{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39944588", "kind": "science-record", "revision": 1, "content_hash": "sha256:49575b70a3ff756739a1230fa2d3cdf41f2c7e5e691dc8a9e0c1b502b81e13e1", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T10:25:49Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Pan-gastrointestinal adenocarcinoma analysis uncovers the prognostic and immune correlates of ferroptosis-related genes.", "doi": "10.21037/tgh-24-15", "pmid": "39944588", "authors": null, "journal": "Translational gastroenterology and hepatology", "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": 0.67, "unit": "hazard ratio (hr)", "tolerance": null, "source": "chars 1159-1355 of source sha256 66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734"}, "evidence": [{"asset": "source:pmid:39944588", "locator": "chars 1159-1355 of source sha256 66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734", "quote": "The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87]"}]}], "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:39944588"], "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:39944588", "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:39944588' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39944588", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tgh-24-15", "sha256": "sha256:66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tgh-24-15", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:39944588 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:39944588"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39944588"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "d54686694fe6d7d26773d093b676989e57b11af52c090129cd91c38edafa26de", "source_hash": "66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734", "raw_response_sha256": "sha256:550ecc47be9586b5a89585953a997f74497c579fcfecec69b05d9b9b38068a62", "raw_response_chars": 8366}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "fd067a9cd63957cd06c88755851f7310ec8cdb7900c66f2f8a6c48124085feea", "source_hash": "66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734", "raw_response_sha256": "sha256:87519868106415bb8a5d7a863c67e38795f93559296a97a2abcac24d7b7b3c20", "raw_response_chars": 62773}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "7b4fefc9454e9c7602bdc239544279d69dc6a5b83fdbc9a9b9647c694450477e", "source_hash": "66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734", "raw_response": "{\"parent_value\":0.67,\"unit\":\"hazard ratio (HR)\",\"evidence\":\"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87]\",\"target_result\":\"The headline training-cohort result was a hazard ratio of 0.67 for the ferroptosis-score and overall survival.\",\"number_stated\":true}", "reading": {"parent_value": 0.67, "unit": "hazard ratio (HR)", "evidence": "The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87]", "target_result": "The headline training-cohort result was a hazard ratio of 0.67 for the ferroptosis-score and overall survival.", "number_stated": true, "source_locator": "chars 1159-1355 of source sha256 66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734"}, "recorded_at": "2026-10-31T15:30:53.772146+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "b6851b14169329a4f31f14bcc80a49db5b120472100e17d8b6e4b884b4300c63", "source_hash": "66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734", "raw_response": "<think>We need answer JSON only. Need determine single numerical result replication registered target headline main finding. Source abstract states training cohort TCGA P=.003 HR 0.67 CI .52-.87, validation HRs. \"headline number\" likely HR 0.67? Registered target main finding. Need report value paper states for registered target, not calculated. Unit printed perhaps hazard ratio? Need exact contiguous quotation contains number. Number likely 0.67, unit \"hazard ratio (HR)\"? Evidence exact clause/sentence. They request headline number only, unit paper prints. Could choose HR 0.67 and unit \"hazard ratio (HR)\" or maybe no unit? JSON fields.\n\nNeed carefully interpret. The main finding: ferroptosis-score significantly associated favorable overall survival in training cohort TCGA: P=0.003; hazard ratio (HR), 0.67, 95% CI. Headline numerical result likely HR 0.67. Replication of registered target has to reproduce. Could target be AUC? No such. Need quote whole clause attribution. Exact contiguous evidence perhaps \"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87]\" This exact quote contains and attribution. unit \"hazard ratio (HR)\" maybe dimensionless. They say unit must be unit paper prints. Hazard ratio isn't unit exactly but metric. Could put \"hazard ratio (HR)\". target_result concise.\n\nNeed \"headline number only\" means parent_value 0.67, evidence quote can include surrounding clause mandated. Unit perhaps \"hazard ratio (HR)\" but JSON expected. Could use \"hazard ratio\" exactly printed. Exact quote must exact contiguous; use sentence maybe ends before and? Quote can be clause. Ensure no shortening? User says \"do not shorten it\" likely evidence exact quotation, not necessarily entire source. They explicitly say quote whole clause. So quote full clause: \"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87] and across the four validation cohorts ...\" To attach target to number, likely whole sentence ideally. Evidence exact full sentence from Results, including all cohorts. They said \"headline number only\" perhaps evidence can full sentence. Need choose target result 0.67 from training cohort. Full sentence includes multiple numbers but parent_value one. Is that okay? \"single numerical result\" and \"headline number only\" likely answer number 0.67; evidence necessarily includes CI and P. Could quote clause with training cohort. Exact contiguous quotation from source text. It can be: \"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87]\" But grammatically this is contiguous substring, though not complete sentence. \"do not shorten it\" perhaps asks exact full quote, no ellipsis; likely this clause suffices.\n\nCould unit be \"hazard ratio (HR)\"? Unit field maybe empty because HR unitless. But instruction says unit must be unit paper prints. Paper prints \"hazard ratio (HR)\" and value 0.67. Usually extraction benchmark expects unit maybe \"HR\". Registered target is main finding perhaps target_result should identify \"training-cohort hazard ratio for overall survival\". Parent value 0.67. Unit \"hazard ratio (HR)\" is a measure not unit. We can set unit \"hazard ratio (HR)\" to preserve printed designation. Maybe unit should be \"\" if unitless, but required says unit string and \"unit must be unit paper prints.\" It might expect unit \"HR\". Need infer task origin: \"headline numerical result\" perhaps compare numerical value. They want fields parent_value, unit, evidence, target_result, number_stated. Parent value could be 0.67. Unit \"hazard ratio (HR)\". target_result perhaps \"The ferroptosis-score was significantly associated with favorable overall survival in the TCGA training cohort.\" Fine.\n\nNeed exact evidence. Let's ensure punctuation exactly: \"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87] and across the four validation cohorts (GSE17536: P=0.03; HR, 0.57, 95% CI: 0.34–0.96; GSE19417: P=0.047; HR, 0.53, 95% CI: 0.28–1.01; GSE84437: P=0.004; HR, 0.68, 95% CI: 0.51–0.90; GSE103479: P=0.03; HR, 0.55, 95% CI: 0.32–0.96).\" Full exact quote. But then evidence contains five numerical results, conflicting single headline? Yet attribution to 0.67 clear due \"training cohort\". Could quote full clause up to bracket only, no ellipsis. User: \"Attribution may be carried by the text's own wording... When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" The clause is \"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: ...]\" likely quote. Exact contiguous. \"do not shorten it\" likely means don't use \"...\" to skip. This is okay.\n\nCould headline numerical result instead be cohort sample n=828? Main finding headline HR clearly. Maybe title/abstract first quantitative result is P=.003 and HR=.67. Replication target likely wants effect size HR. \"headline number\" convention chooses primary metric, likely HR. Need not choose p-value. Unit \"hazard ratio\". If asking numerical result replication target, likely they registered target in some broader task perhaps main finding statistic. Source says association; primary result is HR. So yes.\n\nNeed JSON valid, no markdown. Evidence exact. Should unit be \"hazard ratio (HR)\" or \"HR\"? They demand paper prints unit. Exact paper wording is \"hazard ratio (HR), 0.67\". Unit designation perhaps \"hazard ratio (HR)\". Maybe dimensionless so unit should be \"\". Yet schema insists string but can empty. They specifically say unit must be unit paper prints, likely if no physical unit, use metric label. In similar tasks, unit may be \"hazard ratio (HR)\". Let's phrase.\n\ntarget_result could be \"Training-cohort hazard ratio for overall survival in the TCGA cohort.\" Or perhaps must state what text says instead only if false. Here number stated true, target_result should identify target result. Maybe \"TCGA training-cohort overall-survival hazard ratio for the ferroptosis-score.\" Fine.\n\nEvidence full clause perhaps:\n\"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87]\"\nIs the phrase \"whole clause\" ending without \"and across...\" weird. Better full sentence exactly, but then multiple numbers. They asked single number but evidence can have context. To identify training HR, full sentence works. Yet registered target \"headline numerical result\" perhaps no explicit cohort registration. Full sentence may expose multiple candidates. The training cohort is labeled. We can quote the exact complete first clause, but source punctuation uses \"and across...\" continuing. A clause technically includes \"both ... and across...\" Full sentence is safest and exact. Evidence can include all because exact contiguous quote. But perhaps instruction \"headline number only\" means don't report other results in target_result, not evidence. We'll do full sentence.\n\nCould quote just abstract sentence same exact. Full sentence includes all. Unit printed \"hazard ratio (HR)\" and then subsequent cohorts \"HR\". Use \"hazard ratio (HR)\".\n\nNeed ensure en dash exact. JSON Unicode okay. Return only object.</think>\n\n{\"parent_value\":0.67,\"unit\":\"hazard ratio (HR)\",\"evidence\":\"The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87] and across the four validation cohorts (GSE17536: P=0.03; HR, 0.57, 95% CI: 0.34–0.96; GSE19417: P=0.047; HR, 0.53, 95% CI: 0.28–1.01; GSE84437: P=0.004; HR, 0.68, 95% CI: 0.51–0.90; GSE103479: P=0.03; HR, 0.55, 95% CI: 0.32–0.96).\",\"target_result\":\"Overall-survival hazard ratio for the ferroptosis-score in the TCGA training cohort.\",\"number_stated\":true}", "reading": {"parent_value": 0.67, "unit": "hazard ratio (HR)", "evidence": "The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87] and across the four validation cohorts (GSE17536: P=0.03; HR, 0.57, 95% CI: 0.34–0.96; GSE19417: P=0.047; HR, 0.53, 95% CI: 0.28–1.01; GSE84437: P=0.004; HR, 0.68, 95% CI: 0.51–0.90; GSE103479: P=0.03; HR, 0.55, 95% CI: 0.32–0.96).", "target_result": "Overall-survival hazard ratio for the ferroptosis-score in the TCGA training cohort.", "number_stated": true, "source_locator": "chars 1159-1587 of source sha256 66736f01379a293914326c1a9d7f4d73c2cf6db431519866a1e78d2f34898734"}, "recorded_at": "2026-10-31T15:31:03.536915+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The ferroptosis-score was significantly associated with favorable overall survival in the TCGA training cohort (P=0.003; HR, 0.67, 95% CI: 0.52–0.87) and in four validation cohorts: GSE17536 (P=0.03; HR, 0.57, 95% CI: 0.34–0.96), GSE19417 (P=0.047; HR, 0.53, 95% CI: 0.28–1.01), GSE84437 (P=0.004; HR, 0.68, 95% CI: 0.51–0.90), and GSE103479 (P=0.03; HR, 0.55, 95% CI: 0.32–0.96).", "minimax_alt": "The ferroptosis-score was significantly associated with favorable overall survival both in the training cohort [TCGA: P=0.003; hazard ratio (HR), 0.67, 95% confidence interval (95% CI): 0.52–0.87] and across the four validation cohorts (GSE17536: P=0.03; HR, 0.57, 95% CI: 0.34–0.96; GSE19417: P=0.047; HR, 0.53, 95% CI: 0.28–1.01; GSE84437: P=0.004; HR, 0.68, 95% CI: 0.51–0.90; GSE103479: P=0.03; HR, 0.55, 95% CI: 0.32–0.96).", "decisive": false}, "analysis_methods": {"minimax": ["gene set variation analysis (GSVA)", "univariable Cox regression analysis", "multivariate Cox regression analysis", "Kaplan-Meier survival analysis", "log-rank test"], "minimax_alt": ["gene set variation analysis (GSVA)", "Kaplan-Meier survival analysis", "log-rank tests", "univariable Cox analysis", "multivariate Cox regression analysis"], "decisive": false}, "statistical_method": {"minimax": "Univariable and multivariable Cox regression analyses, together with Kaplan-Meier survival analysis with log-rank tests", "minimax_alt": "Kaplan-Meier analyses with log-rank tests; univariable and multivariable Cox regression analyses", "decisive": true}}, "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": "blocked", "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.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:603a6498c272921e6e66fe5f0a88ffd323ac195775b2302664fc6f0ac276a341", "type": "sep_package", "label": "SEP v1 package for pmid:39944588"}], "activities": [{"id": "activity:conversion:pmid:39944588", "type": "conversion", "used": ["package:603a6498c272921e6e66fe5f0a88ffd323ac195775b2302664fc6f0ac276a341"], "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": "1adc8b70-7bf6-4f3c-a13a-9c7da19b4229", "parent_hash": "603a6498c272921e6e66fe5f0a88ffd323ac195775b2302664fc6f0ac276a341", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:39944588 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "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:39944588' 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":"2026-11-04T01:44:37+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}}}