{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40746611", "kind": "science-record", "revision": 2, "content_hash": "sha256:93da4fe2bd29058f68294da9f3e1066c2b0a122280cb689a5ce2801a8737489d", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:45Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrating single-cell regulatory atlas and multi-omics data for differential treatment response and multimodal predictive modeling in CDK 4/6 inhibitor-treated breast cancer.", "doi": "10.3389/fonc.2025.1585574", "pmid": "40746611", "authors": null, "journal": "Frontiers in 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": 86.0, "unit": "resistance-associated regulons", "tolerance": null, "source": "chars 1162-1294 of source sha256 bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984"}, "evidence": [{"asset": "source:pmid:40746611", "locator": "chars 1162-1294 of source sha256 bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984", "quote": "We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3)."}]}], "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:40746611"], "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:40746611", "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:40746611' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40746611", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2025.1585574", "sha256": "sha256:bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2025.1585574", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40746611:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0703d60b4dca63e198861ef239cdc5d055df94483061ed9aed47a38b67dc2281", "bytes": 902, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#T1", "version": null, "note": "The sample information of P11 through P46 in 10x single cells: the second column in the table is whether or not there was a response to treatment, and the third column is whether or not a CDK4/6 i was used in the treatment (i.e. Ribociclib).", "structure": {"pmcid": "PMC12310732", "section_index": 2, "section_title": "Materials", "row_count": 18, "column_count": 3}, "table": {"label": "Table 1", "caption": "The sample information of P11 through P46 in 10x single cells: the second column in the table is whether or not there was a response to treatment, and the third column is whether or not a CDK4/6 i was used in the treatment (i.e. Ribociclib).", "rows": [["Patient", "Response", "Ribociclib given or endocrine alone"], ["P11", "No Phase E samples"], ["P12", "Non-responder", "1"], ["P13", "Non-response", "1"], ["P14", "Response", "0"], ["P15", "Non-response", "0"], ["P16", "Responder", "0"], ["P17", "No Phase E samples"], ["P18", "No Phase E samples"], ["P19", "No Phase E samples"], ["P20", "Non-response", "0"], ["P21", "Responder", "1"], ["P22", "Response", "1"], ["P23", "No Phase E samples"], ["P24", "No Phase E samples"], ["P25", "Response", "1"], ["P26", "No Phase E samples"], ["P27", "Response", "1"]], "row_count": 18, "column_count": 3, "numeric_cells": 27, "header_rows": 1, "locator": "section[2]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:40746611 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:40746611", "asset:table:pmid:40746611:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40746611"]}, "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": "b6ad5acdab2c55e493bd8a898b8f31c9a55b2ccfa2ae54f985639b7b0a3d9e14", "source_hash": "bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984", "raw_response_sha256": "sha256:df1c9acd296d100a8fc49ad4c6c35eba5d2dab60482ff79a798e90d3d3bfa7cd", "raw_response_chars": 7045}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "3bf34a3ce14cd9d5ef92edaaa3bcd088eb1349143c98d29b468fd2e3bce6a9b3", "source_hash": "bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984", "raw_response_sha256": "sha256:f3d6c1ada93613eaa1f97d96d727dc5724d63da6552650fdd72495108b58d603", "raw_response_chars": 58745}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "5ae24c76b5eeedbc9ec2492e237915cfd62b6ea946ea81761ac86979b6a05eea", "source_hash": "bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984", "raw_response": "{\"parent_value\":86,\"unit\":\"resistance-associated regulons\",\"evidence\":\"We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3).\",\"target_result\":\"The paper states that 86 resistance-associated regulons were identified.\",\"number_stated\":true}", "reading": {"parent_value": 86, "unit": "resistance-associated regulons", "evidence": "We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3).", "target_result": "The paper states that 86 resistance-associated regulons were identified.", "number_stated": true, "source_locator": "chars 1162-1294 of source sha256 bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984"}, "recorded_at": "2026-10-31T15:24:38.003216+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "aa4755af7eb357aecd8f975708c7a9c700c8642c57743a0b247b2928a3cd39f6", "source_hash": "bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984", "raw_response": "<think>We need answer JSON only. Need identify headline numerical result paper states main finding. Need carefully interpret target. Paper abstract results: identified 86 resistance-associated regulons; TPRI; multimodal model superior prognostic accuracy (95%CI:0.6575-0.75). Registered target headline numerical result paper states for main finding. Which single numerical result replication of registered target has reproduce. Need likely headline number perhaps 86 resistance-associated regulons? Or model AUC? Need infer from wording. \"main finding\" paper itself states. Numerical result likely \"We identified 86 resistance-associated regulons\" or multimodal model accuracy CI. Headline number perhaps 86? Need determine.\n\nUser asks \"Read supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. ... REGISTERED TARGET: the headline numerical result the paper states for its main finding.\"\n\nWe need select one numerical result. The abstract's main finding perhaps TPRI and model, and headline numerical outcome could be 95% CI 0.6575–0.75. But asks \"single numerical result\", \"headline number\", maybe target corresponds to one scalar. Could be number of resistance-associated regulons: 86. Evidence exact contiguous quote. Parent value number. Unit maybe \"resistance-associated regulons\" or \"regulons\". They say unit must be unit paper prints. Could unit empty if dimensionless? Schema asks string. Need perhaps \"86 resistance-associated regulons\". Evidence exact contiguous quote. Target_result description.\n\nLet's deeply parse likely benchmark/task. Registered target vague but intended identify \"headline numerical result the paper states for its main finding\". There may be many numbers. Usually these prompts ask extract one numerical result for a target, often e.g. sample size or AUC. Here target intentionally generic. They expect identify headline result, likely \"86 resistance-associated regulons\". Why? Results starts \"We identified 86 resistance-associated regulons and established TPRI...\" This is first/main result. The model performance is perhaps \"95%CI:0.6575-0.75\" but that's an interval, not a single headline number. User explicitly says \"single numerical result\" and \"headline number only\", \"parent_value number\". The only clear scalar headline finding is 86 resistance-associated regulons. There are also P=0.0237, P<0.01, P<2.2e-16, CI. The headline finding likely count 86. Registered target wording \"the headline numerical result the paper states for its main finding\" perhaps target = headline number of main finding, likely 86.\n\nNeed ensure exact evidence quote containing number and attribution. Exact contiguous: \"We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3).\" This is exact source. Value 86, unit maybe \"resistance-associated regulons\" (paper prints phrase). target_result maybe \"The paper identified 86 resistance-associated regulons.\" number_stated true.\n\nCould unit simply \"regulons\"? \"unit must be the unit the paper prints.\" The text prints \"86 resistance-associated regulons\", so unit could be \"resistance-associated regulons\". Likely.\n\nBut let's not jump. Analyze possibility target is \"95%CI:0.6575-0.75\", perhaps parent_value 0.6575? Yet asks headline number only and target result. Since range isn't one number, schema parent_value number means maybe extract lower bound? Not allowed reconstructed, but could value? There is no single headline. So likely 86.\n\nCould headline numerical result be P=0.0237? Main finding TPRI stratification significant with differential survival and treatment response. A replication would reproduce effect significance P=0.0237? But paper's \"main finding\" stated as TPRI biomarker; headline numerical result could be P-value. Yet wording \"headline numerical result\" often in these extraction prompts means specific result (e.g., \"86 resistance-associated regulons\"). Need reason based on supplied paper organization and repeated abstract/results. \"We identified 86 resistance-associated regulons and established TPRI...\" prominent. Main title integrating atlas etc. 86 likely main discovery.\n\nCould output unit \"%\" for CI? No, no central AUC value, only CI. There is \"superior prognostic accuracy (95%CI:0.6575-0.75)\"—maybe replication needs reproduce AUC confidence interval, not scalar, contradict schema. Number 0.75 could be upper CI but headline number only no.\n\nQuestion might have been generated to ask parent result from a paper, with target unspecified due semantic mapping. \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\" This likely asks us to identify title/abstract headline. The 86 regulons count is clean.\n\nNeed JSON valid, no markdown. parent_value 86; unit likely \"resistance-associated regulons\"; evidence exact contiguous quotation. target_result perhaps \"The study identified 86 resistance-associated regulons.\" number_stated true.\n\nCheck no extra properties. Ensure evidence exact punctuation. Source: \"We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3).\" exact. Could quote only \"We identified 86 resistance-associated regulons\" contiguous and sufficient. User says when attached target directly, quote whole clause so check attribution. Better whole sentence. Unit printed: \"resistance-associated regulons.\" Could unit perhaps \"regulons\" more conventional. They explicitly require unit paper prints; phrase is printed. \"resistance-associated regulons\" safe.\n\ntarget_result not necessarily quote. We can state direct.\n\nNeed answer JSON only.</think>\n\n{\"parent_value\":86,\"unit\":\"resistance-associated regulons\",\"evidence\":\"We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3).\",\"target_result\":\"The paper identifies 86 resistance-associated regulons as a main finding.\",\"number_stated\":true}", "reading": {"parent_value": 86, "unit": "resistance-associated regulons", "evidence": "We identified 86 resistance-associated regulons and established TPRI based on five prognostic TFs (ATF1, TEAD4, NFIL3, FOXO1, ETV3).", "target_result": "The paper identifies 86 resistance-associated regulons as a main finding.", "number_stated": true, "source_locator": "chars 1162-1294 of source sha256 bcb23a132a21407ef446bd9cb4eb55ddf7216c05a0629922d1110d7368e50984"}, "recorded_at": "2026-10-31T15:24:44.929726+00:00"}], "agreement": true, "disagreements": {"physical_methods": {"minimax": ["qPCR", "qRT-PCR"], "minimax_alt": ["qPCR", "real-time quantitative PCR (qRT-PCR)"], "decisive": false}, "analysis_methods": {"minimax": ["SCENIC", "limma", "logistic regression", "ROC/AUC analysis", "Student’s t-test", "one-way ANOVA with Holm-Sidak’s multiple comparison"], "minimax_alt": ["SCENIC", "Seurat", "reciprocal pairwise canonical correlation analysis (CCA) with mutual nearest neighbor anchoring", "principal component analysis (PCA)", "uniform manifold approximation and projection (UMAP)", "graph-based clustering", "limma", "enrichGO with clusterProfiler", "logistic regression", "ROC/AUC analysis", "Fisher’s exact test", "Student’s t-test", "one-way ANOVA with Holm-Sidak’s multiple comparison", "2-ΔΔCT method"], "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:31c971a7cf34a3e5d705ce955c2ffcc62baa008220c6f4d50b60485984cbbe68", "type": "sep_package", "label": "SEP v1 package for pmid:40746611"}], "activities": [{"id": "activity:conversion:pmid:40746611", "type": "conversion", "used": ["package:31c971a7cf34a3e5d705ce955c2ffcc62baa008220c6f4d50b60485984cbbe68"], "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:40746611", "parent_hash": "sha256:28a8d753c03d0b56a5ae697c853d0fbf1f1b6a77edaaf92f710171bd2d186751", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40746611 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:40746611' 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":"2026-11-04T01:45:40+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}}}