{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29216278", "kind": "science-record", "revision": 8, "content_hash": "sha256:e9cf7b604ef7e4c29f8654fb2db342b5853e651425c9cf54ef6d62164923eb11", "created_at": "2026-11-01T15:40:30Z", "updated_at": "2026-11-01T21:59:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Systematic integrative analysis of gene expression identifies HNF4A as the central gene in pathogenesis of non-alcoholic steatohepatitis.", "doi": "10.1371/journal.pone.0189223", "pmid": "29216278", "authors": ["Cristina Baciu", "Elisa Pasini", "Marc Angeli", "Katherine Schwenger", "Jenifar Afrin", "Atul Humar", "Sandra Fischer", "Keyur Patel", "Johane Allard", "Mamatha Bhat"], "journal": "PloS one", "year": 2017, "abstract": "Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease in the Western world, and encompasses a spectrum from simple steatosis to steatohepatitis (NASH). There is currently no approved pharmacologic therapy against NASH, partly due to an incomplete understanding of its molecular basis. The goal of this study was to determine the key differentially expressed genes (DEGs), as well as those genes and pathways central to its pathogenesis. We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632). The DEGs were identified using GEOquery, and only the genes present in at least three of the studies, to a total of 190 DEGs, were considered for further analyses. The pathways, networks, molecular interactions, functional analyses were generated through the use of Ingenuity Pathway Analysis (IPA). For selected networks, we computed the centrality using igraph package in R. Among the statistically significant predicted networks (p-val < 0.05), three were of most biological interest: the first is involved in antimicrobial response, inflammatory response and immunological disease, the second in cancer, organismal injury and development and the third in metabolic diseases. We discovered that HNF4A is the central gene in the network of NASH connected to metabolic diseases and that it regulates HNF1A, an additional transcription regulator also involved in lipid metabolism. Therefore, we show, for the first time to our knowledge, that HNF4A is central to the pathogenesis of NASH. This adds to previous literature demonstrating that HNF4A regulates the transcription of genes involved in the progression of NAFLD, and that HNF4A genetic variants play a potential role in NASH progression.", "claims": [{"id": "claim-method", "statement": "The p-value was determined by a right-tailed Fisher’s exact test[52] that takes into account the number of so-called focus molecules (input genes) in the network and the total number of molecules in the Ingenuity Knowledge Base that could be included in networks.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29216278", "locator": "sections[11] \"Pathway and network analysis\" paragraph 2", "quote": "The p-value was determined by a right-tailed Fisher’s exact test[52] that takes into account the number of so-called focus molecules (input genes) in the network and the total number of molecules in the Ingenuity Knowledge Base that could be included in networks."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29216278", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used GEOquery-based differential-expression analysis on publicly available NASH gene-expression data from GEO to identify DEGs for downstream statistical pathway and network analyses; its headline finding was that HNF4A is central to NASH pathogenesis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29216278", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632)."}, {"asset": "source:pmid:29216278", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The DEGs were identified using GEOquery, and only the genes present in at least three of the studies, to a total of 190 DEGs, were considered for further analyses."}, {"asset": "source:pmid:29216278", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Therefore, we show, for the first time to our knowledge, that HNF4A is central to the pathogenesis of NASH."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used GEOquery-based differential-expression analysis on publicly available NASH gene-expression data from GEO to identify DEGs for downstream statistical pathway and network analyses; its headline finding was that HNF4A is central to NASH pathogenesis.", "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:29216278"], "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:GSE17470"], "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:GSE17470"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29216278", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0189223", "sha256": "sha256:71bb5cdd521ef08a409cd6b76ab05addbe882b42d828aef61f7cdc2973340eb2", "bytes": 26231, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0189223", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5720788", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17470", "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=GSE17470", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17470", "version": null, "note": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM435821", "GSM435822", "GSM435823", "GSM435824", "GSM435825", "GSM435826", "GSM435827", "GSM435828", "GSM435833", "GSM435834", "GSM435835"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Global gene expression of NASH patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE24807", "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=GSE24807", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24807", "version": null, "note": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM435821", "GSM435822", "GSM435823", "GSM435824", "GSM435825", "GSM435826", "GSM435827", "GSM435828", "GSM435833", "GSM610690", "GSM610691", "GSM610695", "GSM610696", "GSM610717", "GSM610718", "GSM610737", "GSM610738"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Increased hemoglobin expression in NASH livers", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE37031", "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=GSE37031", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37031", "version": null, "note": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM909136", "GSM909137", "GSM909138", "GSM909139", "GSM909140", "GSM909141", "GSM909142", "GSM909143", "GSM909144", "GSM909145", "GSM909146", "GSM909147", "GSM909148", "GSM909149", "GSM909150"], "sample_count": 15, "group_sizes": null, "group_sizes_basis": null, "platform": "14877", "taxon": "Homo sapiens", "title": "Transcriptome Analysis from non-alcoholic steatohepatitis (NASH)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE89632", "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=GSE89632", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE89632", "version": null, "note": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2385720", "GSM2385721", "GSM2385722", "GSM2385723", "GSM2385724", "GSM2385725", "GSM2385726", "GSM2385727", "GSM2385728", "GSM2385729", "GSM2385730", "GSM2385731", "GSM2385732", "GSM2385733", "GSM2385734", "GSM2385735", "GSM2385736", "GSM2385737", "GSM2385738", "GSM2385739", "GSM2385740", "GSM2385741", "GSM2385742", "GSM2385743", "GSM2385744", "GSM2385745", "GSM2385746", "GSM2385747", "GSM2385748", "GSM2385749", "GSM2385750", "GSM2385751", "GSM2385752", "GSM2385753", "GSM2385754", "GSM2385755", "GSM2385756", "GSM2385757", "GSM2385758", "GSM2385759", "GSM2385760", "GSM2385761", "GSM2385762", "GSM2385763", "GSM2385764", "GSM2385765", "GSM2385766", "GSM2385767", "GSM2385768", "GSM2385769", "GSM2385770", "GSM2385771", "GSM2385772", "GSM2385773", "GSM2385774", "GSM2385775", "GSM2385776", "GSM2385777", "GSM2385778", "GSM2385779", "GSM2385780", "GSM2385781", "GSM2385782"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Genome-wide analysis of hepatic gene expression in patients with non-alcoholic fatty liver disease  and in healthy donors in relation to hepatic fatty acid composition and other nutritional factors", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29216278:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b877ecd05347d396d3c05235216fefb115584c1421c777f8760495ec3bc6c40f", "bytes": 388, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#pone.0189223.t001", "version": null, "note": "Significant pathways predicted to be activated or inhibited by z-score.A positive z-score predicts activation, a negative z-score predicts inhibition. Genes listed in Bold and Italic show up- and down-regulation, respectively.", "structure": {"pmcid": "PMC5720788", "section_index": 3, "section_title": "Canonical pathways", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Significant pathways predicted to be activated or inhibited by z-score.A positive z-score predicts activation, a negative z-score predicts inhibition. Genes listed in Bold and Italic show up- and down-regulation, respectively.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[3]/table-wrap[1]#pone.0189223.t001"}}, {"id": "asset:table:pmid:29216278:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b25b08789464d402948d6abfec78ad1a76912631ea8202f8fab9c6206db1840f", "bytes": 208, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#pone.0189223.t002", "version": null, "note": "Upstream regulators predicted to be activated.", "structure": {"pmcid": "PMC5720788", "section_index": 4, "section_title": "Upstream regulator analysis", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Upstream regulators predicted to be activated.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[4]/table-wrap[1]#pone.0189223.t002"}}, {"id": "asset:table:pmid:29216278:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b2cf8f95c4aaafb43f6e8bbf1b2acc64a16ad439395f08c7cdf5a654346b6351", "bytes": 189, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#pone.0189223.t003", "version": null, "note": "Top diseases and functions.", "structure": {"pmcid": "PMC5720788", "section_index": 5, "section_title": "Diseases and functions", "row_count": 0, "column_count": 0}, "table": {"label": "Table 3", "caption": "Top diseases and functions.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[5]/table-wrap[1]#pone.0189223.t003"}}], "gaps": ["asset:data:geo:GSE17470 not downloaded", "asset:data:geo:GSE17470 licence not read", "asset:data:geo:GSE24807 not downloaded", "asset:data:geo:GSE24807 licence not read", "asset:data:geo:GSE37031 not downloaded", "asset:data:geo:GSE37031 licence not read", "asset:data:geo:GSE89632 not downloaded", "asset:data:geo:GSE89632 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "centrality", "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": "centrality"}}, {"id": "method-2", "family": null, "specific": null, "label": "right-tailed Fisher’s exact test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The p-value was determined by a right-tailed Fisher’s exact test[52] that takes into account the number of so-called focus molecules (input genes) in the network and the total number of molecules in the Ingenuity Knowledge Base that could be included in networks."}}], "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: centrality."}, "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": ["GSE17470", "GSE24807", "GSE37031", "GSE89632"], "resolved_accessions": ["GSE17470", "GSE24807", "GSE37031", "GSE89632"], "statements": ["We performed an integrative computational analysis of publicly available gene expression data in NASH from GEO (GSE17470, GSE24807, GSE37031, GSE89632)."], "basis": "The paper names GSE17470, GSE24807, GSE37031, GSE89632 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:29216278", "data:geo:GSE17470", "asset:table:pmid:29216278:1", "asset:table:pmid:29216278:2", "asset:table:pmid:29216278:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17470"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:53Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 49783, "completion_tokens": 2885, "cached_tokens": 1824}}, "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:29216278", "type": "paper", "label": "pmid:29216278"}, {"id": "source:pmid:29216278", "type": "manuscript", "label": "PMID 29216278 full text"}, {"id": "data:geo:GSE17470", "type": "dataset", "label": "GEO GSE17470"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29216278", "type": "paper", "label": "pmid:29216278"}, {"id": "source:pmid:29216278", "type": "manuscript", "label": "PMID 29216278 full text"}, {"id": "data:geo:GSE17470", "type": "dataset", "label": "GEO GSE17470"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29216278", "type": "extraction", "used": ["source:pmid:29216278"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17470", "type": "accession_resolution", "used": ["data:geo:GSE17470"], "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:29216278", "parent_hash": "sha256:e881bafeab7bbf34d882bb2dc8ba0e7e25884c37dc2d9338bab6a525049ff9ac", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE17470 licence not read", "asset:data:geo:GSE17470 not downloaded", "asset:data:geo:GSE24807 licence not read", "asset:data:geo:GSE24807 not downloaded", "asset:data:geo:GSE37031 licence not read", "asset:data:geo:GSE37031 not downloaded", "asset:data:geo:GSE89632 licence not read", "asset:data:geo:GSE89632 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["Twelve NASH patients were included for HNF4A IHC validation using anti HNF4-Alpha, mouse mono"], "order_basis": "paper_text_order:2108", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["HNF4A IHC validation using anti HNF4-Alpha, mouse monoclonal antibody (Abcam, ab201460, rabbit"], "order_basis": "paper_text_order:2147", "id": "assay:2"}, {"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": ["centrality"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T00:38:32+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}}}