rewirebio.iobenchmarks
Evidence claim

HyInv report: training evaluation overlap

Training evaluation overlap of HyInv

The authors state: 'We do not claim zero sequence overlap between the training data and the evaluation panels.' The reinforcement-learning pool was filtered against the benchmark panels with a same-source homology mask built from MMseqs2 searches of the candidate records against the benchmark sequences, excluding a record if it is positive under the mask and using a record only if that search queried it; the supervised corpus was filtered by exact-sequence removal and a homology filter. For the application panels Appendix G's screen is a coverage rule: a hit counts only if its identity is at least 0.3 and it covers at least 0.8 of the query or of the target, so partial hits remain, and the report says a backbone passing the rule is homology-filtered at these thresholds, 'which is weaker than having no similar fragment in the library'.

Descriptive fact read from the pinned sources at the locator given. Not a measurement on a benchmark panel.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

6 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Claimed field
training_evaluation_overlap
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.field

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Source location
Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Claimed value
The authors state: 'We do not claim zero sequence overlap between the training data and the evaluation panels.' The reinforcement-learning pool was filtered against the benchmark panels with a same-source homology mask built from MMseqs2 searches of the candidate records against the benchmark sequences, excluding a record if it is positive under the mask and using a record only if that search queried it; the supervised corpus was filtered by exact-sequence removal and a homology filter. For the application panels Appendix G's screen is a coverage rule: a hit counts only if its identity is at least 0.3 and it covers at least 0.8 of the query or of the target, so partial hits remain, and the report says a backbone passing the rule is homology-filtered at these thresholds, 'which is weaker than having no similar fragment in the library'.
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.value

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Description
Descriptive fact read from the pinned sources at the locator given. Not a measurement on a benchmark panel.
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: description

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Relationship: subject
hyinv-20261106-model-hyinv
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: links:subject:hyinv-20261106-model-hyinv

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Name
HyInv report: training evaluation overlap
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: name

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: hyinv-20261106-claim-hyinv-training-evaluation-overlap

areas
proteins-complexes; protein-structure
contexts
research
field
training_evaluation_overlap
review
artifact sha256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419; method: independent-cell-check; deterministic-table-parse; pdf-text-parse; source-hash-verification; method note: Independent review pass. The pinned PDF was re-downloaded at the pinned commit and its SHA-256 checked against the source record; pdftotext -layout reproduced the archived text layer byte for byte. npm run batch -- check-values was run over the whole batch against that text layer (value-check.tsv). The 170 cells of Tables 6, 7, 8 and 9 and the 290 cells of the Figure 14 and Figure 15 matrices were then re-read by a reviewer script that finds each row by its printed label and splits the printed cells by position, written for this pass without using the extractor's parser; every printed value and column matched. Column assignment in Figure 14 was confirmed against the labelled columns of Table 2 and against Section 5.2's prose figures; Figure 15's was confirmed by the coordinator reading the rotated column headers on the rendered page 17, which match Figure 14's order. Table 1, Figure 4a and the eleven prose values were read by hand against the text layer. Each claim was re-read against the passage its locator names.; retrieval url: https://raw.githubusercontent.com/Tencent-Hunyuan/Hyra-results/0dcc533cc9f8f76c90ecbfe944df816b6672328a/AI4Science/hyinv/HyInv_Technical_Report.pdf; reviewed at: 2026-11-06T00:00:00Z; reviewer: claude; reviewer note: Claude research agent; no human review claimed. Reviewed by a different agent from the one that extracted the batch. Transcription checked against the pinned source; nothing was reproduced and no value was recomputed.
source locator
Appendix C 'Data and pool', third and fourth bullets; Appendix G 'Homology of the panels'; Table 10
value
The authors state: 'We do not claim zero sequence overlap between the training data and the evaluation panels.' The reinforcement-learning pool was filtered against the benchmark panels with a same-source homology mask built from MMseqs2 searches of the candidate records against the benchmark sequences, excluding a record if it is positive under the mask and using a record only if that search queried it; the supervised corpus was filtered by exact-sequence removal and a homology filter. For the application panels Appendix G's screen is a coverage rule: a hit counts only if its identity is at least 0.3 and it covers at least 0.8 of the query or of the target, so partial hits remain, and the report says a backbone passing the rule is homology-filtered at these thresholds, 'which is weaker than having no similar fragment in the library'.
Related records

Suggest a correction