Evidence record
Selected versions and limits. The original Currentness v0.2 ZIP has been recovered and hash-checked against the identical Zenodo download; its 24 cases reproduce 10/24, 16/24 and 24/24 against author labels. Of the 17 primary sources, 16 remain SOURCE_MISSING. Missing originals have not been reconstructed, and Foundry, TRACE and Receipt Gate have not been rerun. Bounded reproduction and SELF_REVIEW, without independent evaluation.
RESEARCH SUMMARY · SELF_REVIEW
B01 · SELF_REVIEW
A conflict test suite
Currentness v0.2 preserves 24 cases, code and results: latest-write-wins 10/24; authority-first 16/24; reference 24/24 against author labels. This is consistency within that corpus, not independent semantic validation. Later self-review found additional cases that challenge generalizing the resolver. See F01.
Original-source status · documentary review: Currentness v0.2 release package recovered with matching SHA-256 (1/2 required originals in this group). The original adjudication_results.json is missing; labels and semantic interpretation lack independent adjudication.
Evidence archive withheld. Original sources marked as outstanding have not been fully verified; the private JSON is not part of this review.
Return to this record · Español
RESEARCH SUMMARY · SELF_REVIEW
B02 · SELF_REVIEW
An experiment lab
Experiment Foundry R2 has source code, evaluation records and a 17-scenario report. It is a synthetic laboratory. The R2 version reviewed here is recorded as R2_NOT_VALIDATED. It establishes neither real-world performance nor an independently qualified evaluator. See F02 for an R1 failure and the bounded R2 repair.
Original-source status · documentary review: Foundry R1/R2 original sources outstanding: 7/7 without matching SHA-256 in this review. Reported outcomes come from historical summaries and self-review; the experiment was not rerun here.
Evidence archive withheld. Original sources marked as outstanding have not been fully verified; the private JSON is not part of this review.
Return to this record · Español
RESEARCH SUMMARY · SELF_REVIEW
B03 · SELF_REVIEW
A source-reading prototype
TRACE V1.1 is a local, decoupled adapter with a prospective protocol. The retained suite reports 108/108 checks; the captured sample produced ABSTAIN. SELF_REVIEW, with partial source coverage. This is not native Core integration, predictive validation or evidence of economic utility. This card describes V1.1; later V1.2 work is separate.
Original-source status · documentary review: TRACE V1.1 original sources outstanding: 5/5 without matching SHA-256 in this review. The historical 108/108 figure is attributed to the version record; it was not rerun here and does not establish predictive usefulness.
Evidence archive withheld. Original sources marked as outstanding have not been fully verified; the private JSON is not part of this review.
Return to this record · Español
RESEARCH SUMMARY · SELF_REVIEW
F01 · SELF_REVIEW
A passing suite was insufficient
In the retained case, B corrects C and A remains unlinked. Output B is reproduced; UNKNOWN is the author’s expectation under local precedence. The 15 October review leaves open a rival global-priority interpretation and possible author misinterpretation. SELF_REVIEW / DISPUTED: a counterexample to the proposed criterion, not an unambiguous bug or independent adjudication. The original 24/24 does not settle this dispute.
Original-source status · documentary review: Currentness v0.2 release package recovered with matching SHA-256 (1/2 required originals in this group). The original adjudication_results.json is missing; the counterexample interpretation remains disputed and independently unadjudicated.
Evidence archive withheld. Original sources marked as outstanding have not been fully verified; the private JSON is not part of this review.
Return to this record · Español
RESEARCH SUMMARY · SELF_REVIEW
F02 · SELF_REVIEW
Consistent reports were insufficient
The retained summary of the historical review states that an authorized falsifier supplied 11 self-consistent reports for a false-causality scenario, that R1 accepted them and that the honest control failed. That summary attributes to R2 the rejection of the retained attack as INVALID_EXPERIMENT, with the holdout closed. The historical review reported inspecting the R2 receipt and the R1 audit, without rerunning R1 or recovering its vulnerable-run stdout. In this website review, those originals have not been recovered and Foundry has not been rerun; these claims remain pending verification. R2 remains unvalidated.
Original-source status · documentary review: Foundry R1/R2 original sources outstanding: 7/7 without matching SHA-256 in this review. The negative result is a summarized historical record, not a new execution or independent audit.
Evidence archive withheld. Original sources marked as outstanding have not been fully verified; the private JSON is not part of this review.
Return to this record · Español
RESEARCH SUMMARY · SELF_REVIEW
F03 · SELF_REVIEW
A receipt check could approve nothing
The retained R1 evaluation records PASS_BOUNDED, delivery_allowed=true and evidence_grade=NONE for null. Each of two runs found three false acceptances among 36 contract negatives. The package verdict is KILL. This is a failure of that candidate validator, not evidence that AEGIS performed an external action. SELF_REVIEW.
Original-source status · documentary review: Receipt Gate original sources outstanding: 3/3 without matching SHA-256 in this review. The anomaly is reported from a historical summary; it was neither reproduced nor independently verified here.
Evidence archive withheld. Original sources marked as outstanding have not been fully verified; the private JSON is not part of this review.
Return to this record · Español
Currentness v0.2 · Zenodo