| # Executive summary |
|
|
| --- |
| <!-- trackio-cell |
| {"type": "markdown", "id": "composite_dTMrITkTr5_summary", "created_at": "2026-07-31T02:31:21.708213+00:00", "title": "Claim-selective evidence upgrade", "pinned": true, "pinned_at": "2026-07-31T02:31:21.708213+00:00"} |
| --> |
| ## Claim-selective evidence upgrade |
|
|
| The existing canonical reproduction was retained for claims where it already |
| had equal or stronger evidence. The following weaker claim pages were replaced |
| with stronger current public evidence: |
|
|
| - Claim 4: [ai-sherpa/source-screening-repro](https://huggingface.co/spaces/ai-sherpa/source-screening-repro) (falsified) |
| - Claim 5: [snaykey/repro-source-screening-shared-feature-extractors](https://huggingface.co/spaces/snaykey/repro-source-screening-shared-feature-extractors) (verified) |
|
|
|
|
| --- |
| <!-- trackio-cell |
| {"type": "markdown", "id": "cell_source_reuse_summary", "created_at": "2026-07-21T06:27:02+00:00", "title": "Executive summary", "pinned": true, "pinned_at": "2026-07-21T06:27:02+00:00"} |
| --> |
| This canonical logbook independently audits all five supplied claims for [OpenReview dTMrITkTr5](https://openreview.net/forum?id=dTMrITkTr5). The main result is now supported by **1,520 seeded split-local-averaging fits**, including a new high-dimensional stress grid up to `d=320` and `N=51,200`; the empirical error stays within `1.884–2.449 × sqrt(d/(N lambda_k))`. The remaining pages preserve a deterministic theorem-condition counterexample, an executable algorithm-constant audit, a release audit for the unavailable real-data pipeline, and a 500-seed screened-versus-full comparison. |
|
|
| ## Scope & cost |
|
|
| | Scope | Hardware | Cost | |
| |---|---|---| |
| | 1,520 rate fits + 500-seed estimator comparison + exact theorem/algorithm audits | Local CPU | under 30 CPU-min; no paid compute | |
|
|
| --- |
| <!-- trackio-cell |
| {"type":"markdown","id":"cell_upgrade_source_summary","created_at":"2026-07-25T14:26:03+00:00","title":"Upgrade summary (2026-07-25)"} |
| --> |
| The audit now includes an explicit theorem-to-algorithm ledger and release-boundary ledger. Claim 1 remains the positive reproduction. Claims 2 and 3 are source-level wording/specification contradictions rather than failed stochastic experiments. Claim 4 remains source-verified but experimentally indeterminate, and Claim 5 remains a well-powered negative robustness check—not an exact implementation match. These distinctions prevent paper values, proxy estimators, and theorem statements from being conflated. |
|
|
|
|
| --- |
| <!-- trackio-cell |
| {"type": "figure", "id": "cell_source_poster", "created_at": "2026-07-21T06:27:05+00:00", "title": "Reproduction poster", "pinned": true, "pinned_at": "2026-07-21T06:27:05+00:00"} |
| --> |
| ````html |
| <!-- poster_embed.html --> |
| <iframe src="https://chenruishuo-posterly.hf.space" title="Posterly reproduction poster" style="width:100%;height:720px;border:0" loading="lazy"></iframe> |
| ```` |
|
|
