{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36836696", "kind": "science-record", "revision": 3, "content_hash": "sha256:cbe546a1c902b7ddc933c9f5bea77da50e74903ad7a5c850615611b4f4b9f1ba", "created_at": "2026-11-01T19:01:27Z", "updated_at": "2026-11-01T22:08:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Mechanism of Wuyao-Ginseng Medicine Pair in the Prevention and Treatment of Diarrhea-Type Irritable Bowel Syndrome Based on Gene Expression Omnibus Chip Data.", "doi": "10.3390/life13020339", "pmid": "36836696", "authors": ["Wenjing Sun", "Ruizi Qing", "Zhiqiang Fan", "Qin He", "Jinhong Wu", "Yang He", "Linqi Ouyang", "Zhen Chen", "Guiming Deng"], "journal": "Life (Basel, Switzerland)", "year": 2023, "abstract": "Based on a Gene Expression Omnibus (GEO) chip analysis combined with network pharmacology and molecular docking technology, in this study we explored the molecular targets and mechanism of the wuyao-ginseng medicine pair in the prevention and treatment of diarrhea-type irritable bowel syndrome (IBS-D). The Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP) was used to search for the chemical constituents and targets of wuyao and ginseng. The UniProt database was used to search for the target gene name. In the GEO database, IBS was searched to obtain GSE36701 and GSE14841 microarray data. We imported the intersection targets into the STRING database to construct a protein-protein interaction (PPI) network. Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (Go) pathway analyses were performed using the Metascape database. A total of 30 active ingredients of wuyao-ginseng, 171 drug targets, 1257 IBS differentially expressed genes, and 20 drug-disease intersection genes were obtained from the GEO data. We screened the results and obtained the core active ingredients beta-sitosterol, DMPEC, Boldine, etc.; the core targets NCOA2, EGFR, VEGFA, etc.; and the key pathways P13K-Akt, MAPK, etc. The wuyao-ginseng medicine pair may be involved in inflammation-related signaling pathways, acting on disease targets such as NCOA2, EGFR, and VEGFA as well as pathways such as P13K-Akt and MAPK, thereby playing a key role in the prevention and treatment of IBS-D.", "claims": [{"id": "claim-method", "statement": "The GSE36701 chip, with a total of 221 samples consisting of the selection of 40 cases of healthy volunteers (HV) and 53 cases of IBS-D subjects, was used to conduct a variance analysis using a |logFC| ≥ 0.5 and a p-value < 0.05 for the standard selection.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36836696", "locator": "sections[15] \"3.3. Analysis of GEO Differential Gene Data\" paragraph 2", "quote": "The GSE36701 chip, with a total of 221 samples consisting of the selection of 40 cases of healthy volunteers (HV) and 53 cases of IBS-D subjects, was used to conduct a variance analysis using a |logFC| ≥ 0.5 and a p-value < 0.05 for the standard selection."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are included within the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36836696", "locator": "sections[27] \"Data Availability Statement\" paragraph 2", "quote": "The data used to support the findings of this study are included within the article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The analysis identified 1257 IBS differentially expressed genes and 20 drug-disease intersection genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36836696", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 30 active ingredients of wuyao–ginseng, 171 drug targets, 1257 IBS differentially expressed genes, and 20 drug-disease intersection genes were obtained from the GEO data."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The analysis identified 1257 IBS differentially expressed genes and 20 drug-disease intersection genes.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:36836696"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE14841"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE14841"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36836696", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/life13020339", "sha256": "sha256:74977f2771ffa21f6ed80b7ac1205933f7303d6afd44e2fa1a79e1f529cc7771", "bytes": 37833, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/life13020339", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9961312", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE14841", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14841", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14841", "version": null, "note": "The data used to support the findings of this study are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM371301", "GSM371302", "GSM371303", "GSM371304", "GSM371305", "GSM371306", "GSM371307", "GSM371308", "GSM371309"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from healthy volunteers and IBS patients", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE36701", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36701", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36701", "version": null, "note": "The data used to support the findings of this study are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM899034", "GSM899035", "GSM899036", "GSM899037", "GSM899038", "GSM899039", "GSM899040", "GSM899041", "GSM899042", "GSM899043", "GSM899044", "GSM899045", "GSM899046", "GSM899047", "GSM899048", "GSM899049", "GSM899050", "GSM899051", "GSM899052", "GSM899053", "GSM899054", "GSM899055", "GSM899056", "GSM899057", "GSM899058", "GSM899059", "GSM899060", "GSM899061", "GSM899062", "GSM899063", "GSM899064", "GSM899065", "GSM899066", "GSM899067", "GSM899068", "GSM899069", "GSM899070", "GSM899071", "GSM899072", "GSM899073", "GSM899074", "GSM899075", "GSM899076", "GSM899077", "GSM899078", "GSM899079", "GSM899080", "GSM899081", "GSM899082", "GSM899083", "GSM899084", "GSM899085", "GSM899086", "GSM899087", "GSM899088", "GSM899089", "GSM899090", "GSM899091", "GSM899092", "GSM899093", "GSM899094", "GSM899095", "GSM899096", "GSM899097", "GSM899098", "GSM899099", "GSM899100", "GSM899101", "GSM899102", "GSM899103", "GSM899104", "GSM899105", "GSM899106", "GSM899107", "GSM899108", "GSM899109", "GSM899110", "GSM899111", "GSM899112", "GSM899113", "GSM899114", "GSM899115", "GSM899116", "GSM899117", "GSM899118", "GSM899119", "GSM899120", "GSM899121", "GSM899122", "GSM899123", "GSM899124", "GSM899125", "GSM899126", "GSM899127", "GSM899128", "GSM899129", "GSM899130", "GSM899131", "GSM899132", "GSM899133", "GSM899134", "GSM899135", "GSM899136", "GSM899137", "GSM899138", "GSM899139", "GSM899140", "GSM899141", "GSM899142", "GSM899143", "GSM899144", "GSM899145", "GSM899146", "GSM899147", "GSM899148", "GSM899149", "GSM899150", "GSM899151", "GSM899152", "GSM899153", "GSM899154", "GSM899155", "GSM899156", "GSM899157", "GSM899158", "GSM899159", "GSM899160", "GSM899161", "GSM899162", "GSM899163", "GSM899164", "GSM899165", "GSM899166", "GSM899167", "GSM899168", "GSM899169", "GSM899170", "GSM899171", "GSM899172", "GSM899173", "GSM899174", "GSM899175", "GSM899176", "GSM899177", "GSM899178", "GSM899179", "GSM899180", "GSM899181", "GSM899182", "GSM899183", "GSM899184", "GSM899185", "GSM899186", "GSM899187", "GSM899188", "GSM899189", "GSM899190", "GSM899191", "GSM899192", "GSM899193", "GSM899194", "GSM899195", "GSM899196", "GSM899197", "GSM899198", "GSM899199", "GSM899200", "GSM899201", "GSM899202", "GSM899203", "GSM899204", "GSM899205", "GSM899206", "GSM899207", "GSM899208", "GSM899209", "GSM899210", "GSM899211", "GSM899212", "GSM899213", "GSM899214", "GSM899215", "GSM899216", "GSM899217", "GSM899218", "GSM899219", "GSM899220", "GSM899221", "GSM899222", "GSM899223", "GSM899224", "GSM899225", "GSM899226", "GSM899227", "GSM899228", "GSM899229", "GSM899230", "GSM899231", "GSM899232", "GSM899233", "GSM899234", "GSM899235", "GSM899236", "GSM899237", "GSM899238", "GSM899239", "GSM899240", "GSM899241", "GSM899242", "GSM899243", "GSM899244", "GSM899245", "GSM899246", "GSM899247", "GSM899248", "GSM899249", "GSM899250", "GSM899251", "GSM899252", "GSM899253", "GSM899254"], "sample_count": 221, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of rectal mucosa in chronic irritable bowel syndrome (IBS) compared to healthy volunteers (HV)", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE14841 not downloaded", "asset:data:geo:GSE14841 licence not read", "asset:data:geo:GSE36701 not downloaded", "asset:data:geo:GSE36701 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Variance analysis using absolute log fold change and p-value thresholds", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The GSE36701 chip, with a total of 221 samples consisting of the selection of 40 cases of healthy volunteers (HV) and 53 cases of IBS-D subjects, was used to conduct a variance analysis using a |logFC| ≥ 0.5 and a p-value < 0.05 for the standard selection."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE36701", "GSE14841"], "resolved_accessions": ["GSE36701", "GSE14841"], "statements": ["The data used to support the findings of this study are included within the article."], "basis": "The paper names GSE36701, GSE14841 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:36836696", "data:geo:GSE14841"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE14841"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:31:37Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12048, "completion_tokens": 1628, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:36836696", "type": "paper", "label": "pmid:36836696"}, {"id": "source:pmid:36836696", "type": "manuscript", "label": "PMID 36836696 full text"}, {"id": "data:geo:GSE14841", "type": "dataset", "label": "GEO GSE14841"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36836696", "type": "paper", "label": "pmid:36836696"}, {"id": "source:pmid:36836696", "type": "manuscript", "label": "PMID 36836696 full text"}, {"id": "data:geo:GSE14841", "type": "dataset", "label": "GEO GSE14841"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36836696", "type": "extraction", "used": ["source:pmid:36836696"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE14841", "type": "accession_resolution", "used": ["data:geo:GSE14841"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:36836696", "parent_hash": "sha256:7dddda165bf2a5921f806762d9124d64b2c3cf8847fb3861a55908e6e35e5c63", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE14841 licence not read", "asset:data:geo:GSE14841 not downloaded", "asset:data:geo:GSE36701 licence not read", "asset:data:geo:GSE36701 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T01:28:29+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}}}