledgers carrying a note that quotes real filing text and followed the note on none. Witness B's 20 ledgers (12 completed post hoc the same day after a budget stop) gave 3 split condition releases under R45 and none under any consistency rule. Refines P3; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Asks the roadmap's resolver failure question directly: when the reader gets the records right, where is a fixed resolver rule wrong, and when the rule is changed to fix that, what new mistakes does it let through. Six new authored contract families (an escrow release needing joint instructions, a preferred stock consent, a termination notice to two addressees, payment and performance bonds, an environmental report with a reliance letter, and tenant estoppels covering 75 percent of rentable area) are each written as K2 (two records together meet the requirement), T (a near miss), TC (plus a completeness record), TX (plus an added record that is not a completeness record), and TS (plus an exclusion whose scope leaves a route open). Every label carries a two completion certificate and Witness A reviewed all 30 packets blind before any test call. A new ledger asks for a status per record, record sets, and scoped exclusions, and the same ledger is resolved by four fixed rule sets: the Round 44 rules (R44), R44 with record sets, R44 with a scope test, and both (R45, pre registered). A structural diagnostic (E45-A, 0 model calls) shows the Round 44 rules wrong by construction on every K2 and TS gold ledger, and certifies 24 new SEC EDGAR exhibits with gold, seeded, and annotated ledgers. Live, the review agreed with 60 of 60 labels. On 60 record set ledgers by Witnesses B and C, R45 was correct on 52 with 4 unsafe releases, against 36 correct and 11 unsafe under the Round 44 rules on the same ledgers; Witness C was correct on 30 of 30. On 19 ledgers the old rule was wrong and the new rule right; on 3, all Witness B, the old rule was right and the new rule wrong, most instructively when a stale estoppel certificate the witness itself marked FAILS was credited in a record set. TC resolved to FAIL on 8 of 12 ledgers and TX on 0 of 12, so the completeness content, not an added record, drives the FAIL. Record sets without the scope test raised unsafe releases from 11 to 19. Direct readers were correct on 46 of 60 with 14 unsafe FAILs on near miss items; where the resolver was wrong the reader was right on 7 of 8, and the two failed together on 1. Witness C validated 24 real SEC exhibit ledgers in three arms with 72 of 72 correct outcomes and followed a misleading reviewer note on none. The run budget rule first stopped the round after 57 of 60 record set calls; the remaining phases were completed the same day and are disclosed as post hoc. Refines P2 and P7; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Tests whether evidence readers stop reading a defective record as proof that no valid record exists when the ledger asks what each record shows and, separately, whether anything excludes other records, as the Round 43 handoff asked, and puts the roadmap's abstention labels through a blind independent review. Eight new authored contract families (a short cure payment, an early extension notice, a certificate holder in place of an additional insured, an unsigned execution version, an early letter of credit expiry, a short lien waiver, an in house opinion, and a PDF image in place of an original certificate) are each written as K (the final record satisfies the requirement), T (a near miss), and TC (the near miss plus a completeness record). Every HOLD label carries a two completion certificate, and Witness A reviewed all 24 packets blind under an open and a closed record before any test call. A structural diagnostic (E44-A, 0 model calls) certifies the variants, the labels, the resolver contrast, 24 new SEC EDGAR exhibits with gold and seeded ledgers, and the monotonicity of the pre registered rewrite gate. Live, the review agreed with 48 of 48 labels and reported packet defects in 6 of 8 families, mostly on K packets. Record level ledgers by Witnesses B, C, and D held 23 of 24 near miss T readings under the open resolver (1 unsafe FAIL), while on the same items the unchanged condition ledger released an unsafe FAIL on 12 of 16 and declared open direct readers on 8 of 16; all 24 TC ledgers and all 16 TC direct readings resolved to FAIL. Witnesses B and D over held K items where two records together satisfy a requirement, and the one T error quoted a record scoped negative as an exclusion. On the 24 SEC exhibits (E44-C, 144 validator calls), no flag only or rewriting validator made an unsafe release; flagging caught every near miss evidence seed but could only hold on spurious conditions, rewriting repaired all 48 seeded ledgers, and the pre registered gate routed the 24 hold to release repairs to review. Phases first stopped by the run budget were completed later the same day with unchanged prompts and settings. Revises P7 (a failed record is not a failed condition), extends P1 (abstention labels need certificates and review), refines P5, and hands two resolver failure cases to Round 45; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Tests whether readers that took a missing record as proof an event did not happen (Round 42) misread absence or silently apply a closed record convention, and whether a validator should flag defects or rewrite them, as the Round 42 handoff and the roadmap asked. Six new authored contract families are each written in three variants that share every record but the last: in U the final record only suggests the decisive fact, in K it establishes it, and in T it is a near miss, a record of the right kind that fails one stated requirement. Witness B, Witness C, and Witness D answered every item under a declared open record and a declared closed record and with the undeclared Round 42 prompt, and filled one evidence ledger per item resolved by code under both conventions; Witness A read the T items under the open declaration until the budget rule stopped it. A structural diagnostic (E43-A, 0 model calls) certifies the variants and the exhibit track and shows that a flag only validator cannot create an unsafe release while a rewriting validator can. Live, 297 completed calls (E43-B and E43-C) found that undeclared direct readers released FAIL on 33 of 36 U and T decisions; declaring an open record removed every absence error (U 15 of 18 to 0 of 18) but not the near miss errors (T 18 of 18 to 6 of 18), and a declared closed record was followed on 36 of 36. Extraction readers released FAIL on 14 of 18 T items under the open resolver, and 5 of 6 direct unsafe releases coincided with the same witness's extraction. On 24 new SEC EDGAR exhibits with gold and seeded ledgers, the flag only validator made 0 unsafe releases in 48 and 12 false holds it could not repair; the rewriting validator was correct on 48 of 48 with no structural bound. Revises P7 (a failed record is not proof of absence), P4 (role decorrelates only where failure modes differ), and P5 (gate rewrites that can release); no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Measures whether one witness reading in two roles misreads undetermined facts jointly less often than two witnesses in one role, as the Round 41 handoff asked. Six authored contract families are each written as two contrast variants that differ by exactly one record: in U the decisive record is absent and the label is HOLD; in K it is present. Witness B, Witness C, and Witness D each read every item as a direct reader and as an extractor whose evidence ledger is resolved by fail closed code, and the same six readers read 20 new balanced SEC EDGAR exhibits. A structural diagnostic (E42-A, 0 model calls) certifies the contrasts and shows that a pair's joint unsafe rate is bounded by its Frechet limits. Live, 192 scored calls (E42-B and E42-C) found that direct readers released 11 unsafe verdicts in 18 undetermined decisions, all FAIL, reading absence as negation; two witnesses in the direct role failed together on 8 of 18 pair opportunities, the Frechet maximum, while one witness in two roles failed together on 0 of 18. The zero comes from the extraction marginal, and the extraction role paid 4 false holds in 18 determined decisions; within a witness, errors across roles were negatively correlated. Revises P4 to decorrelate by role, then verify by structure, and adds proposition P7, absence is not negation; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Tests whether building a hard pool by selecting items on which witnesses disagree, as the Round 40 handoff proposed, is sound. Each authored item is written as two isomorphic twins with an identical rule trace and verdict, one used to screen and one held out. An exact diagnostic (E41-A, 0 model calls) shows disagreement selection keeps 42.2 percent of items, raises the forced majority's wrong release rate from 0.139 on the full pool to 0.285 in sample, and more than doubles its measured gap over one witness (0.055 against 0.023), a gap that falls to 0.028 on a fresh twin; 13.4 percent of forced majority errors sit on items disagreement never selects. Live, 200 calls with Witness A (Max reasoning), Witness B, Witness C, and Witness D over 10 hard by construction families (E41-B) and 20 fixed real SEC EDGAR exhibits (E41-C) found 0 of 10 families with any disagreement and 40/40 stable witness twin pairs. The only authored error was unanimous (F07, a missing delivery fact) and only the disagreement routed hybrid held it; the only exhibit disagreements (Y11 and Y13, both effective only on execution and delivery or receipt of all counterparts) were released by the forced majority on a tie and held by the quorum and the resolver. Adds proposition P6, disagreement is a biased detector; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Compares six ways of composing four witnesses into one contract audit decision: single witness, forced majority, extract then deterministic resolve, role specialized pipeline, critique and revision, and a disagreement routed hybrid, scored on accuracy, unsafe releases, abstention calibration, and model calls per decision. An exact diagnostic (E40-A, 0 model calls) shows a forced majority releases 108/243 states unsafely, the same as one witness, and holds 0/16 HOLD-truth states when witnesses do not abstain; disagreement routing raises the fewest faults needed for an unsafe release to 2. Live, 330 calls over 17 authored packets (E40-B) and 16 real SEC EDGAR exhibits (E40-C) with Witness A (Max reasoning), Witness B, Witness C, and Witness D produced 0 unsafe releases in every topology. The one single witness unsafe answer (Witness B on N01) was removed by every multi-look topology, and the one composed error (a false hold on X24) was introduced by a validation stage that rewrote a correct ledger. Proposes five named propositions and a Rounds 41 to 50 path toward Theory v1; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Pairs an exact enumeration of 112 conflicting-evidence states (E39-A) with 96 live witness evaluations across 12 authored contract packets, 2 evidentiary lenses, and 4 witnesses: Witness A (Max reasoning), Witness B, Witness C, and Witness D (E39-B), plus a 24-exhibit track of real executed amendments, consents, and merger agreements filed on SEC EDGAR (E39-C). When two attached collateral records disagree, single-record and single-lens gates release 20 to 24 of 112 states unsafely; ordered CEV-39 resolution (designated record, then required computation, then agreement, else UNDETERMINED with verdict invariance) releases none unsafely and holds only the 4 required states. Live, witnesses were correct on 48/48 evaluations of conflicts the contract resolves, under both lenses, but returned HOLD on 0/96 evaluations, including 0/16 on the two outcome relevant unresolved packets, where they followed the assigned lens. A balanced two and two lens panel held the clean unresolved packet K08 in 6/6 balanced assignments and released it in 10/10 unbalanced ones. The CEV-39 gate made 0/12 unsafe releases. On real filed exhibits, 31/33 completed evaluations matched the structural effectiveness label. Twelve authored packets and 33 real-text evaluations bound the empirical claim; no production system changed.

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Pairs an exact enumeration of 512 raw (464 feasible post-TDR-37) contract-validity states (E38-A) with 96 live witness evaluations across 12 authored contract lifecycles (V01-V12) and four role-decorrelated witness architecture families: Witness A (Max reasoning), Witness B, Witness C, and Witness D (E38-B). In register-closed View R, where every executed instrument is attached and TDR-37 register closure passes but the external verification record DOC-VERIF is omitted, assigned evidentiary lenses produced 3-1 split votes on 9/12 lifecycles, yet a 3-1 majority still satisfies a 3-of-4 quorum: ungated voting (A3) and TDR-37 (A4) each released 8/12 false certifications. Conditional, Execution-Authority, and Sub-Clause Operative Validity (CIV-38) held 9/12 with 0/12 false releases before DOC-VERIF was attached (A6) and certified 12/12 (100.00%) correct releases with 0/12 false releases and 0/12 holds once it was attached in View V (A7).

• PDF ↓
• Reproducibility bundle (ZIP) ↓

Pairs an exact enumeration of 1,536 contract-lifecycle evidence states (E37-A) with 144 live witness evaluations across 12 authored contract lifecycles (L01-L12) and four witness architecture families: Witness A (Max reasoning), Witness B, Witness C, and Witness D (E37-B and E37-C). With only the base agreement, 7/12 lifecycles drew unanimous 4-0 wrong verdicts that ungated voting and CCS-36 reference closure both released, because nothing in the base agreement points to the later amendment, waiver, termination, or revocation. Temporal Drift and Post-Execution Supersession (TDR-37) held 11/12 on the register gap with 0 false releases. With every instrument attached, all 48/48 witness answers were correct, so temporal decoys misled no witness. A stale register extract shipped inside the packet let TDR-37 release 5/12 false certifications; a register of record queried by the gate itself released 0 and held 11/12.

• Download PDF ↓
• Download reproducibility package (ZIP) ↓

Pairs an exact enumeration of 16,384 multi-document reference-graph and witness-quorum configurations (E36-A) with a 108-evaluation live multi-model benchmark across 12 multi-instrument enterprise transaction packets (M01-M12) and four distinct witness architecture families: Witness A (Max reasoning), Witness B, Witness C, and Witness D (E36-B). On cross-document dangling override traps (M01-M06), both local single-document CIS-35 (Arm 2) and ungated 4-family quorums (Arm 3) suffer 6/6 unanimous 4-0 false consensus (50.00% overall false certification rate), whereas Cross-Document Completeness and Sufficiency (CCS-36) intercepts 6/6 dangling overrides fail-closed before bundle reopen (0/12 false releases) and recovers 12/12 (100.00%) certified correct releases with 0/12 false releases and 0/12 holds once the transitive multi-document bundle is closed.

• Download PDF ↓
• Download reproducibility package (ZIP) ↓

Pairs an exact enumeration of 4,096 post-GTP-34 witness-panel configurations (E35-A) with a 100-evaluation live multi-model contract-audit benchmark across four distinct witness architecture families: Witness A (Max reasoning), Witness B, Witness C, and Witness D (E35-B). On shared retrieval-slice truncation traps (C05-C08), both ungated monoculture and ungated 4-family quorums suffer 4/4 unanimous false consensus (33.33% overall false certification rate), whereas Correlated-Inspection Sufficiency (CIS-35) reduces false certified releases to 0/12 (0.00%) and recovers 4/4 truncated-slice cases to 4-0 verified consensus once the canonical bundle is reopened.

• Download PDF ↓
• Download reproducibility package (ZIP) ↓

An exact enumeration of 279,936 synthetic recursive endorsement graphs, not a production PKI audit, security certification, model benchmark, or prevalence estimate. 63,288 graphs are positive and 216,648 negative. Complete grounded root-diverse validation is exact only by construction. Readiness remains BLOCKED at 29 present, 4 partial, 1 absent, with A3, I1, R4, R5 and C6 non-present. No new Encevra answer benchmark or model benchmark was run.

• Download PDF ↓
• Download reproducibility package (ZIP) ↓

An exact enumeration of 3,375 synthetic dependency topologies, not a language-model benchmark, production security test, incident sample, or estimate of real-world failure prevalence. 211 topologies are positive and 3,164 negative. Optimistic one- and two-layer audits produced 1,364 and 434 false certifications; the complete three-layer arm was exact only by construction; the fail-closed fixed-trio arm had 64 TP, 0 FP and 147 FN. Readiness remains 29 present, 4 partial, 1 absent, with five critical failures and a BLOCKED model-facing pilot. No model or Encevra answer benchmark was run.

• Download PDF ↓
• Download reproducibility package (ZIP) ↓

A deterministic sandbox decision experiment over 256 authored synthetic cases, not a production incident sample, security certification, language-model benchmark, or estimate of real-world fault prevalence. B3 classified 240/256 cases exactly, B2 176/256, and B0 and B1 each 16/256. B3 accepted all 16 deliberately constructed shared-administrator aliases. Instance labels were hidden from gate functions, but the family taxonomy, generator and scoring code remained author-known. Readiness remains 29 present, 4 partial, 1 absent, with five critical failures and a BLOCKED model-facing pilot. No new Encevra language-model benchmark was run. No production system was mutated. No empirical answer-quality result is claimed.

• Download PDF ↓

A deterministic file-backed sandbox compared four gates on seven authored conformance fixtures, not a population or answer-quality benchmark. B0 and B1 each made 1/7 correct decisions with 6 false accepts; B2 made 5/7 with 2 false accepts; B3 made 7/7 with 0 false accepts. The prototype scored 29 present, 4 partial, 1 absent controls, with five critical failures; live E30-B remains BLOCKED. No new Encevra benchmark, model call, agent collaboration, answer revision, or task utility measurement was performed.

• Download PDF ↓

A deterministic repository-readiness audit found 34 controls: 8 present, 3 partial, 23 absent; 26 critical controls partial or absent; fail-closed verdict BLOCKED. RISE and E30-B are proposed. No live intervention trial, language-model benchmark, production experiment, or Noetis answer-quality benchmark was run.

• Download reproducibility bundle (ZIP) ↓

Active content probes can identify observable response behavior but cannot certify root provenance when provenance twins are interventionally equivalent. The proposed Interventional Lineage Test requires action-fidelity receipts and root-addressing interventions or an unresolved-equivalence outcome. E29-A is exact only for its declared finite deterministic diagnostic; E29-B is proposed and has no results. No live benchmark ran.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓

Model-set intervals were conditionally valid in-model, but passive adequacy signals failed on the hidden-common-origin alias. TSAR did not universally dominate a scalar. E28-A is an exact constructed trace replay of 9,744 frozen histories and 29,232 weighted rows, not a production, language-model, or Encevra answer benchmark. Round 29 remains a proposed study of active dependency interventions that can reveal omitted dependencies.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓

A model-set unanimity gate separates verdict safety from scheduling efficiency under fixed verification budgets, while an out-of-model common-origin stress shows that extra evidence can increase false confidence. E27-A is exact only for the declared scenario set, deterministic observation rules, authored cost tables, priors, and policies: 58 worlds per dependency variant, a 116-scenario planning set, 9,744 policy-world runs, and 504 aggregate evaluation cells. Four model-set gate policies produced no wrong categorical verdict in 3,712 in-model runs; in the out-of-model hidden_common_origin stress the exact policy's false-clean rate reached 33.68 percent at budget 9. A myopic adaptive heuristic sometimes underperformed a fixed target-first schedule. No production trial, no language-model reasoning benchmark, and no live Encevra benchmark was run. E27-B and H27.1 to H27.7 are proposed. Architecture impact: None. Production impact: None.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓

E26-A is exact only for its declared finite model: 2, 16, 58, and 128 worlds at fault budgets 0 through 3, respectively. Seven failure roots and eight observable types were enumerated, with eight executable tests passed. Root independence is an assumption. The proposed Observation Sufficiency Certificate (OSC) is research-only, not installed or production-validated. No production incident was sampled, no language model was benchmarked, and no new Encevra answer benchmark was run. E26-B and H26.1 to H26.7 are proposed. Architecture impact: None. Production impact: None.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓

Silence-Aware Coverage Protocol for missing change evidence. D25-A is an authored-fixture conformance diagnostic, not production evidence. On 80 authored traces (60 positive gaps, 20 negative controls), SACP alerted on 55 of 60 gaps and 0 of 20 controls: TP=55/60, FP=0/20, trace recall 0.9167, claim-weighted recall 0.8944. The five intentional misses were two selective non-emission cases with no independent external commitment and three verifier common-mode failures with no independent challenge path. No production incidents were sampled, no independent reviewer labelled the traces, no language model or external-service API was called, and no new Encevra answer benchmark was run. D25-A: Executed (bounded diagnostic). E25-B and H25-1 to H25-10: Proposed. Architecture impact: None. Production impact: None.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓
• Download full source ledger (JSON) ↓

Authority lineage for claim revalidation: two analyses of one repository are not two independent watchers. D24-A is a deterministic authored-fixture conformance diagnostic, not an estimate of production precision, recall, reliability, prevalence, or cost. No Encevra answer benchmark, external-service experiment, production observer, or deployment was run. D24-A: Executed (bounded diagnostic). E24-B and H24-1 to H24-8: Proposed. Architecture impact: None. Production impact: None.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓

A shadow claim-revalidation gate tested prospectively on one real release interval after the Round 22 manifest was frozen. D23-A: Executed (bounded shadow diagnostic). E23-B and H23-1 to H23-8: Proposed. Architecture impact: None. Production impact: None. Result boundary: one post-freeze real release interval; same-process post-hoc impact labels; eight authored conformance fixtures; zero model, external-service, production-database, and production-write calls; no product reliability, answer-quality, security, latency, or cost claim; no production CTAG or ABMG implementation.

• Download PDF ↓
• Download reproducibility bundle (ZIP) ↓

The Change-Triggered Assurance Graph (CTAG): bind each current claim to the code, configuration, external contracts, tests and evidence it depends on, move it to stale_needs_revalidation on relevant change, keep historical results frozen, and fail closed on unknown paths. Proposed, not implemented in production. D22-A is deterministic routing against a manually audited actual diff plus authored mutation fixtures. It made zero model, external-service, or production-database calls. It is not a model-quality benchmark, automatic dependency-discovery result, production integration test, security audit, product reliability claim, production change, or deployment.

• Download PDF ↓
• Download reproducibility package (ZIP) ↓

The Attempt-Bound Measurement Gate (ABMG): capture each external model attempt at the boundary, require service-specific stream finality, persist completeness atomically, and reserve the audit-qualified label for complete traces. Executed deterministic development diagnostic only: 34 of 34 named checks; static audit found 10 of 31 requirements present, 9 partial, 12 absent; zero model, external-service or production-database calls. E21-B and six hypotheses are proposed and untested. No model benchmark, production change, or deployment.

Minimal-Disclosure Invocation Receipts (MDIR) that bind application-observable evidence delivery for authorized audit while keeping raw prompts and source text out of routine telemetry. Executed deterministic development harness only: 76 of 76 named checks across 96 constructed episodes, eight synthetic task families, twelve corruption families, and 6,912 mutated episode-arm evaluations; 480 valid reveals verified and 480 altered reveals rejected; zero model calls. E20-B and four hypotheses are proposed and untested. No new model benchmark, production change, or deployment.

A measurement contract for reconstructing which source version reached each agent and how the final answer is bound to it. Executed deterministic diagnostics only: 44 named checks across 15 constructed fixtures; a static audit found 4 of 18 collector requirements present, 3 partial, 11 absent. E19-B and three hypotheses are proposed and untested. No new model benchmark, model call, production change, or deployment.

A versioned support and dependency ledger that separates valid time from recorded time, keeps disputes explicit, and repairs only affected conclusions. Executed deterministic constructed diagnostic only: 36 passing checks, twelve developer fixtures. The model study and three hypotheses are proposed and untested. No language-model benchmark, model call, human annotation, production change, or deployment.

A bounded handoff with declared scope and source locators, checked when the question changes. Executed finite constructed diagnostics only: 28 named checks, 15 partitions, 60 recompressions, twelve developer fixtures. The model study is proposed, not run or preregistered, and three hypotheses are untested. No new model benchmark, Noetis performance gain, or deployment.

A bounded contrastive sufficiency probe and separate source-coverage probe. Executed finite-world diagnostics only: 6,912 Boolean pairs, 37 named checks, twelve developer fixtures. The model study and three hypotheses are proposed and untested with language models. No new model benchmark, deployment, or calibrated release guarantee.

Distinguishes messages that change an answer from messages that improve it, and how separate evidence can be valuable only when combined. Exact mathematical diagnostics and proposed experiments; not new Noetis benchmark results.

A measurement protocol for revision gains when evaluation labels are missing, ambiguous, or differentially biased: joint label sets, bounds on repair and damage, and a protected random audit. Primary-source synthesis and 30 exact offline diagnostic checks; no new model benchmark, inference, or expert annotation.

A reproducible audit of saved Noetis records, an offline trace validator, and a pilot protocol for measuring repair, damage, and matched-cost advantage. Audit of existing artifacts and offline checks; no new model inference runs or calibrated release guarantee.

Calibrate the final revised answer under a defined selective-risk target; test whether terminal evidence and revision features improve useful release coverage at identical generation compute. Primary-source synthesis, proposed experiment, and executed exact synthetic diagnostics; no new language-model benchmark.

Predicting repair and damage with claim-specific checks, short bundles, and controlled end-to-end cost. No new Encevra or LLM benchmark; only exact illustrative diagnostic calculations were run.

A critical review and proposed experimental program: what communication and revision protocol makes a correction trustworthy enough to reuse? Introduces hypothesis H10, six comparison arms, and a falsification plan.

A testable question for the lab: whether systems can acquire useful procedures from verified experience, reuse them on unfamiliar problems, and revise them when conditions change, with two experiments specified for the next 90 days.

A failure mode in belief revision: models can acknowledge counterevidence in their response while retaining an incompatible conclusion. We examine what structured adversarial review can and cannot recover.

A research note on eligibility traces, delayed credit assignment and consolidation: how later feedback might modify a temporary trace without destabilising previously learned behaviour.

An examination of hippocampal replay as a hypothesis for recombining evidence into new inferences, with careful limits on its analogy to multi-agent analysis.

The cognitive-science hypotheses informing Encevra's approach to specialist coordination, evidence integration and adaptive reasoning.