{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40056247", "kind": "science-record", "revision": 1, "content_hash": "sha256:51e9bc4155d8be747b286dc5b9ae3b66cf7df1816d8fbb06541670f41d30fa28", "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": "Prognostic risk modeling of endometrial cancer using programmed cell death-related genes: a comprehensive machine learning approach.", "doi": "10.1007/s12672-025-02039-8", "pmid": "40056247", "authors": null, "journal": "Discover oncology", "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": 0.8, "unit": "auc", "tolerance": null, "source": "chars 931-1039 of source sha256 1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a"}, "evidence": [{"asset": "source:pmid:40056247", "locator": "chars 931-1039 of source sha256 1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a", "quote": "The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8)."}]}], "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:40056247"], "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:40056247", "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:40056247' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40056247", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-02039-8", "sha256": "sha256:1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-02039-8", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40056247 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:40056247"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40056247"]}, "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": "552458a50591bf6358fb1c974dd32a029877e9b3823b133dee2bd5fda45cd5b0", "source_hash": "1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a", "raw_response_sha256": "sha256:ca37f119c9c0b4cec12117c5952f6cb022b0a00c773053b7affa95791180d77b", "raw_response_chars": 3398}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "060cb07d5b43375decceb83e469a385f33c1a7255be538ec76f56d949949450e", "source_hash": "1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a", "raw_response_sha256": "sha256:3371e8aca1ef2ebfe20cd71ef85d0f49f251afaab618ee344c0f224c06599b69", "raw_response_chars": 61186}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "9e1b3f5986e848b74d58d338fe7d9d011d6b0e3745d43a395dc4e7274a6fbc83", "source_hash": "1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a", "raw_response": "{\"parent_value\":0.8,\"unit\":\"AUC\",\"evidence\":\"The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8).\",\"target_result\":\"The model achieved an AUC > 0.8.\",\"number_stated\":true}", "reading": {"parent_value": 0.8, "unit": "AUC", "evidence": "The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8).", "target_result": "The model achieved an AUC > 0.8.", "number_stated": true, "source_locator": "chars 931-1039 of source sha256 1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a"}, "recorded_at": "2026-10-31T15:33:23.956847+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "42ea7853e7b1e1417f8bb73896227f76cfead73fe4c41912ac5f58fc4a10eb56", "source_hash": "1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline main finding registered target. Paper abstract: StepCox+plsRcox excellent predictive accuracy (AUC > 0.8). Likely headline number 0.8, unit AUC? User asks value paper itself states, unit paper prints. Need parse. \"single numerical result that a replication ... reproduce. Report headline number only: value paper itself states for registered target\". Main finding likely AUC > 0.8. Could be HR 3.37 etc. Headline numerical result probably AUC > 0.8, numerical headline. Need parent_value number 0.8, unit maybe \"AUC\" (unitless? Paper prints AUC > 0.8). Evidence exact contiguous quote containing number and target attribution: \"The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8).\" target_result perhaps \"AUC > 0.8\". number_stated true. But \"headline number only\" likely value 0.8. Unit must paper prints. Could unit be \"AUC\" perhaps. Is AUC a unit? Printed metric. JSON parent_value numeric cannot encode >; target_result can say \"AUC > 0.8\". They likely expect unit \"AUC\" or perhaps empty? Instruction \"unit must be unit paper prints.\" The paper prints AUC, not a unit. Usually extraction task asks value and unit. Could set unit \"AUC\" perhaps accepted. Need perhaps \"AUC\" as metric label. Evidence exact quote. Let's ensure no issue that > 0.8 is threshold rather than exact result. Yet source states numerical result. The headline result likely model AUC > 0.8. Other headline 10 critical genes and 117 algorithms, but \"main finding\" perhaps prognostic model with AUC >0.8. User wants single numerical result. Yes.\n\nCould HR 3.37 be more headline? Abstract emphasizes predictive accuracy AUC > .8 and survival differences HR. \"headline numerical result the paper states for its main finding.\" Target generic. Usually benchmark target probably asks extract one numerical result associated with target. Main finding is model performance. AUC >0.8 headline. The result sentence immediately after model construction. Number 0.8.\n\nNeed exact contiguous quote, whole clause. \"The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8).\" This attaches target. Unit perhaps \"AUC\". target_result perhaps \"AUC > 0.8\".</think>\n\n{\"parent_value\":0.8,\"unit\":\"AUC\",\"evidence\":\"The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8).\",\"target_result\":\"AUC > 0.8\",\"number_stated\":true}", "reading": {"parent_value": 0.8, "unit": "AUC", "evidence": "The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8).", "target_result": "AUC > 0.8", "number_stated": true, "source_locator": "chars 931-1039 of source sha256 1d76360e1eff4904d83d9f3dca5eb18158ebd2976d68d00bdc5d3ae14507559a"}, "recorded_at": "2026-10-31T15:33:28.162616+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The StepCox[forward] + plsRcox prognostic model achieved excellent predictive accuracy, with AUC > 0.8.", "minimax_alt": "Kaplan–Meier analysis revealed significant survival differences between high- and low-risk groups in both training (HR = 3.37, p < 0.001) and validation cohorts (HR = 2.05, p = 0.021).", "decisive": false}, "analysis_methods": {"minimax": ["117 machine learning algorithms", "StepCox[forward] + plsRcox", "Kaplan–Meier analysis", "differential gene expression analysis", "weighted gene co-expression network analysis", "functional enrichment analysis", "immune landscape evaluation", "multi-dimensional risk stratification"], "minimax_alt": ["117 machine learning algorithms", "StepCox[forward] + plsRcox algorithm combination", "Kaplan–Meier analysis", "differential gene expression analysis using the limma package in R", "weighted gene co-expression network analysis (WGCNA)", "STRING protein–protein interaction network analysis", "GO and KEGG pathway enrichment analyses using clusterProfiler", "gene set enrichment analysis (GSEA)", "immune cell infiltration analysis", "somatic mutation analysis", "drug sensitivity analysis"], "decisive": false}, "statistical_method": {"minimax": "StepCox[forward] + plsRcox algorithm combination", "minimax_alt": "Kaplan–Meier analysis", "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:8106bbd890e1494d87989d8c342b1cfa83f67b2920fcf46354b1e447423da129", "type": "sep_package", "label": "SEP v1 package for pmid:40056247"}], "activities": [{"id": "activity:conversion:pmid:40056247", "type": "conversion", "used": ["package:8106bbd890e1494d87989d8c342b1cfa83f67b2920fcf46354b1e447423da129"], "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": "3c946e88-b6ca-46a9-9fe3-3b4ac0ac502a", "parent_hash": "8106bbd890e1494d87989d8c342b1cfa83f67b2920fcf46354b1e447423da129", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40056247 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:40056247' 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":"2026-11-04T01:32:28+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}}}