{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34118488", "kind": "science-record", "revision": 8, "content_hash": "sha256:c3afe2bf9f57a87cbf98f12560798f2f63c359ad02c80fb084570b29d8322a0c", "created_at": "2026-11-01T15:41:38Z", "updated_at": "2026-11-01T22:03:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Fatty Acids Activate the Transcriptional Coactivator YAP1 to Promote Liver Fibrosis via p38 Mitogen-Activated Protein Kinase.", "doi": "10.1016/j.jcmgh.2021.06.003", "pmid": "34118488", "authors": ["Shadi Salloum", "Andre J Jeyarajan", "Annie J Kruger", "Jacinta A Holmes", "Tuo Shao", "Mozhdeh Sojoodi", "Myung-Ho Kim", "Zhu Zhuo", "Stuti G Shroff", "Andrew Kassa", "Kathleen E Corey", "Sanjoy K Khan", "Wenyu Lin", "Nadia Alatrakchi", "Esperance A K Schaefer", "Raymond T Chung"], "journal": "Cellular and molecular gastroenterology and hepatology", "year": 2021, "abstract": "BACKGROUND & AIMS: Patients with simple steatosis (SS) and nonalcoholic steatohepatitis can develop progressive liver fibrosis, which is associated with liver-related mortality. The mechanisms contributing to liver fibrosis development in SS, however, are poorly understood. SS is characterized by hepatocellular free fatty acid (FFA) accumulation without lobular inflammation seen in nonalcoholic steatohepatitis. Because the Hippo signaling transcriptional coactivator YAP1 (YAP) has previously been linked with nonalcoholic fatty liver disease (NAFLD)-related fibrosis, we sought to explore how hepatocyte FFAs activate a YAP-mediated profibrogenic program.\nMETHODS: We analyzed RNA sequencing data from a GEO DataSet (accession: GSE162694) consisting of 143 patients with NAFLD. We also performed immunohistochemical, immunofluorescence, immunoblot, and quantitative reverse-transcription polymerase chain reaction analyses (qRT-PCR) in liver specimens from NAFLD subjects, from a murine dietary NAFLD model, and in FFA-treated hepatic spheroids and hepatocytes.\nRESULTS: YAP-target gene expression correlated with increasing fibrosis stage in NAFLD patients and was associated with fibrosis in mice fed a NAFLD-inducing diet. Hepatocyte-specific YAP deletion in the murine NAFLD model attenuated diet-induced fibrosis, suggesting a causative role of YAP in NAFLD-related fibrosis. Likewise, in hepatic spheroids composed of Huh7 hepatoma cells and primary human hepatic stellate cells, Huh7 YAP silencing reduced FFA-induced fibrogenic gene expression. Notably, inhibition of p38 mitogen-activated protein kinase could block YAP activation in FFA-treated Huh7 cells.\nCONCLUSIONS: These studies provide further evidence for the pathological role of YAP in NAFLD-associated fibrosis and that YAP activation in NAFLD may be driven by FFA-induced p38 MAPK activation.", "claims": [{"id": "claim-method", "statement": "Human data were compared using Fisher’s exact test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34118488", "locator": "sections[20] \"Statistical Analysis\" paragraph 3", "quote": "Human data were compared using Fisher’s exact test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We utilized GEO data (accession: GSE162694) (G. Agyapongm, MD et al, 2020, unpublished data), which includes RNAseq data for 143 NAFLD patients with various stages of fibrosis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34118488", "locator": "sections[14] \"Human Samples and Histopathological Analysis\" paragraph 2", "quote": "We utilized GEO data (accession: GSE162694) (G. Agyapongm, MD et al, 2020, unpublished data), which includes RNAseq data for 143 NAFLD patients with various stages of fibrosis."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:34118488"], "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:GSE162694"], "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:GSE162694"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34118488", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.jcmgh.2021.06.003", "sha256": "sha256:60d9fe09cfe3bd9d2d916d7def80da9d4c036f1b6c2871f55b4c33720df32cba", "bytes": 48821, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.jcmgh.2021.06.003", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8463869", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE162694", "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=GSE162694", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE162694", "version": null, "note": "We utilized GEO data (accession: GSE162694) (G. Agyapongm, MD et al, 2020, unpublished data), which includes RNAseq data for 143 NAFLD patients with various stages of fibrosis.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We utilized GEO data (accession: GSE162694) (G. Agyapongm, MD et al, 2020, unpublished data), which includes RNAseq data for 143 NAFLD patients with various stages of fibrosis.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM4957321", "GSM4957322", "GSM4957323", "GSM4957324", "GSM4957325", "GSM4957326", "GSM4957327", "GSM4957328", "GSM4957329", "GSM4957330", "GSM4957331", "GSM4957332", "GSM4957333", "GSM4957334", "GSM4957335", "GSM4957336", "GSM4957337", "GSM4957338", "GSM4957339", "GSM4957340", "GSM4957341", "GSM4957342", "GSM4957343", "GSM4957344", "GSM4957345", "GSM4957346", "GSM4957347", "GSM4957348", "GSM4957349", "GSM4957350", "GSM4957351", "GSM4957352", "GSM4957353", "GSM4957354", "GSM4957355", "GSM4957356", "GSM4957357", "GSM4957358", "GSM4957359", "GSM4957360", "GSM4957361", "GSM4957362", "GSM4957363", "GSM4957364", "GSM4957365", "GSM4957366", "GSM4957367", "GSM4957368", "GSM4957369", "GSM4957370", "GSM4957371", "GSM4957372", "GSM4957373", "GSM4957374", "GSM4957375", "GSM4957376", "GSM4957377", "GSM4957378", "GSM4957379", "GSM4957380", "GSM4957381", "GSM4957382", "GSM4957383", "GSM4957384", "GSM4957385", "GSM4957386", "GSM4957387", "GSM4957388", "GSM4957389", "GSM4957390", "GSM4957391", "GSM4957392", "GSM4957393", "GSM4957394", "GSM4957395", "GSM4957396", "GSM4957397", "GSM4957398", "GSM4957399", "GSM4957400", "GSM4957401", "GSM4957402", "GSM4957403", "GSM4957404", "GSM4957405", "GSM4957406", "GSM4957407", "GSM4957408", "GSM4957409", "GSM4957410", "GSM4957411", "GSM4957412", "GSM4957413", "GSM4957414", "GSM4957415", "GSM4957416", "GSM4957417", "GSM4957418", "GSM4957419", "GSM4957420", "GSM4957421", "GSM4957422", "GSM4957423", "GSM4957424", "GSM4957425", "GSM4957426", "GSM4957427", "GSM4957428", "GSM4957429", "GSM4957430", "GSM4957431", "GSM4957432", "GSM4957433", "GSM4957434", "GSM4957435", "GSM4957436", "GSM4957437", "GSM4957438", "GSM4957439", "GSM4957440", "GSM4957441", "GSM4957442", "GSM4957443", "GSM4957444", "GSM4957445", "GSM4957446", "GSM4957447", "GSM4957448", "GSM4957449", "GSM4957450", "GSM4957451", "GSM4957452", "GSM4957453", "GSM4957454", "GSM4957455", "GSM4957456", "GSM4957457", "GSM4957458", "GSM4957459", "GSM4957460", "GSM4957461", "GSM4957462", "GSM4957463"], "sample_count": 143, "group_sizes": null, "group_sizes_basis": null, "platform": "21290", "taxon": "Homo sapiens", "title": "Molecular Characterization and Cell Type Composition Deconvolution of Fibrosis in NAFLD", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34118488:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7a3930c595ce9f55621f67bd8c1304d9537406fa26e2d5633a12f004268cfb99", "bytes": 640, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#tbl1", "version": null, "note": "Demographic and Patient Characteristics", "structure": {"pmcid": "PMC8463869", "section_index": 7, "section_title": "YAP Is Activated in the Livers of Humans With NAFLD-Related Fibrosis", "row_count": 6, "column_count": 6}, "table": {"label": "Table 1", "caption": "Demographic and Patient Characteristics", "rows": [["", "All Patients (N = 182)", "Normal Histology (n = 41)", "Steatosis (n = 45)", "F1–2 (n = 81)", "F3–4 (n = 33)"], ["Male", "35", "22.5", "33.3", "36.2", "53.7"], ["BMI, kg/m2", "41.4 ± 10.3", "41.4 ± 4.4", "46.6 ± 10.2", "38.8 ± 11", "36.1 ± 11.7"], ["Diabetes", "33.5", "15", "24.4", "37.7", "85.7"], ["ALT, U/L", "36.6 ±19.2", "22.9 ± 12.1", "29.9 ± 9.6", "41.8 ± 21", "53.3 ± 18"], ["AST, U/L", "30 ± 15.8", "19.1 ± 5", "22.7 ± 4.8", "33.1 ± 16", "48.8 ± 19.5"]], "row_count": 6, "column_count": 6, "numeric_cells": 30, "header_rows": 1, "locator": "section[7]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE162694 not downloaded", "asset:data:geo:GSE162694 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "image_quantification", "specific": "densitometry", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "Densitometr"}}, {"id": "method-2", "family": null, "specific": null, "label": "Fisher’s exact test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Human data were compared using Fisher’s exact test."}}], "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": ["segment_objects", "quantify_intensity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: densitometry."}, "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": ["GSE162694"], "resolved_accessions": ["GSE162694"], "statements": ["We utilized GEO data (accession: GSE162694) (G. Agyapongm, MD et al, 2020, unpublished data), which includes RNAseq data for 143 NAFLD patients with various stages of fibrosis."], "basis": "The paper names GSE162694 in GEO DataSet and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["segment_objects", "quantify_intensity"], "assets": ["source:pmid:34118488", "data:geo:GSE162694", "asset:table:pmid:34118488:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE162694"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:42Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 39373, "completion_tokens": 1041, "cached_tokens": 13320}}, "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:34118488", "type": "paper", "label": "pmid:34118488"}, {"id": "source:pmid:34118488", "type": "manuscript", "label": "PMID 34118488 full text"}, {"id": "data:geo:GSE162694", "type": "dataset", "label": "GEO GSE162694"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34118488", "type": "paper", "label": "pmid:34118488"}, {"id": "source:pmid:34118488", "type": "manuscript", "label": "PMID 34118488 full text"}, {"id": "data:geo:GSE162694", "type": "dataset", "label": "GEO GSE162694"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34118488", "type": "extraction", "used": ["source:pmid:34118488"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE162694", "type": "accession_resolution", "used": ["data:geo:GSE162694"], "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:34118488", "parent_hash": "sha256:2956d8b2e1e050123bd95479040b8049fb247d2bab411fbf3cc69e035f167e2e", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE162694 licence not read", "asset:data:geo:GSE162694 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["profibrogenic program. METHODS: We analyzed RNA sequencing data from a GEO DataSet (accession: GSE16269", "al, 2020, unpublished data), which includes RNAseq data for 143 NAFLD patients with various sta"], "order_basis": "paper_text_order:764", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["f 143 patients with NAFLD. We also performed immunohistochemical, immunofluorescence, immunoblot, and quantit", "AFLD. We also performed immunohistochemical, immunofluorescence, immunoblot, and quantitative reverse-transc"], "order_basis": "paper_text_order:882", "id": "assay:2"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["med immunohistochemical, immunofluorescence, immunoblot, and quantitative reverse-transcription poly", "-transcription polymerase chain reaction and immunoblot studies at the specified time points, and da", "e, San Diego, CA). Densitometric analyses of immunoblot images were performed using Image Studio Lit"], "order_basis": "paper_text_order:923", "id": "assay:3"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["liver specimens from NAFLD subjects, from a murine dietary NAFLD model, and in FFA-treated hepa", "iet. Hepatocyte-specific YAP deletion in the murine NAFLD model attenuated diet-induced fibrosis", "LD patients and was associated with fibrosis in mice fed a NAFLD-inducing diet. Hepatocyte-specif", "20). Animal Studies Alb-Cre and Yapflox/flox mice were purchased from the Jackson Laboratory (Bar H"], "order_basis": "paper_text_order:1067", "id": "assay:4"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["lected as previously described.28 Cells were cultured in Dulbecco's modified Eagle's medium supplemen", "mittee of MGH. Cell Culture We used Huh7 and HepG2 human hepatoma cells, Human Embryonic Kidney"], "order_basis": "paper_text_order:3885", "id": "assay:5"}, {"role": "analysis", "definition_id": "image_quantification", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["segment_objects", "quantify_intensity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Densitometr"], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T03:15:58+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}