{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39807391", "kind": "science-record", "revision": 2, "content_hash": "sha256:2bfd5db43271310d8f6fb09d4945284f613817570ce613c7ce11599e228cbd03", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:33Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Investigating combined hypoxia and stemness indices for prognostic transcripts in gastric cancer: Machine learning and network analysis approaches.", "doi": "10.1016/j.bbrep.2024.101897", "pmid": "39807391", "authors": null, "journal": "Biochemistry and biophysics reports", "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": 0.81, "unit": "auc", "tolerance": null, "source": "chars 1621-1812 of source sha256 6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96"}, "evidence": [{"asset": "source:pmid:39807391", "locator": "chars 1621-1812 of source sha256 6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96", "quote": "The decision tree, based on genes such as AKAP6, GLRB, and RUNX1T1, achieved an AUC of 0.81 (training) and 0.67 (test), demonstrating the utility of combined scores in patient stratification."}]}], "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:39807391"], "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:39807391", "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:39807391' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39807391", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.bbrep.2024.101897", "sha256": "sha256:6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.bbrep.2024.101897", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39807391:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3ac721b6c953c07d0b6ebaf3accfcdd41b35d7646285fa80808a5e5c2f9c2e9d", "bytes": 325, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#tbl1", "version": null, "note": "Decision tree model performance metrices", "structure": {"pmcid": "PMC11729012", "section_index": 16, "section_title": "Survival analysis of the shared genes and construction of a decision tree", "row_count": 2, "column_count": 6}, "table": {"label": "Table 1", "caption": "Decision tree model performance metrices", "rows": [["AUCa", "Precision", "Recall", "F1 score", "Youden's index", "Maximum classification accuracy"], ["0.68", "0.73", "0.76", "0.75", "0.26", "0.32"]], "row_count": 2, "column_count": 6, "numeric_cells": 6, "header_rows": 1, "locator": "section[16]/table-wrap[1]#tbl1"}}], "gaps": ["asset:source:pmid:39807391 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:39807391", "asset:table:pmid:39807391:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39807391"]}, "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": "57729dcb87c3dd0ddcddb39f84fe9f1401ac40be9b27c31aa84509f158c8d408", "source_hash": "6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96", "raw_response_sha256": "sha256:bd3d03cbf9bf2ad912def3a5947d776efc7c40df231a3670ff2322a49d28bc39", "raw_response_chars": 3658}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "c82a6903e524c2c75479f7a46de6fba2c4d03d90bf89cd0774787b71b910620a", "source_hash": "6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96", "raw_response_sha256": "sha256:d649bd8623dfb8ab8ec03c6a8d31855687871a88ad65880b75dfe1afbe01c5e0", "raw_response_chars": 76721}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "9c1c1c5a61d7defc1fbd414d14b63150a20fb51e9cac24d655e359afa8e8ee7d", "source_hash": "6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96", "raw_response": "{\"parent_value\":0.81,\"unit\":\"AUC\",\"evidence\":\"The decision tree, based on genes such as AKAP6, GLRB, and RUNX1T1, achieved an AUC of 0.81 (training) and 0.67 (test), demonstrating the utility of combined scores in patient stratification.\",\"target_result\":\"The prognostic decision tree achieved an AUC of 0.81 in the training set.\",\"number_stated\":true}", "reading": {"parent_value": 0.81, "unit": "AUC", "evidence": "The decision tree, based on genes such as AKAP6, GLRB, and RUNX1T1, achieved an AUC of 0.81 (training) and 0.67 (test), demonstrating the utility of combined scores in patient stratification.", "target_result": "The prognostic decision tree achieved an AUC of 0.81 in the training set.", "number_stated": true, "source_locator": "chars 1621-1812 of source sha256 6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96"}, "recorded_at": "2026-10-31T15:21:03.165673+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "392a09d339f0fc3e27e98f32e7bd11deffe48c6f140b88aa8631dd92bf7fcc9f", "source_hash": "6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96", "raw_response": "<think>We need answer JSON only per developer and user. Need determine single numerical headline result paper main finding registered target \"the headline numerical result the paper itself states for its main finding\". Source abstract results says decision tree achieved AUC 0.81 (training) and 0.67 (test). They request single numerical result. Need decide which one registered target means likely headline AUC perhaps 0.81? Need carefully parse. We must extract claims only source. Report headline number only value paper states registered target, not calculate etc. Unit paper prints. Evidence exact contiguous quote contains number, attribution whole clause if attached via list/respectively. Need likely parent_value 0.81, unit \"AUC\", evidence full sentence/clause \"The decision tree, based on genes such as AKAP6, GLRB, and RUNX1T1, achieved an AUC of 0.81 (training) and 0.67 (test), demonstrating the utility of combined scores in patient stratification.\" Target result perhaps \"The prognostic decision tree achieved an AUC of 0.81 in the training set.\" number_stated true. But is headline target one value or two? User asks \"single numerical result that a replication of the registered target has to reproduce. Report the headline number only\". There are two AUCs, but headline maybe training AUC 0.81 (main result) and test 0.67 external. They may expect 0.81 AUC. Need infer task convention. They stress \"single numerical result ... registered target: headline numerical result ... main finding\". In source abstract \"The decision tree ... achieved an AUC of 0.81 (training) and 0.67 (test)\" headline numerical result. Usually extraction target might be AUC of decision tree, multiple values complicate. Could be target result includes two? But required parent_value number only. Need choose 0.81 likely as headline (training performance) and 0.67 validation. Need no conversion. Unit \"AUC\" not percentage. Evidence exact contiguous quote whole clause includes both if attribution list. They explicitly \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" So evidence should full clause sentence \"The decision tree, based on genes such as AKAP6, GLRB, and RUNX1T1, achieved an AUC of 0.81 (training) and 0.67 (test), demonstrating the utility of combined scores in patient stratification.\" Could choose exact from results detailed \"The efficiency of the model was evaluated using the ROC curves, according to which the AUC of the training and the test sets were 0.81 and 0.67, respectively (Fig. 7b and c).\" Whole clause necessary to map. That is clear respectively. If parent 0.81, evidence quote entire sentence to link respectively. Unit AUC. Target_result concise \"AUC of 0.81 in the training set.\" They ask \"Report headline number only\" likely target_result shouldn't include other number. We can provide 0.81 only in target_result? Schema field target_result string. Could say \"The decision tree achieved a training-set AUC of 0.81.\" Good.\n\nNeed think if headline number maybe six clusters among 375? No main finding is prognostic decision tree AUC 0.81. Source has abstract results concluding AUC 0.81 training and 0.67 test. We choose 0.81. But possible task expects the single numerical result as e.g. \"AUC 0.81\". Need cite full sentence in abstract, no paraphrase in evidence. JSON valid unicode quotes not necessary.\n\nWe should not include analysis etc final just JSON. Need respect \"Report headline number only\" maybe target_result = \"AUC = 0.81 (training set).\" It says evidence exact contiguous. Full sentence works. Parent_value 0.81 unit \"AUC\". number_stated true. target_result \"The decision tree achieved an AUC of 0.81 in the training set.\" This contains number. They might mean target_result explains target only, number no extra. Fine.\n\nLet's consider alternative detailed sentence \"the AUC of the training and the test sets were 0.81 and 0.67, respectively (Fig. 7b and c).\" It explicitly maps. Better quote exactly whole clause (and maybe full sentence) because attribution respectively. \"The efficiency of the model was evaluated using the ROC curves, according to which the AUC of the training and the test sets were 0.81 and 0.67, respectively (Fig. 7b and c).\" Exact contiguous from source. That's sufficient, no paraphrase. It contains 0.81 and 0.67 but they require quote whole clause when linked. We cannot remove 0.67 because respectively ties both. They request headline number only but evidence needs include other number. Fine target_result mentions only 0.81. Using abstract sentence parentheses likewise. Which is stronger? Detailed sentence explicitly respective train/test. Full sentence quote. Unit AUC, no conversion. Good.\n\nNeed ensure \"single numerical result that a replication of the registered target has to reproduce\" maybe they want 0.67 since \"target\" from abstract final? Let's deeply consider wording maybe benchmark style. They give REGISTERED TARGET \"the headline numerical result the paper itself states for its main finding\". Many such tasks user asks source claims for \"parent study\" etc; they want value not calculated. Here ambiguous. We need choose what paper itself states headline. They highlight main finding. AUC 0.81 training and 0.67 test both in one headline. But singular suggests prioritize headline. Could interpret target as \"AUC of 0.81\" main finding and test 0.67 is validation. We should not overthink. Need perhaps evidence quote abstract sentence because headline numerical result located there. It explicitly says achieved AUC 0.81 (training) and 0.67 (test). Headline is 0.81. Detailed same.\n\nMaybe they expect \"0.81\" and \"AUC\" evidence exact full clause. Good.\n\nWe can finish.</think>\n\n{\"parent_value\":0.81,\"unit\":\"AUC\",\"evidence\":\"The efficiency of the model was evaluated using the ROC curves, according to which the AUC of the training and the test sets were 0.81 and 0.67, respectively (Fig. 7b and c).\",\"target_result\":\"The prognostic decision tree achieved a training-set AUC of 0.81.\",\"number_stated\":true}", "reading": {"parent_value": 0.81, "unit": "AUC", "evidence": "The efficiency of the model was evaluated using the ROC curves, according to which the AUC of the training and the test sets were 0.81 and 0.67, respectively (Fig. 7b and c).", "target_result": "The prognostic decision tree achieved a training-set AUC of 0.81.", "number_stated": true, "source_locator": "chars 9878-10052 of source sha256 6aae6bf32ac7a55498786cde4d089d5b45eea1090011d68c0f086c6bb6b00d96"}, "recorded_at": "2026-10-31T15:21:21.307707+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The prognostic decision tree achieved an AUC of 0.81 in the training set and 0.67 in the test set.", "minimax_alt": "The decision tree, based on genes such as AKAP6, GLRB, and RUNX1T1, achieved an AUC of 0.81 (training) and 0.67 (test), demonstrating the utility of combined scores in patient stratification.", "decisive": false}, "analysis_methods": {"minimax": ["Gene Set Variation Analysis (GSVA)", "mRNA expression-based stemness index (mRNAsi)", "one-class logistic regression (OCLR)", "hierarchical clustering", "Kaplan-Meier survival analysis", "log-rank test", "edgeR differential expression analysis", "Weighted Gene Co-expression Network Analysis (WGCNA)", "survival analysis of shared genes", "Recursive Partitioning", "receiver operating characteristic (ROC) curve analysis"], "minimax_alt": ["Gene Set Variation Analysis (GSVA)", "mRNA expression-based stemness index (mRNAsi) using Spearman's method", "Hierarchical clustering", "Kaplan-Meier curve and log-rank test", "edgeR differential-expression analysis", "Weighted Gene Co-expression Network Analysis (WGCNA)", "GO and KEGG functional enrichment analysis", "Protein-protein interaction (PPI) network analysis", "Recursive Partitioning", "ROC curve analysis with AUC"], "decisive": false}, "statistical_method": {"minimax": "Receiver operating characteristic (ROC) curve analysis", "minimax_alt": "ROC curve analysis with area under the curve (AUC)", "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:50ce53f9d7f6cc1087a874122c1409fb28200096a00669063f1dc8aa12d2394c", "type": "sep_package", "label": "SEP v1 package for pmid:39807391"}], "activities": [{"id": "activity:conversion:pmid:39807391", "type": "conversion", "used": ["package:50ce53f9d7f6cc1087a874122c1409fb28200096a00669063f1dc8aa12d2394c"], "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:39807391", "parent_hash": "sha256:002f93c168e886cbf71233872ebaf2d1597c2481fc357ce5420069956d820ea3", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39807391 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:39807391' 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":"2026-11-04T01:46:58+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}}}