{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40950700", "kind": "science-record", "revision": 2, "content_hash": "sha256:37cda7e56127fabfc88a6824bb0d7769176973458256a40d53bcd9a7c4f1da75", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T14:01:48Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development and validation of an immune-related gene signature for the prognostic and immune landscape prediction in head and neck squamous cell carcinoma by integrated analysis of machine learning and Mendelian randomization.", "doi": "10.21037/tcr-2024-2665", "pmid": "40950700", "authors": null, "journal": "Translational cancer research", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 3.647, "unit": "hazard ratio", "tolerance": null, "source": "chars 1831-1985 of source sha256 bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c"}, "evidence": [{"asset": "source:pmid:40950700", "locator": "chars 1831-1985 of source sha256 bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c", "quote": "The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001)."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40950700"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40950700", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40950700' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40950700", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tcr-2024-2665", "sha256": "sha256:bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tcr-2024-2665", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40950700:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:23748cf1a5922654617501ca07afa615c5b84d0029f84e446cb807002eae9357", "bytes": 1207, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t1", "version": null, "note": "Clinicopathological features of the patients with head and neck squamous carcinomas in this study", "structure": {"pmcid": "PMC12432597", "section_index": 4, "section_title": "Data collection", "row_count": 30, "column_count": 3}, "table": {"label": "Table 1", "caption": "Clinicopathological features of the patients with head and neck squamous carcinomas in this study", "rows": [["Covariates", "TCGA cohort", "GSE65858 cohort"], ["Age", "", ""], ["≤65 years", "338 (66.14)", "182 (68.16)"], [">65 years", "173 (33.86)", "85 (31.84)"], ["Sex", "", ""], ["Female", "133 (26.03)", "47 (17.60)"], ["Male", "378 (73.97)", "220 (82.40)"], ["Histologic grade", "", ""], ["G1–2", "359 (70.25)", "–"], ["G3–4", "130 (25.44)", "–"], ["Unknown", "22 (4.31)", "–"], ["T stage", "", ""], ["T1–2", "180 (35.23)", "114 (42.70)"], ["T3–4", "268 (52.45)", "153 (57.30)"], ["Unknown", "63 (12.33)", "–"], ["N stage", "", ""], ["N0", "172 (33.66)", "93 (34.83)"], ["N1–3", "239 (46.77)", "174 (65.17)"], ["Unknown", "100 (19.57)", "–"], ["Metastasis status", "", ""], ["Yes", "1 (0.20)", "–"], ["No", "181 (35.42)", "–"], ["Unknown", "329 (64.38)", "–"], ["Clinical stage", "", ""], ["Stage I–II", "97 (18.98)", "54 (20.22)"], ["Stage III–IV", "339 (66.34)", "213 (79.78)"], ["Unknown", "75 (14.68)", "–"], ["Survival status", "", ""], ["Dead", "214 (41.88)", "91 (34.08)"], ["Alive", "297 (58.12)", "176 (65.92)"]], "row_count": 30, "column_count": 3, "numeric_cells": 41, "header_rows": 1, "locator": "section[4]/table-wrap[1]#t1"}}], "gaps": ["asset:source:pmid:40950700 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40950700", "asset:table:pmid:40950700:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40950700"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "037aa7b59a0163df981f7a2e1ebe9e1fabc4b4ff4d1e83ae6c52b5dac8a43e61", "source_hash": "bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c", "raw_response_sha256": "sha256:ad2787b47c15d38ff7576e3d1f747c3e7b57946aa16a4fd2eaac48350579da9a", "raw_response_chars": 5053}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "2627bb857708fdb860f511c902ca01e2e58249a6c9d7cab079532866de3978ad", "source_hash": "bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c", "raw_response_sha256": "sha256:906f98643ed30b17a659d1c3ede080843d6c832f19e6eb8135306fd432207220", "raw_response_chars": 35131}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "1b17cdfe1d5dcc2a51556eb185bb58dc6cb9bd4236c388dafd747f4a5c2e497e", "source_hash": "bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c", "raw_response": "{\"parent_value\":3.647,\"unit\":\"hazard ratio\",\"evidence\":\"The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).\",\"target_result\":\"The risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).\",\"number_stated\":true}", "reading": {"parent_value": 3.647, "unit": "hazard ratio", "evidence": "The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).", "target_result": "The risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).", "number_stated": true, "source_locator": "chars 1831-1985 of source sha256 bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c"}, "recorded_at": "2026-10-31T15:35:39.273614+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "c0f53a9d282b6c6ea272ec50e740610f5328463a37adf080ccc3c8d52c728d7e", "source_hash": "bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c", "raw_response": "<think>We need answer JSON object only. Need identify single numerical result headline for registered target = headline numerical result paper states for main finding. Need infer which number. Source has several candidates: 10 IRGs, AUCs 0.694, .731, .656, hazard ratio 3.647. Headline numerical result likely hazard ratio = 3.647? User asks \"single numerical result that a replication of the registered target has to reproduce\" and registered target \"the headline numerical result the paper itself states for the main finding.\" Need report headline number only, paper stated, not calculated. Evidence exact contiguous quote containing number. Likely 3.647, unit \"hazard ratio\" perhaps. Need decide.\n\nCould be \"Ten IRGs\" but headline numerical result? Main finding is novel immune-related gene signature; ten IRGs. A replication target likely signature's performance? The abstract highlights 10 IRGs and AUCs and HR. \"headline numerical result\" often asks identify a specific primary numerical outcome. Here likely hazard ratio 3.647. Need not overthink? Let's parse wording. \"REGISTERED TARGET: the headline numerical result the paper itself states for its main finding\". They want one number, unit. Evidence exact quote. The main finding includes signature; key finding no number. In Results first number \"Ten IRGs were identified...\" This is arguably the headline count of main finding. But \"headline numerical result\" likely refers to the number reported in abstract perhaps hazard ratio. Which one singular?\n\nLet's inspect title and abstract. Main finding: risk score independent prognostic factor associated with HNSCC (hazard ratio =3.647, P&lt;0.001). The headline quantitative performance likely HR. AUC list has 3 values, violates single number unless choose best .731? Instructions explicitly mention attribution via parenthetical list, respectively — perhaps designed to handle multi-value AUC sentence? Yet request \"single numerical result.\" Maybe they expect e.g. number can be attached by parenthetical list. Here perhaps target is \"the headline numerical result\" and candidate is HR 3.647. Parenthetical list mention generic benchmark instruction. Need output evidence whole clause when attribution indirect. Evidence could be exact sentence: \"The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P&lt;0.001).\" Unit \"hazard ratio\". parent_value 3.647. target_result maybe concise \"Hazard ratio of 3.647 for the risk score as an independent prognostic factor associated with HNSCC.\" They say \"Report the headline number only\" likely target_result should just number/unit, no extraneous values. Need avoid mentioning P. Evidence necessarily includes P, okay. Unit paper prints? It prints \"hazard ratio\" perhaps unit dimensionless. Could say \"hazard ratio\" rather than \"HR\". JSON valid.\n\nBut let's thoroughly assess possibility that expected number is \"Ten\" / \"10 IRGs\". Registered target wording could point to \"the headline numerical result the paper itself states for its main finding\" and source's headline: \"Ten IRGs were identified and incorporated into the predictive signature.\" This may be more headline than HR. Yet replication of \"registered target\" requires reproduce the main finding, likely model composed of 10 genes. A headline number might be AUC at 1,3,5 years, but that's three. They insist single numerical result, perhaps choose \"hazard ratio = 3.647\". Why mention \"single\" if source has multiple? It's designed to disambiguate only one headline result. Hazard ratio explicitly called result in abstract.\n\nLet's understand task schema semantics: `parent_value` weird naming maybe standardized benchmark where target could be \"hazard ratio\" and parent_value numerical. They ask number stated. \"REGISTERED TARGET: the headline numerical result the paper itself states for its main finding.\" They may expect extraction based on target description rather than specific field. We need identify best.\n\nMaybe this benchmark asks \"replication of registered target\" where a registered report has one target? Here target is broad. Headline numerical result usually from abstract's conclusion? In abstracts, quantitative result frequently hazard ratio. The primary claim is prognostic signature; performance measures: 10 IRGs, AUC at years, HR. Which is headline? The first sentence in results says 10 IRGs; the \"headline numerical result\" could indeed be 10. But replication of main finding would need reproduce signature and its reported HR. Let's inspect abstract structure:\n- Objective\n- Methods data counts\n- Results: Ten IRGs... AUC ... KM ... multivariate ... HR=3.647...\n- Conclusion.\nMain quantitative claim probably HR because prognostic significance. The number 10 is model composition, not effect result.\nQuestion says \"headline numerical result\" singular, likely asks effect estimate. \"value the paper itself states for the registered target\" likely HR.\nEvidence must exact contiguous quotation containing number. We can quote full sentence, exact punctuation. Unit must paper prints. \"hazard ratio\" is label. Could set unit \"hazard ratio\". Is that a unit? Hazard ratio is dimensionless measure, but prompt allows unit as printed. Alternatively \"hazard ratio =3.647\" means value 3.647 and unit \"hazard ratio\". Usually output parent_value number and unit \"hazard ratio\". We should not use \"3.647\" in target_result plus unit perhaps.\n\nCould output:\n{\"parent_value\":3.647,\"unit\":\"hazard ratio\",\"evidence\":\"The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).\",\"target_result\":\"3.647 hazard ratio\",\"number_stated\":true}\nDoes \"headline number only\" mean target_result should only be number perhaps \"3.647\". They ask report headline number only, likely no extra. JSON has fields. Could set target_result \"3.647 (hazard ratio)\" but evidence enough. Maybe target_result is prose for if false; when true likely number/unit. Schema no guidance. To be safe target_result: \"3.647\" only. But then unit separately. Evidence sentence includes attribution. \"headline number only\" perhaps target_result \"3.647 hazard ratio\". They explicitly say report headline number only: value and unit. Let's make \"3.647 (hazard ratio)\"? Number only might mean don't give all AUCs. Fine.\n\nNeed ensure exact source quote. Source sentence exact: \"The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).\" Yes.\n\nCould there be space around equals? Printed \"hazard ratio =3.647\". Exact quote must preserve. Fine.\n\nLet's think if they instead expect 10 IRGs. We need maximize. Analyze linguistic cue \"headline numerical result the paper itself states for its main finding.\" If target were 10 genes, unit \"IRGs\", evidence \"Ten IRGs were identified and incorporated into the predictive signature.\" But parent_value needs number; \"Ten\" is textual numeral, but instruction \"single numerical result\" and \"number paper states\" could convert word to 10? They explicitly say don't convert; \"value the paper itself states\" perhaps if number printed as \"Ten\", parent_value 10 still numeric representation necessarily converted. They might want 10. Yet \"headline number\" typically 10 IRGs is first result. But source's \"main finding\" is the IRG signature. The count of IRGs is perhaps central headline. Hazard ratio is also central.\n\nCould phrase target result be \"the headline numerical result the paper itself states for its main finding\"—perhaps generated target mapping from scientific paper benchmark where registered target is \"headline numerical result\". They want identify one. The abstract's headline numeric claim often the central effect. For prognostic papers, hazard ratio is likely.\n\nLook at \"unit must be the unit the paper prints.\" Hazard ratio is not a physical unit but measure label. \"Ten IRGs\" has unit IRGs. AUC values have unit AUC. Which one seems likely given instruction on parenthetical list and \"respectively\"? Maybe they intentionally included that because source sentence with AUC list might tempt returning multiple values. The target could be AUC perhaps \"the area under ROC curves for overall survival at 1, 3, and 5 years\" but registered target generic, not specify year. Thus impossible to choose one among three, indicating not AUC.\n\nThey mention \"a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" This generic instruction would apply to HR in parenthetical \"(hazard ratio =3.647, P&lt;0.001)\"—indeed direct naming within parentheses. For AUC sentence, each value attached by respectively and time points. But target perhaps could be \"headline numerical result\" as one of them? No.\n\nMaybe headline number is \"hazard ratio =3.647\" because it's directly parenthetical and singular. Good.\n\nNeed only JSON, no markdown. Let's ensure number_stated boolean. parent_value 3.647. unit perhaps \"hazard ratio\". target_result \"3.647\". But target_result should likely describe result? They say \"Report the headline number only\" so \"3.647\" is apt. Evidence has full exact quote. Unit separate.\n\nLet's answer.</think>\n\n{\"parent_value\":3.647,\"unit\":\"hazard ratio\",\"evidence\":\"The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).\",\"target_result\":\"3.647\",\"number_stated\":true}", "reading": {"parent_value": 3.647, "unit": "hazard ratio", "evidence": "The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).", "target_result": "3.647", "number_stated": true, "source_locator": "chars 1831-1985 of source sha256 bf593054b21be92025c7c550b61793bbc6e61c81f15a72659525e813040ddc6c"}, "recorded_at": "2026-10-31T15:35:47.323325+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "A 10-IRG prognostic signature was established; the risk score was an independent prognostic factor for HNSCC with a hazard ratio of 3.647 (P<0.001).", "minimax_alt": "The multivariate prognostic analysis showed that the risk score was an independent prognostic factor associated with HNSCC (hazard ratio =3.647, P<0.001).", "decisive": false}, "analysis_methods": {"minimax": ["machine learning algorithms", "Kaplan-Meier survival analysis", "multivariate prognostic analysis", "receiver operating characteristic curve analysis", "subgroup analysis", "Wilcoxon signed-rank test", "Chi-squared test", "Pearson correlation analysis", "gene set enrichment analysis", "single-sample gene set enrichment analysis", "CIBERSORT", "Tumor Immune Dysfunction and Exclusion score analysis", "Immunophenoscore analysis", "Mendelian randomization", "MR-Egger intercept examination", "Cochran Q test for heterogeneity", "leave-one-out sensitivity analysis"], "minimax_alt": ["machine learning algorithms", "area under the receiver operating characteristic curves", "Kaplan-Meier survival analysis", "multivariate prognostic analysis", "subgroup analysis", "Mendelian randomization (MR)", "gene set enrichment analysis (GSEA)", "single-sample GSEA (ssGSEA)", "CIBERSORT", "Wilcoxon signed-rank test", "Chi-squared test", "Pearson correlation analysis", "leave-one-out sensitivity analysis", "MR-Egger", "IVW", "Cochran Q test"], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:5d83b9e8c7582e4866577ce291988a26ab166e50ba06c0ebfc74aeb4e309e92c", "type": "sep_package", "label": "SEP v1 package for pmid:40950700"}], "activities": [{"id": "activity:conversion:pmid:40950700", "type": "conversion", "used": ["package:5d83b9e8c7582e4866577ce291988a26ab166e50ba06c0ebfc74aeb4e309e92c"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40950700", "parent_hash": "sha256:29f4ce93c8b092fd745817053090ff5f69499511426fea617731dbacb3be82aa", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40950700 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40950700' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:03:28+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}