{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40100580", "kind": "science-record", "revision": 2, "content_hash": "sha256:0b931a85455b6c4a305659c29272cda0a5ce81b3974eb5cddf845feb5cb40cb1", "created_at": "2026-11-01T10:25:50Z", "updated_at": "2026-11-01T14:01:38Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development and validation of M2 macrophage-related genes in a prognostic model of lung adenocarcinoma based on bulk RNA and ScRNA datasets.", "doi": "10.1007/s12672-025-02123-z", "pmid": "40100580", "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": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "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:40100580"], "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:40100580", "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:40100580' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40100580", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-02123-z", "sha256": "sha256:0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-02123-z", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40100580:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:087993df3e8d3b623753e3fb61875b2831bd43e09076642e3d1131690f2064f3", "bytes": 926, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Detailed information regarding the lung adenocarcinoma data sets", "structure": {"pmcid": "PMC11920479", "section_index": 3, "section_title": "Data sources", "row_count": 11, "column_count": 5}, "table": {"label": "Table 1", "caption": "Detailed information regarding the lung adenocarcinoma data sets", "rows": [["Data set", "Platform", "Type", "Group", "Survival time and status information"], ["GSE10072", "GPL96", "Bulk RNA-seq", "58 LUAD and 50 control", "No"], ["GSE115002", "GPL13497", "Bulk RNA-seq", "52 LUAD and 52 control", "No"], ["GSE116959", "GPL17077", "Bulk RNA-seq", "57 LUAD and 11 control", "No"], ["GSE32863", "GPL6884", "Bulk RNA-seq", "58 LUAD and 58 control", "No"], ["GSE43458", "GPL6884", "Bulk RNA-seq", "80 LUAD and 30 control", "No"], ["GSE14814", "GPL96", "Bulk RNA-seq", "70 LUAD", "Yes"], ["GSE37745", "GPL570", "Bulk RNA-seq", "105 LUAD", "Yes"], ["GSE50081", "GPL570", "Bulk RNA-seq", "125 LUAD", "Yes"], ["TCAG-LUAD", "N/A", "Bulk RNA-seq", "510 LUAD and 58 control", "Yes"], ["GSE149655", "GPL24676", "scRNA-seq", "2 LUAD and 2 control", "No"]], "row_count": 11, "column_count": 5, "numeric_cells": 28, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}], "gaps": ["asset:source:pmid:40100580 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:40100580", "asset:table:pmid:40100580:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40100580"]}, "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": "6add621ca15b659ac05188874ace932c8ec2b81fc6b9d472aa99b6b49799c157", "source_hash": "0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b", "raw_response_sha256": "sha256:2b0049667127d88d848eb156bfc5f9da03ea48b67e32cf28463cc6ec89cf204d", "raw_response_chars": 6252}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "3f018d578c07103d73a60de9ca76949d95194dfc276295dfca6e003a8796ac1a", "source_hash": "0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b", "raw_response_sha256": "sha256:c114070973eafa287b2a59f7ffab2c600725e3bf3b56e5ee955516a9dfff80f4", "raw_response_chars": 51665}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "f3215bc65a28ed6aba4c0adfeb7ca425c100a3e2504c8f1044c07f0656fdb09f", "source_hash": "0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b", "raw_response": "{\"parent_value\":4,\"unit\":\"key M2 macrophage–linked genes\",\"evidence\":\"We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.\",\"target_result\":\"The paper identifies four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.\",\"number_stated\":true}", "reading": {"parent_value": 4, "unit": "key M2 macrophage–linked genes", "evidence": "We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.", "target_result": "The paper identifies four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.", "number_stated": true, "source_locator": "chars 1157-1239 of source sha256 0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b"}, "recorded_at": "2026-10-31T15:35:05.302129+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3f344915b37aa1863a3a90298a35a9d70d9a93e351e85df5ef157995b8d080a7", "source_hash": "0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline stated for main finding / registered target. Source abstract: four key genes, survival high-risk lower across datasets p values. \"headline numerical result\" perhaps four? User asks replication of registered target has to reproduce, headline number only, value paper itself states for registered target. Registered target: headline numerical result paper states for main finding. Need infer likely number 4 key genes? Main finding identifies four key M2 macrophage-linked genes. Evidence exact contiguous quote containing number, whole clause. Unit perhaps \"genes\" or empty? They demand unit paper prints. Quote: \"We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.\" Number written \"four\", but parent_value number 4. Unit paper prints? It prints \"key M2 macrophage–linked genes\", could unit \"genes\". Headline numerical result perhaps this. But perhaps p=1.2 × 10–4 is headline numerical result for prognosis. Let's carefully parse wording.\n\nThey ask \"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 deliberately generic: \"the headline numerical result the paper states for its main finding.\" Need select from supplied text. The paper's main finding likely four key genes. Yet \"headline numerical result\" could be survival P in TCGA-LUAD = 1.2×10^-4. Which is numerical performance/result of prognostic model. Replication must reproduce headline p-value? Maybe target extraction task where registered target in hidden terms, and asks identify single numerical result. We need determine.\n\nCould be \"We identified four key M2 macrophage–linked genes\" central headline. Number \"four\" explicitly. Unit genes. Evidence quote exact. target_result describe. number_stated true. parent_value 4, unit \"genes\". Is \"four\" a numerical result? Yes.\n\nAlternatively, the abstract's concrete headline numerical result: \"Survival durations in the high-riskscore cluster were lower across the TCGA-LUAD (P = 1.2 × 10–4), GSE14814 (P = 0.02), and GSE37745 (P = 0.01) data sets.\" There are three numbers, not single. Registered target singular perhaps main finding refers risk model and headline number could p=1.2e-4 (TCGA primary dataset), but the text lists three. They ask single numerical result perhaps use \"four key genes\" because unique main count.\n\nNeed obey \"headline number only\" perhaps target_result should only number? Schema target_result string. Evidence quote exact. We can say \"Four M2 macrophage–linked genes (TIMP1, CAV2, MIF, and SELENBP1).\" But report headline number only perhaps unit/evidence enough. target_result maybe \"4 genes\". Ensure no invented. They specifically unit must be unit paper prints. \"genes\" printed. Exact quote contains word four, though numerical value converted from word to digit? \"value paper itself states\", parent_value must number JSON. That's okay, four is numerical value stated lexically. They said no value calculated/converted. Translating four to 4 may technically conversion? JSON requires number, so unavoidable. Likely accepted.\n\nCould unit be \"M2 macrophage–linked genes\" exact printed unit. Usually unit field expected e.g. \"genes\". Use \"genes\". Evidence exact full clause: \"We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.\" Contiguous exact punctuation? In source yes. Target result maybe \"The study identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.\" This is paraphrase outside evidence, permitted? User asks target_result what text states if no number. For number stated perhaps target_result likely label. \"headline number only\" might mean target_result should simply say \"4 genes\". Need JSON valid.\n\nLet's assess whether unit empty could be required because \"four\" is count and unit \"genes\" explicit. no.\n\nCould \"four key genes\" be main finding, yes. Conclusion reiterates model constructed on basis of TIMP1, CAV2, MIF, SELENBP1 but without number. Abstract starts \"We identified four key...\" It's headline. The p-values are supporting findings. The requested \"single numerical result\" likely points exactly to count four.\n\nNeed not mention source DOI. Return JSON object only. Evidence exact contiguous. number_stated true. target_result maybe \"4 genes\". They said report headline number only; perhaps target_result should be \"4 genes\". Parent value 4, unit genes. Let's produce.</think>\n\n{\"parent_value\":4,\"unit\":\"genes\",\"evidence\":\"We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.\",\"target_result\":\"4 genes\",\"number_stated\":true}", "reading": {"parent_value": 4, "unit": "genes", "evidence": "We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1.", "target_result": "4 genes", "number_stated": true, "source_locator": "chars 1157-1239 of source sha256 0e3a82341619e85d6418388acd465efebd3a004c73ec85b6cfcc467cafd5900b"}, "recorded_at": "2026-10-31T15:35:11.469441+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The prognostic model identified four M2 macrophage–linked genes (TIMP1, CAV2, MIF, and SELENBP1); survival durations were lower in the high-risk-score group in TCGA-LUAD (P = 1.2 × 10–4), GSE14814 (P = 0.02), and GSE37745 (P = 0.01).", "minimax_alt": "We identified four key M2 macrophage–linked genes: TIMP1, CAV2, MIF, and SELENBP1. Survival durations in the high-riscore cluster were lower across the TCGA-LUAD (P = 1.2 × 10–4), GSE14814 (P = 0.02), and GSE37745 (P = 0.01) data sets.", "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis", "Single-cell RNA sequencing quality control", "Batch-effect removal", "Cell annotation", "Cross-analysis of M2 macrophage-associated differentially expressed genes", "Machine learning for risk-model construction", "Risk-score computation", "Median-based high- and low-risk grouping", "Immune infiltration assessment using the Estimate and MCPcounter R packages", "Gene set enrichment analysis (GSEA; version 4.1.0)", "Drug-sensitivity prediction using the oncoPredict R package and GDSC"], "minimax_alt": ["Differentially expressed gene analysis", "Single-cell RNA-seq quality control, batch-effect removal, and annotation", "Cross-analysis of M2 macrophage–linked genes", "Machine-learning construction of a gene-based risk model", "Bulk RNA-seq evaluation of the risk model", "Risk-score stratification into low- and high-risk groups", "Survival comparison between risk groups (statistical test not specified in the supplied text)", "Immune infiltration analysis using the “Estimate” and “MCPcounter” R packages", "Gene set enrichment analysis (GSEA; version 4.1.0)", "Drug-sensitivity analysis using the “oncoPredict” R package and GDSC half-maximal drug suppression concentrations"], "decisive": false}, "unit": {"minimax": "key M2 macrophage–linked genes", "minimax_alt": "genes", "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:a30ca185d677c7dd03dea3c00d465bedafd2a77fe8aab1fa8284af30b1918268", "type": "sep_package", "label": "SEP v1 package for pmid:40100580"}], "activities": [{"id": "activity:conversion:pmid:40100580", "type": "conversion", "used": ["package:a30ca185d677c7dd03dea3c00d465bedafd2a77fe8aab1fa8284af30b1918268"], "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:40100580", "parent_hash": "sha256:05e959bb4ae42e04153dcbe97dd103e052809504d28c1b630cda33c6c11df1a6", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40100580 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:40100580' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:00:06+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}}}