{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39854742", "kind": "science-record", "revision": 2, "content_hash": "sha256:f3468b284df2aa5e3dd92edc06094064a33ba571290d8c2aafe97f7cfbaf9a27", "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": "Exploring markers in nursing care of prostate cancer.", "doi": "10.1097/md.0000000000041357", "pmid": "39854742", "authors": null, "journal": "Medicine", "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": 1151.0, "unit": "degs", "tolerance": null, "source": "chars 562-849 of source sha256 862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b"}, "evidence": [{"asset": "source:pmid:39854742", "locator": "chars 562-849 of source sha256 862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b", "quote": "A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis."}]}], "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:39854742"], "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:39854742", "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:39854742' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39854742", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/md.0000000000041357", "sha256": "sha256:862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/md.0000000000041357", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39854742:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6b765d481e26a785348fe08b5168a3b538915ea9816700461cd36438996f4fb2", "bytes": 677, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[23]/table-wrap[1]#T1", "version": null, "note": "A summary of miRNAs that regulate hub genes.", "structure": {"pmcid": "PMC11771610", "section_index": 23, "section_title": "3.7. miRNA prediction and functional annotation related to hub gene", "row_count": 11, "column_count": 5}, "table": {"label": "Table 1", "caption": "A summary of miRNAs that regulate hub genes.", "rows": [["", "Gene", "miRNA", ""], ["1", "MYL9", "hsa-miR-134-5p", "hsa-miR-3118", "hsa-miR-760"], ["2", "TAGLN", "hsa-miR-22-3p", "", ""], ["3", "SMTN", "hsa-miR-338-3p", "", ""], ["4", "CNN1", "hsa-miR-15a-5p", "hsa-miR-15b-5p", "hsa-miR-497-5p"], ["5", "MYH11", "hsa-miR-124-3p.1", "", ""], ["6", "MYLK", "hsa-miR-129-5p", "", ""], ["7", "MYOCD", "hsa-miR-449a", "hsa-miR-34a-5p", "hsa-miR-34c-5p"], ["8", "ACTC1", "hsa-miR-7-5p", "", ""], ["9", "LMOD1", "hsa-miR-133a-3p.1", "", ""], ["10", "TPM2", "hsa-miR-193a-3p", "hsa-miR-193b-3p", ""]], "row_count": 11, "column_count": 5, "numeric_cells": 28, "header_rows": 1, "locator": "section[23]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:39854742 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:39854742", "asset:table:pmid:39854742:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39854742"]}, "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": "d0a38ce9520b82cfeb5a1960a3cb54a3c5789cc015e896b8a34fcca97c653dd3", "source_hash": "862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b", "raw_response_sha256": "sha256:f425de26cf2e4aed7efa6b767eb4634c1e49fdc09266455d33fc90c5dba5a884", "raw_response_chars": 4619}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "66faf65c8a2f69066954ba23c71fb1f500e16dfd24345ec9a1863c378c07c1c4", "source_hash": "862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b", "raw_response_sha256": "sha256:b4ddb2c67febd146f3db6d8a9d77c6b2952b5ea999335b65fb95186e8481cf85", "raw_response_chars": 26013}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "852c09111438942c6bf89a0c78c5f185c08f94e0fa3c908f49492bfb1919353d", "source_hash": "862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b", "raw_response": "{\"parent_value\":1151,\"unit\":\"DEGs\",\"evidence\":\"A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis.\",\"target_result\":\"1151 DEGs\",\"number_stated\":true}", "reading": {"parent_value": 1151, "unit": "DEGs", "evidence": "A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis.", "target_result": "1151 DEGs", "number_stated": true, "source_locator": "chars 562-849 of source sha256 862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b"}, "recorded_at": "2026-10-31T15:21:27.086084+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "b6dd9ee4002cb4471a5047bacf39755f20ea02b37b0ea3995efd3aaaba6a6298", "source_hash": "862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b", "raw_response": "<think>We need answer JSON only. Need interpret question: single numerical result replication registered target headline numerical result paper states for main finding. Source has \"A total of 1151 DEGs were found\" perhaps headline numerical result? Or 10 core genes. Need identify \"main finding\" and registered target broad. User asks \"single numerical result that a replication of the registered target has to reproduce. Report headline number only: value paper itself states for registered target... registered target: headline numerical result the paper states for its main finding.\" We need infer likely target value. Source abstract: \"A total of 1151 DEGs were found...\" Main finding perhaps \"10 core genes...\"? The paper title exploring markers nursing care prostate cancer. Headline numerical result likely number of DEGs = 1151, or number core genes = 10. Need examine wording and request likely benchmark task \"parent_value\" maybe asks numerical result attached to registered target. They explicitly mention parenthetical list / respectively / direct naming. Registered target generic. Need select single numerical result. Could be \"A total of 1151 DEGs were found\" likely headline. Unit \"DEGs\". Evidence exact contiguous quotation. Target_result concise. parent_value number 1151. Unit \"DEGs\". Evidence perhaps \"A total of 1151 DEGs were found\" exact. target_result \"A total of 1151 DEGs were found.\" number_stated true.\n\nBut need be certain. Let's parse source. Abstract:\n\"We found prostate cancer GSE141551 and GSE200879 profiles ... A total of 1151 DEGs were found, most of them focusing ... The core genes (10 names) obtained in end are all lowly expressed ... LMOD1 and SMTN are lowly expressed ... may be used as markers...\"\nMain finding perhaps core genes list, with count ten. The \"headline numerical result\" perhaps \"10 genes associated with hypertension, tumor metastasis, prostate tumor, and tumor invasiveness\". However paper does not explicitly phrase \"10 main finding\"; it lists 10. Replication of registered target \"headline numerical result\" maybe asks result of study, often number participants/sample size, etc. Here likely 1151 DEGs as numerical abstract result. They request headline number only and exact quote attribution. Number attached directly via wording.\n\nCould target be 2 genes (LMOD1/SMTN) as markers? Yet paper doesn't state \"2\"; list of two names. Can't infer/calculate. It says 10 genes in CTD analysis. Numerical result explicitly stated. \"single numerical result\" likely asks identify among all numbers. Need decide.\n\nMaybe benchmark is designed to ask \"find single numerical result that a replication of the registered target has to reproduce\" where REGISTERED TARGET could correspond to entity? The target says \"the headline numerical result the paper states for its main finding\", broad. Need choose main headline. Abstract highlights 1151 DEGs first. \"A total of 1151 DEGs were found\" is strongest clear result. Unit printed? DEGs. Need exact unit paper prints. Could unit be \"DEGs\" yes. No unit as count perhaps \"DEGs\". parent_value numeric 1151.\n\nEvidence exact contiguous quote containing number. Could include full sentence: \"A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis.\" This demonstrates headline result. Requirement \"When text links them, quote whole clause\". Exact sentence good. They demand \"do not shorten it\" perhaps means quote exact evidence not truncate relevant attribution; use full sentence.\n\ntarget_result likely \"The paper states that a total of 1151 differentially expressed genes were found.\" Unit \"DEGs\". Evidence exact source. Could include \"A total...\" full sentence. JSON no markdown.\n\nNeed ensure no issue \"headline numerical result for main finding\" might instead be \"10 core genes\". Let's inspect phrasing. Title and conclusion. Abstract says \"A total of 1151 DEGs were found...\" then functional findings, then \"The core genes (list)...\" Main finding likely LMOD1 and SMTN. Headline number could be 2 marker genes, but paper doesn't state a numerical result for that, and instruction says if no number set false and describe. Hmm perhaps registered target intentionally main finding and source doesn't assign count to \"LMOD1 and SMTN\" except names. They ask single numerical result paper states. Maybe expected answer could be 1151 because explicitly numerical headline result. Why wording \"registered target: the headline numerical result the paper states for its main finding\" perhaps target is not a named metric like sample size, but asks \"headline number.\" In text 1151 is the only obvious abstract headline count. Other numbers: GSE IDs (not results), P thresholds, analysis parameters, 2 groups, 1000 samplings, 10 genes, 2 markers, versions. Thus 1151 clear.\n\nUnit must paper prints. \"DEGs\". Evidence full sentence. target_result no extra calculated.\n\nNeed output valid JSON. parent_value number 1151. unit maybe \"DEGs\" (paper prints). target_result perhaps \"A total of 1151 DEGs were found.\" Exact enough. number_stated true.\n\nLet's formulate.</think>\n\n{\"parent_value\":1151,\"unit\":\"DEGs\",\"evidence\":\"A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis.\",\"target_result\":\"A total of 1151 DEGs were found.\",\"number_stated\":true}", "reading": {"parent_value": 1151, "unit": "DEGs", "evidence": "A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis.", "target_result": "A total of 1151 DEGs were found.", "number_stated": true, "source_locator": "chars 562-849 of source sha256 862a5bc33efba073b3e17986d2c51883f2dcc4a15c3c2b016c0a50e2a1152f0b"}, "recorded_at": "2026-10-31T15:21:36.438055+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "A total of 1151 DEGs were found, most of them focusing on systematic development, cell development, cell differentiation, regulation of multicellular biological processes, anatomical morphogenesis, MAPK signaling pathway, proteoglycans in cancer, fluid shear stress, and atherosclerosis.", "minimax_alt": "A total of 1151 DEGs were found", "decisive": false}, "analysis_methods": {"minimax": ["differentially expressed genes (DEGs) analysis", "weighted gene co-expression network analysis (WGCNA)", "protein–protein interaction analysis", "gene function enrichment analysis", "comparative toxicology database analysis", "GO–KEGG analysis", "gene set enrichment analysis (GSEA)", "CTD analysis"], "minimax_alt": ["differentially expressed genes (DEGs) analysis", "weighted gene co-expression network analysis (WGCNA)", "protein–protein interaction analysis", "gene function enrichment analysis", "comparative toxicology database analysis (CTD)", "GO–KEGG analysis", "gene set enrichment analysis (GSEA)"], "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:87ada7d7a162c2b23335c392e2a9e30c2673c48ebda6a2abd8beb3b2f750d8c9", "type": "sep_package", "label": "SEP v1 package for pmid:39854742"}], "activities": [{"id": "activity:conversion:pmid:39854742", "type": "conversion", "used": ["package:87ada7d7a162c2b23335c392e2a9e30c2673c48ebda6a2abd8beb3b2f750d8c9"], "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:39854742", "parent_hash": "sha256:df63a71878266acd7b4307fb04a741231ccaf44b3ac7d669657cafb7b8aba3ef", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39854742 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:39854742' 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":"2026-11-04T00:47:37+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}