Proof bank

Receipts before claims.

Each entry is shaped for audit: ID, status, claim, setup, result, limit, reproduce, related repo/artifact, date, and confidence level.

Claim discipline: Claims are bounded to the linked experiment scale. Broad capability claims require benchmark receipts.

Receipt anatomy

The proof bank is intentionally repetitive. Strong claims should be boring to audit: same fields, same limits, same reproduction pressure.

Claim
Setup
Result
Limit
Replay
TS-003receipt

Local relaxation can generate global coherence

Toy constraint graph receipt showing a large tension reduction through local relaxation.

Claim: Local relaxation supports the narrow claim that local constraint updates can reduce global tension in a bounded graph.

relaxationgraphstelemetryts-core
View proof note
TS-004toy

Attractors emerge from local constraint relaxation

Hopfield-style binary graph receipt for noisy recovery and context-biased recovery.

Claim: Local relaxation can recover stable attractor states in a toy binary graph.

attractorrelaxationtoy
View proof note
TS-005receipt

Contradiction localizes as residual/provenance tension

Small graph receipt where a planted contradiction ranks first by residual energy and relief-if-removed.

Claim: Contradictions can localize as residual graph tension in a provenance-aware toy graph.

cigcontradictionprovenance
View proof note
TS-006receipt

Break/Evolve through context splitting

Mechanism receipt showing incompatible regimes become stable after context splitting.

Claim: Break/Evolve-style context splitting supports the narrow claim that mixed regimes can be separated to reduce tension.

break evolvecontextsrelaxation
View proof note
TS-008toy

Coherence vs complexity

Synthetic MDL-style receipt where three contexts beat underfit and overfit alternatives.

Claim: A tension-plus-complexity penalty can prefer a compact context split over both underfit and overfit variants.

coherencecomplexitymdl
View proof note
TS-009receipt

Provenance-weighted coherence

Provenance weighting improves error and catches bad sources in a controlled setup.

Claim: Source provenance can support more coherent aggregation than flat averaging in a bounded setup.

cigprovenancesources
View proof note
TS-011toy

Strategic Stabilization Graph

Toy planning graph receipt for reducing tension across selected public research assets.

Claim: A strategic graph can identify high-pressure documentation and proof-bank work without pretending the toy model is the real system.

strategysitestabilization
View proof note
TS-013draft

Bayesian update rigidity under regime change

Bayesian-style test showing decay/forgetting is needed when regimes change.

Claim: Overconfident priors can create rigidity under regime changes unless decay or revision pressure is present.

bayesianrevisionrigidity
View proof note
TS-014draft

CIG source correlation matters

CIG-style note showing correlated sources should not be treated as independent votes.

Claim: Dependency-aware consensus is needed because source correlation can inflate apparent agreement.

cigconsensussource correlation
View proof note
TS-015draft

Free-energy-style mixed-regime split

Free-energy-style framing for why context splits can solve mixed regimes.

Claim: Context splitting can reduce residual pressure when one model is forced across incompatible regimes.

free energycontextsrevision
View proof note
TS-016draft

Seeded Word-Function parser

Seeded parser line for semantic-frame accuracy under a toy grammar.

Claim: Seeded word-function structure can improve inspectability of parser decisions in a toy/synthetic grammar.

languageseeded parsertoy grammar
View proof note
TS-018draft

Learned tension weights

Seeded operator line testing learned tension weights under controlled negatives.

Claim: Learned tension weights can become a useful diagnostic signal when paired with hard negatives.

tension weightshard negativeslanguage
View proof note
TS-019draft

Hard-negative mining lesson

Negative examples are required before local tension/failure signals become meaningful.

Claim: Failure localization receipts are weak without hard negatives that pressure the model into mistakes.

proof rankerhard negativeslocalization
View proof note
TS-020planned

Seeded Operator LM direction

Planned receipt path for seeded operator language-model experiments.

Claim: Seeded operator structure is a research direction, not yet a benchmark claim.

operator lmplannedlanguage
View proof note
TS-021draft

TS-pi independent route audit

Audit-line receipt for independent pi routes and block-level tension.

Claim: Independent derivation routes can expose block tension and corruption pressure in a bounded audit.

auditpiprovenance
View proof note
TS-022draft

TS-pi corruption localization and selective repair

Audit-line receipt for identifying corrupted blocks and repairing selectively.

Claim: Block tension can support selective repair in a bounded corruption-localization setup.

auditrepairconsensus
View proof note
TS-023replication

Provenance consensus and dependency limits

Consensus note where provenance helps, but dependency-aware consensus remains the hard part.

Claim: Agreement should be weighted by provenance and dependency structure, not treated as simple vote count.

cigprovenanceconsensus
View proof note

TS-003

Local relaxation can generate global coherence

receiptStrong within toy scope

Claim

Local relaxation supports the narrow claim that local constraint updates can reduce global tension in a bounded graph.

Setup

Fixed-seed quadratic constraint graph with local update rules and tension telemetry.

Result

Tension fell from 156.216618 to 11.862658, a 92.4063% reduction.

Limit

Quadratic constraint graph only; this is not a full-scale reasoning benchmark.

Reproduce

Run the fixed-seed local relaxation script and compare initial/final tension.

Last updated

2026-05-20

Related repo

TS-Core

Related artifact/model

No public artifact linked yet.

TS-004

Attractors emerge from local constraint relaxation

toyStrong within toy scope

Claim

Local relaxation can recover stable attractor states in a toy binary graph.

Setup

Hopfield-style binary graph with 30% noise and a context-bias condition.

Result

30% noise recovery was around 87%; context bias improved recovery to about 98%.

Limit

Toy attractor graph; requires replication beyond synthetic binary states.

Reproduce

Replay the seeded attractor graph with and without context bias.

Last updated

2026-05-20

Related repo

TS-Core

Related artifact/model

No public artifact linked yet.

TS-005

Contradiction localizes as residual/provenance tension

receiptStrong within toy scope

Claim

Contradictions can localize as residual graph tension in a provenance-aware toy graph.

Setup

9 nodes and 16 constraints with one planted contradiction.

Result

The planted contradiction ranked #1 by residual energy and relief-if-removed; removing the bad edge reduced tension near zero.

Limit

Small planted contradiction test; requires larger messy-source replication.

Reproduce

Replay the 9-node graph, compute residual energy by edge, remove the top edge, and compare tension.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.

TS-006

Break/Evolve through context splitting

receiptStrong within toy scope

Claim

Break/Evolve-style context splitting supports the narrow claim that mixed regimes can be separated to reduce tension.

Setup

Two incompatible regimes: y-x approximately +2 and y-x approximately -2.

Result

Single global relation tension was 786.8852; context split tension was 0.5270, a 99.933% reduction.

Limit

Synthetic two-regime setup; not evidence of general unsupervised concept discovery.

Reproduce

Fit one global relation, then split by context and compare tension plus complexity penalty.

Last updated

2026-05-20

Related repo

TS-Core

Related artifact/model

No public artifact linked yet.

TS-008

Coherence vs complexity

toyMedium

Claim

A tension-plus-complexity penalty can prefer a compact context split over both underfit and overfit variants.

Setup

K=1..6 context candidates evaluated under MDL/tension plus complexity penalty.

Result

K=3 was best under the combined penalty.

Limit

Synthetic data; requires replication on public datasets.

Reproduce

Replay K=1..6 context scoring and verify the minimum at K=3.

Last updated

2026-05-20

Related repo

TS-Core

Related artifact/model

No public artifact linked yet.

TS-009

Provenance-weighted coherence

receiptStrong within toy scope

Claim

Source provenance can support more coherent aggregation than flat averaging in a bounded setup.

Setup

Mixed-source aggregation with trusted, noisy, and adversarial sources.

Result

Flat averaging error was 2.3185; provenance-weighted error was 0.7714; median error was 0.1996; suspicion caught 12/12 bad sources.

Limit

Controlled source model; real source correlation and incentives are harder.

Reproduce

Replay the seeded aggregation and suspicion-scoring script.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.

TS-011

Strategic Stabilization Graph

toyMedium

Claim

A strategic graph can identify high-pressure documentation and proof-bank work without pretending the toy model is the real system.

Setup

Selected proof-bank docs, Start Here page, Obsidian vault, research statement, and demo video as nodes in a stabilization graph.

Result

Weighted tension energy fell from 452.05 to 10.7258.

Limit

Strategic toy model; not a real productivity benchmark.

Reproduce

Replay the weighted stabilization graph with the selected asset nodes.

Last updated

2026-05-20

Related artifact/model

No public artifact linked yet.

TS-013

Bayesian update rigidity under regime change

draftMedium

Claim

Overconfident priors can create rigidity under regime changes unless decay or revision pressure is present.

Setup

Synthetic regime-change sequence with fixed and decayed priors.

Result

Decay/forgetting was needed to adapt after the regime shift.

Limit

Synthetic Bayesian-style test; requires public replay artifact.

Reproduce

Replay fixed-prior and decayed-prior update curves under a regime switch.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.

TS-014

CIG source correlation matters

draftMedium

Claim

Dependency-aware consensus is needed because source correlation can inflate apparent agreement.

Setup

Claim/evidence graph with correlated source branches and confidence updates.

Result

Source correlation changed confidence behavior compared with flat independent-source assumptions.

Limit

Draft receipt until backed by a public dataset and replay command.

Reproduce

Build correlated and independent source graphs, then compare confidence propagation.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.

TS-015

Free-energy-style mixed-regime split

draftMedium

Claim

Context splitting can reduce residual pressure when one model is forced across incompatible regimes.

Setup

Mixed regimes scored with pressure, fit, and complexity terms.

Result

Context split solved the mixed-regime pressure in the bounded setup; overconfident priors caused rigidity.

Limit

Framing receipt, not a general theory proof.

Reproduce

Replay mixed-regime scoring with and without context split and prior decay.

Last updated

2026-05-20

Related repo

TS-Core

Related artifact/model

No public artifact linked yet.

TS-016

Seeded Word-Function parser

draftLow

Claim

Seeded word-function structure can improve inspectability of parser decisions in a toy/synthetic grammar.

Setup

Synthetic grammar with seeded semantic-frame parser and fixed evaluation prompts.

Result

Records semantic-frame accuracy and trace structure for the seeded parser direction.

Limit

Toy/synthetic grammar; not a natural-language capability benchmark.

Reproduce

Replay fixed prompts against seeded parser exports and compare semantic frames.

Last updated

2026-05-20

Related repo

TensionLM

Related artifact/model

TS-018

Learned tension weights

draftLow

Claim

Learned tension weights can become a useful diagnostic signal when paired with hard negatives.

Setup

Seeded operator/word-function examples with learned local tension weights.

Result

The receipt captures the lesson that hard-negative mining matters for meaningful tension weights.

Limit

Synthetic grammar and small models; requires benchmark expansion.

Reproduce

Train with and without hard negatives and compare failed-step/tension localization.

Last updated

2026-05-20

Related repo

TensionLM

Related artifact/model

TS-019

Hard-negative mining lesson

draftMedium

Claim

Failure localization receipts are weak without hard negatives that pressure the model into mistakes.

Setup

Proof/language traces compared under easy negatives and hard negatives.

Result

Hard negatives exposed local tension behavior that easy negatives did not.

Limit

Lesson receipt; not a published full benchmark.

Reproduce

Run the same detector with easy negatives and hard negatives, then compare localization quality.

Last updated

2026-05-20

Related repo

Proof Ranker

Related artifact/model

TS-020

Seeded Operator LM direction

plannedLow

Claim

Seeded operator structure is a research direction, not yet a benchmark claim.

Setup

Operator-token traces, local tension telemetry, and fixed prompts.

Result

Next result should report parser/frame accuracy, tension diagnostics, and failure modes.

Limit

No broad claim until public benchmark receipts exist.

Reproduce

Pending: publish fixed prompts, checkpoint, seed, and export script.

Last updated

2026-05-20

Related repo

TensionLM

Related artifact/model

TS-021

TS-pi independent route audit

draftMedium

Claim

Independent derivation routes can expose block tension and corruption pressure in a bounded audit.

Setup

Multiple independent pi routes with block tension and provenance notes.

Result

Block tension highlighted disagreement locations for inspection.

Limit

Audit toy line; route independence must be proven, not assumed.

Reproduce

Replay independent route generation and compare block tension by segment.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.

TS-022

TS-pi corruption localization and selective repair

draftMedium

Claim

Block tension can support selective repair in a bounded corruption-localization setup.

Setup

Injected corruption in a pi audit route with block-level consensus checks.

Result

Corruption localized to high-tension blocks and selective repair targeted those blocks.

Limit

Requires stricter dependency-aware consensus tests.

Reproduce

Inject known block corruption, run audit tension, repair top blocks, and compare consensus.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.

TS-023

Provenance consensus and dependency limits

replicationMedium

Claim

Agreement should be weighted by provenance and dependency structure, not treated as simple vote count.

Setup

Claim/evidence graph with independent and dependent sources, contradictions, and provenance edges.

Result

Provenance consensus improved over flat voting, while dependency-aware consensus remained the limitation.

Limit

Needs public CIG dataset and replayable contradiction tests before strong benchmark claims.

Reproduce

Create a small claim/evidence graph, introduce conflicting evidence, and verify dependency-aware confidence updates.

Last updated

2026-05-20

Related repo

CIG

Related artifact/model

No public artifact linked yet.