{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36923791", "kind": "science-record", "revision": 4, "content_hash": "sha256:83a1553ee940144dfe6f10b30505a2f11ee7fc7113e968a2dcd3c8b586170829", "created_at": "2026-11-01T19:01:34Z", "updated_at": "2026-11-01T22:51:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and validation of metabolism-related hub genes in idiopathic pulmonary fibrosis.", "doi": "10.3389/fgene.2023.1058582", "pmid": "36923791", "authors": ["Youjie Zeng", "Jun Huang", "Ren Guo", "Si Cao", "Heng Yang", "Wen Ouyang"], "journal": "Frontiers in genetics", "year": 2023, "abstract": "Background: Idiopathic pulmonary fibrosis (IPF) is a fatal and irreversible interstitial lung disease. The specific mechanisms involved in the pathogenesis of IPF are not fully understood, while metabolic dysregulation has recently been demonstrated to contribute to IPF. This study aims to identify key metabolism-related genes involved in the progression of IPF, providing new insights into the pathogenesis of IPF. Methods: We downloaded four datasets (GSE32537, GSE110147, GSE150910, and GSE92592) from the Gene Expression Omnibus (GEO) database and identified differentially expressed metabolism-related genes (DEMRGs) in lung tissues of IPF by comprehensive analysis. Then, we performed GO, KEGG, and Reactome enrichment analyses of the DEMRGs. Subsequently, key DEMRGs were identified by machine-learning algorithms. Next, miRNAs regulating these key DEMRGs were predicted by integrating the GSE32538 (IPF miRNA dataset) and the miRWalk database. The Cytoscape software was used to visualize miRNA-mRNA regulatory networks. In addition, the relative levels of immune cells were assessed by the CIBERSORT algorithm, and the correlation of key DEMRGs with immune cells was calculated. Finally, the mRNA expression of the key DEMRGs was validated in two external independent datasets and an in vivo experiment. Results: A total of 101 DEMRGs (51 upregulated and 50 downregulated) were identified. Six key DEMRGs (ENPP3, ENTPD1, GPX3, PDE7B, PNMT, and POLR3H) were further identified using two machine-learning algorithms (LASSO and SVM-RFE). In the lung tissue of IPF patients, the expression levels of ENPP3, ENTPD1, and PDE7B were upregulated, and the expression levels of GPX3, PNMT, and POLR3H were downregulated. In addition, the miRNA-mRNA regulatory network of key DEMRGs was constructed. Then, the expression levels of key DEMRGs were validated in two independent external datasets (GSE53845 and GSE213001). Finally, we verified the key DEMRGs in the lung tissue of bleomycin-induced pulmonary fibrosis mice by qRT-PCR. Conclusion: Our study identified key metabolism-related genes that are differentially expressed in the lung tissue of IPF patients. Our study emphasizes the critical role of metabolic dysregulation in IPF, offers potential therapeutic targets, and provides new insights for future studies.", "claims": [{"id": "claim-method", "statement": "To identify the most critical DEMRGs, we used two machine-learning algorithms: least absolute shrinkage and selection operator (LASSO) regression and support vector machine recursive feature elimination (SVM-RFE).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36923791", "locator": "sections[7] \"2.5 Screening of IPF key DEMRGs\" paragraph 2", "quote": "To identify the most critical DEMRGs, we used two machine-learning algorithms: least absolute shrinkage and selection operator (LASSO) regression and support vector machine recursive feature elimination (SVM-RFE)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36923791", "locator": "sections[23] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Six key DEMRGs (ENPP3, ENTPD1, GPX3, PDE7B, PNMT, and POLR3H) were further identified using two machine-learning algorithms (LASSO and SVM-RFE).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36923791", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Six key DEMRGs (ENPP3, ENTPD1, GPX3, PDE7B, PNMT, and POLR3H) were further identified using two machine-learning algorithms (LASSO and SVM-RFE)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Six key DEMRGs (ENPP3, ENTPD1, GPX3, PDE7B, PNMT, and POLR3H) were further identified using two machine-learning algorithms (LASSO and SVM-RFE).", "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:36923791"], "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:GSE110147"], "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:GSE110147"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36923791", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2023.1058582", "sha256": "sha256:c2d162615b8903ccba3c3aa29d8ced4db4ee209a0e46e33881d41d0eb69b1125", "bytes": 34766, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2023.1058582", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10010493", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE110147", "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=GSE110147", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE110147", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2978752", "GSM2978753", "GSM2978754", "GSM2978755", "GSM2978756", "GSM2978757", "GSM2978758", "GSM2978759", "GSM2978760", "GSM2978761", "GSM2978762", "GSM2978763", "GSM2978764", "GSM2978765", "GSM2978766", "GSM2978767", "GSM2978768", "GSM2978769", "GSM2978770", "GSM2978771", "GSM2978772", "GSM2978773", "GSM2978774", "GSM2978775", "GSM2978776", "GSM2978777", "GSM2978778", "GSM2978779", "GSM2978780", "GSM2978781", "GSM2978782", "GSM2978783", "GSM2978784", "GSM2978785", "GSM2978786", "GSM2978787", "GSM2978788", "GSM2978789", "GSM2978790", "GSM2978791", "GSM2978792", "GSM2978793", "GSM2978794", "GSM2978795", "GSM2978796", "GSM2978797", "GSM2978798", "GSM2978799"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling of idiopathic pulmonary fibrosis and non-specific interstitial pneumonia", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE150910", "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=GSE150910", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE150910", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4560505", "GSM4560506", "GSM4560507", "GSM4560508", "GSM4560509", "GSM4560510", "GSM4560511", "GSM4560512", "GSM4560513", "GSM4560514", "GSM4560515", "GSM4560516", "GSM4560517", "GSM4560518", "GSM4560519", "GSM4560520", "GSM4560521", "GSM4560522", "GSM4560523", "GSM4560524", "GSM4560525", "GSM4560526", "GSM4560527", "GSM4560528", "GSM4560529", "GSM4560530", "GSM4560531", "GSM4560532", "GSM4560533", "GSM4560534", "GSM4560535", "GSM4560536", "GSM4560537", "GSM4560538", "GSM4560539", "GSM4560540", "GSM4560541", "GSM4560542", "GSM4560543", "GSM4560544", "GSM4560545", "GSM4560546", "GSM4560547", "GSM4560548", "GSM4560549", "GSM4560550", "GSM4560551", "GSM4560552", "GSM4560553", "GSM4560554", "GSM4560555", "GSM4560556", "GSM4560557", "GSM4560558", "GSM4560559", "GSM4560560", "GSM4560561", "GSM4560562", "GSM4560563", "GSM4560564", "GSM4560565", "GSM4560566", "GSM4560567", "GSM4560568", "GSM4560569", "GSM4560570", "GSM4560571", "GSM4560572", "GSM4560573", "GSM4560574", "GSM4560575", "GSM4560576", "GSM4560577", "GSM4560578", "GSM4560579", "GSM4560580", "GSM4560581", "GSM4560582", "GSM4560583", "GSM4560584", "GSM4560585", "GSM4560586", "GSM4560587", "GSM4560588", "GSM4560589", "GSM4560590", "GSM4560591", "GSM4560592", "GSM4560593", "GSM4560594", "GSM4560595", "GSM4560596", "GSM4560597", "GSM4560598", "GSM4560599", "GSM4560600", "GSM4560601", "GSM4560602", "GSM4560603", "GSM4560604", "GSM4560605", "GSM4560606", "GSM4560607", "GSM4560608", "GSM4560609", "GSM4560610", "GSM4560611", "GSM4560612", "GSM4560613", "GSM4560614", "GSM4560615", "GSM4560616", "GSM4560617", "GSM4560618", "GSM4560619", "GSM4560620", "GSM4560621", "GSM4560622", "GSM4560623", "GSM4560624", "GSM4560625", "GSM4560626", "GSM4560627", "GSM4560628", "GSM4560629", "GSM4560630", "GSM4560631", "GSM4560632", "GSM4560633", "GSM4560634", "GSM4560635", "GSM4560636", "GSM4560637", "GSM4560638", "GSM4560639", "GSM4560640", "GSM4560641", "GSM4560642", "GSM4560643", "GSM4560644", "GSM4560645", "GSM4560646", "GSM4560647", "GSM4560648", "GSM4560649", "GSM4560650", "GSM4560651", "GSM4560652", "GSM4560653", "GSM4560654", "GSM4560655", "GSM4560656", "GSM4560657", "GSM4560658", "GSM4560659", "GSM4560660", "GSM4560661", "GSM4560662", "GSM4560663", "GSM4560664", "GSM4560665", "GSM4560666", "GSM4560667", "GSM4560668", "GSM4560669", "GSM4560670", "GSM4560671", "GSM4560672", "GSM4560673", "GSM4560674", "GSM4560675", "GSM4560676", "GSM4560677", "GSM4560678", "GSM4560679", "GSM4560680", "GSM4560681", "GSM4560682", "GSM4560683", "GSM4560684", "GSM4560685", "GSM4560686", "GSM4560687", "GSM4560688", "GSM4560689", "GSM4560690", "GSM4560691", "GSM4560692", "GSM4560693", "GSM4560694", "GSM4560695", "GSM4560696", "GSM4560697", "GSM4560698", "GSM4560699", "GSM4560700", "GSM4560701", "GSM4560702", "GSM4560703", "GSM4560704", "GSM4560705", "GSM4560706", "GSM4560707", "GSM4560708", "GSM4560709", "GSM4560710", "GSM4560711", "GSM4560712", "GSM4560713", "GSM4560714", "GSM4560715", "GSM4560716", "GSM4560717", "GSM4560718", "GSM4560719", "GSM4560720", "GSM4560721", "GSM4560722", "GSM4560723", "GSM4560724", "GSM4560725", "GSM4560726", "GSM4560727", "GSM4560728", "GSM4560729", "GSM4560730", "GSM4560731", "GSM4560732", "GSM4560733", "GSM4560734", "GSM4560735", "GSM4560736", "GSM4560737", "GSM4560738", "GSM4560739", "GSM4560740", "GSM4560741", "GSM4560742", "GSM4560743", "GSM4560744", "GSM4560745", "GSM4560746", "GSM4560747", "GSM4560748", "GSM4560749", "GSM4560750", "GSM4560751", "GSM4560752", "GSM4560753", "GSM4560754", "GSM4560755", "GSM4560756", "GSM4560757", "GSM4560758", "GSM4560759", "GSM4560760", "GSM4560761", "GSM4560762", "GSM4560763", "GSM4560764", "GSM4560765", "GSM4560766", "GSM4560767", "GSM4560768", "GSM4560769", "GSM4560770", "GSM4560771", "GSM4560772", "GSM4560773", "GSM4560774", "GSM4560775", "GSM4560776", "GSM4560777", "GSM4560778", "GSM4560779", "GSM4560780", "GSM4560781", "GSM4560782", "GSM4560783", "GSM4560784", "GSM4560785", "GSM4560786", "GSM4560787", "GSM4560788", "GSM4560789", "GSM4560790", "GSM4560791", "GSM4560792"], "sample_count": 288, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "RNA-Sequencing of Chronic hypersensitivity pneumonitis compared with Idiopathic Pulmonary Fibrosis and Control Lung", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE213001", "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=GSE213001", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE213001", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6568317", "GSM6568318", "GSM6568319", "GSM6568320", "GSM6568321", "GSM6568322", "GSM6568323", "GSM6568324", "GSM6568325", "GSM6568326", "GSM6568327", "GSM6568328", "GSM6568329", "GSM6568330", "GSM6568331", "GSM6568332", "GSM6568333", "GSM6568334", "GSM6568335", "GSM6568336", "GSM6568337", "GSM6568338", "GSM6568339", "GSM6568340", "GSM6568341", "GSM6568342", "GSM6568343", "GSM6568344", "GSM6568345", "GSM6568346", "GSM6568347", "GSM6568348", "GSM6568349", "GSM6568350", "GSM6568351", "GSM6568352", "GSM6568353", "GSM6568354", "GSM6568355", "GSM6568356", "GSM6568357", "GSM6568358", "GSM6568359", "GSM6568360", "GSM6568361", "GSM6568362", "GSM6568363", "GSM6568364", "GSM6568365", "GSM6568366", "GSM6568367", "GSM6568368", "GSM6568369", "GSM6568370", "GSM6568371", "GSM6568372", "GSM6568373", "GSM6568374", "GSM6568375", "GSM6568376", "GSM6568377", "GSM6568378", "GSM6568379", "GSM6568380", "GSM6568381", "GSM6568382", "GSM6568383", "GSM6568384", "GSM6568385", "GSM6568386", "GSM6568387", "GSM6568388", "GSM6568389", "GSM6568390", "GSM6568391", "GSM6568392", "GSM6568393", "GSM6568394", "GSM6568395", "GSM6568396", "GSM6568397", "GSM6568398", "GSM6568399", "GSM6568400", "GSM6568401", "GSM6568402", "GSM6568403", "GSM6568404", "GSM6568405", "GSM6568406", "GSM6568407", "GSM6568408", "GSM6568409", "GSM6568410", "GSM6568411", "GSM6568412", "GSM6568413", "GSM6568414", "GSM6568415", "GSM6568416", "GSM6568417", "GSM6568418", "GSM6568419", "GSM6568420", "GSM6568421", "GSM6568422", "GSM6568423", "GSM6568424", "GSM6568425", "GSM6568426", "GSM6568427", "GSM6568428", "GSM6568429", "GSM6568430", "GSM6568431", "GSM6568432", "GSM6568433", "GSM6568434", "GSM6568435", "GSM6568436", "GSM6568437", "GSM6568438", "GSM6568439", "GSM6568440", "GSM6568441", "GSM6568442", "GSM6568443", "GSM6568444", "GSM6568445", "GSM6568446", "GSM6568447", "GSM6568448", "GSM6568449", "GSM6568450", "GSM6568451", "GSM6568452", "GSM6568453", "GSM6568454", "GSM6568455"], "sample_count": 139, "group_sizes": null, "group_sizes_basis": null, "platform": "21290", "taxon": "Homo sapiens", "title": "Bulk tissue RNA sequencing from human donors with and without lung fibrosis", "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:GSE32537", "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=GSE32537", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32537", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM806204", "GSM806205", "GSM806206", "GSM806207", "GSM806208", "GSM806209", "GSM806210", "GSM806211", "GSM806212", "GSM806213", "GSM806214", "GSM806215", "GSM806216", "GSM806217", "GSM806218", "GSM806219", "GSM806220", "GSM806221", "GSM806222", "GSM806223", "GSM806224", "GSM806225", "GSM806226", "GSM806227", "GSM806228", "GSM806229", "GSM806230", "GSM806231", "GSM806232", "GSM806233", "GSM806234", "GSM806235", "GSM806236", "GSM806237", "GSM806238", "GSM806239", "GSM806240", "GSM806241", "GSM806242", "GSM806243", "GSM806244", "GSM806245", "GSM806246", "GSM806247", "GSM806248", "GSM806249", "GSM806250", "GSM806251", "GSM806252", "GSM806253", "GSM806254", "GSM806255", "GSM806256", "GSM806257", "GSM806258", "GSM806259", "GSM806260", "GSM806261", "GSM806262", "GSM806263", "GSM806264", "GSM806265", "GSM806266", "GSM806267", "GSM806268", "GSM806269", "GSM806270", "GSM806271", "GSM806272", "GSM806273", "GSM806274", "GSM806275", "GSM806276", "GSM806277", "GSM806278", "GSM806279", "GSM806280", "GSM806281", "GSM806282", "GSM806283", "GSM806284", "GSM806285", "GSM806286", "GSM806287", "GSM806288", "GSM806289", "GSM806290", "GSM806291", "GSM806292", "GSM806293", "GSM806294", "GSM806295", "GSM806296", "GSM806297", "GSM806298", "GSM806299", "GSM806300", "GSM806301", "GSM806302", "GSM806303", "GSM806304", "GSM806305", "GSM806306", "GSM806307", "GSM806308", "GSM806309", "GSM806310", "GSM806311", "GSM806312", "GSM806313", "GSM806314", "GSM806315", "GSM806316", "GSM806317", "GSM806318", "GSM806319", "GSM806320", "GSM806321", "GSM806322", "GSM806323", "GSM806324", "GSM806325", "GSM806326", "GSM806327", "GSM806328", "GSM806329", "GSM806330", "GSM806331", "GSM806332", "GSM806333", "GSM806334", "GSM806335", "GSM806336", "GSM806337", "GSM806338", "GSM806339", "GSM806340", "GSM806341", "GSM806342", "GSM806343", "GSM806344", "GSM806345", "GSM806346", "GSM806347", "GSM806348", "GSM806349", "GSM806350", "GSM806351", "GSM806352", "GSM806353", "GSM806354", "GSM806355", "GSM806356", "GSM806357", "GSM806358", "GSM806359", "GSM806360", "GSM806361", "GSM806362", "GSM806363", "GSM806364", "GSM806365", "GSM806366", "GSM806367", "GSM806368", "GSM806369", "GSM806370", "GSM806371", "GSM806372", "GSM806373", "GSM806374", "GSM806375", "GSM806376", "GSM806377", "GSM806378", "GSM806379", "GSM806380", "GSM806381", "GSM806382", "GSM806383", "GSM806384", "GSM806385", "GSM806386", "GSM806387", "GSM806388", "GSM806389", "GSM806390", "GSM806391", "GSM806392", "GSM806393", "GSM806394", "GSM806395", "GSM806396", "GSM806397", "GSM806398", "GSM806399", "GSM806400", "GSM806401", "GSM806402", "GSM806403", "GSM806404", "GSM806405", "GSM806406", "GSM806407", "GSM806408", "GSM806409", "GSM806410", "GSM806411", "GSM806412", "GSM806413", "GSM806414", "GSM806415", "GSM806416", "GSM806417", "GSM806418", "GSM806419", "GSM806420"], "sample_count": 217, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Molecular phenotyping of the idiopathic interstitial pneumonias [mRNA]", "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:GSE32538", "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=GSE32538", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32538", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM806421", "GSM806422", "GSM806423", "GSM806424", "GSM806425", "GSM806426", "GSM806427", "GSM806428", "GSM806429", "GSM806430", "GSM806431", "GSM806432", "GSM806433", "GSM806434", "GSM806435", "GSM806436", "GSM806437", "GSM806438", "GSM806439", "GSM806440", "GSM806441", "GSM806442", "GSM806443", "GSM806444", "GSM806445", "GSM806446", "GSM806447", "GSM806448", "GSM806449", "GSM806450", "GSM806451", "GSM806452", "GSM806453", "GSM806454", "GSM806455", "GSM806456", "GSM806457", "GSM806458", "GSM806459", "GSM806460", "GSM806461", "GSM806462", "GSM806463", "GSM806464", "GSM806465", "GSM806466", "GSM806467", "GSM806468", "GSM806469", "GSM806470", "GSM806471", "GSM806472", "GSM806473", "GSM806474", "GSM806475", "GSM806476", "GSM806477", "GSM806478", "GSM806479", "GSM806480", "GSM806481", "GSM806482", "GSM806483", "GSM806484", "GSM806485", "GSM806486", "GSM806487", "GSM806488", "GSM806489", "GSM806490", "GSM806491", "GSM806492", "GSM806493", "GSM806494", "GSM806495", "GSM806496", "GSM806497", "GSM806498", "GSM806499", "GSM806500", "GSM806501", "GSM806502", "GSM806503", "GSM806504", "GSM806505", "GSM806506", "GSM806507", "GSM806508", "GSM806509", "GSM806510", "GSM806511", "GSM806512", "GSM806513", "GSM806514", "GSM806515", "GSM806516", "GSM806517", "GSM806518", "GSM806519", "GSM806520", "GSM806521", "GSM806522", "GSM806523", "GSM806524", "GSM806525", "GSM806526", "GSM806527", "GSM806528", "GSM806529", "GSM806530", "GSM806531", "GSM806532", "GSM806533", "GSM806534", "GSM806535", "GSM806536", "GSM806537", "GSM806538", "GSM806539", "GSM806540", "GSM806541", "GSM806542", "GSM806543", "GSM806544", "GSM806545", "GSM806546", "GSM806547", "GSM806548", "GSM806549", "GSM806550", "GSM806551", "GSM806552", "GSM806553", "GSM806554", "GSM806555", "GSM806556", "GSM806557", "GSM806558", "GSM806559", "GSM806560", "GSM806561", "GSM806562", "GSM806563", "GSM806564", "GSM806565", "GSM806566", "GSM806567", "GSM806568", "GSM806569", "GSM806570", "GSM806571", "GSM806572", "GSM806573", "GSM806574", "GSM806575", "GSM806576", "GSM806577", "GSM806578", "GSM806579", "GSM806580", "GSM806581", "GSM806582", "GSM806583", "GSM806584", "GSM806585", "GSM806586", "GSM806587", "GSM806588", "GSM806589", "GSM806590", "GSM806591", "GSM806592", "GSM806593", "GSM806594", "GSM806595", "GSM806596", "GSM806597", "GSM806598", "GSM806599", "GSM806600", "GSM806601", "GSM806602", "GSM806603", "GSM806604", "GSM806605", "GSM806606", "GSM806607", "GSM806608", "GSM806609", "GSM806610", "GSM806611", "GSM806612"], "sample_count": 192, "group_sizes": null, "group_sizes_basis": null, "platform": "8786", "taxon": "Homo sapiens; synthetic construct", "title": "Molecular phenotyping of the idiopathic interstitial pneumonias [miRNA]", "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:GSE53845", "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=GSE53845", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53845", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1302033", "GSM1302034", "GSM1302035", "GSM1302036", "GSM1302037", "GSM1302038", "GSM1302039", "GSM1302040", "GSM1302041", "GSM1302042", "GSM1302043", "GSM1302044", "GSM1302045", "GSM1302046", "GSM1302047", "GSM1302048", "GSM1302049", "GSM1302050", "GSM1302051", "GSM1302052", "GSM1302053", "GSM1302054", "GSM1302055", "GSM1302056", "GSM1302057", "GSM1302058", "GSM1302059", "GSM1302060", "GSM1302061", "GSM1302062", "GSM1302063", "GSM1302064", "GSM1302065", "GSM1302066", "GSM1302067", "GSM1302068", "GSM1302069", "GSM1302070", "GSM1302071", "GSM1302072", "GSM1302073", "GSM1302074", "GSM1302075", "GSM1302076", "GSM1302077", "GSM1302078", "GSM1302079", "GSM1302080"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "40 IPF patients and 8 healthy controls", "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:GSE92592", "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=GSE92592", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE92592", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2433098", "GSM2433099", "GSM2433100", "GSM2433101", "GSM2433102", "GSM2433103", "GSM2433104", "GSM2433105", "GSM2433106", "GSM2433107", "GSM2433108", "GSM2433109", "GSM2433110", "GSM2433111", "GSM2433112", "GSM2433113", "GSM2433114", "GSM2433115", "GSM2433116", "GSM2433117", "GSM2433118", "GSM2433119", "GSM2433120", "GSM2433121", "GSM2433122", "GSM2433123", "GSM2433124", "GSM2433125", "GSM2433126", "GSM2433127", "GSM2433128", "GSM2433129", "GSM2433130", "GSM2433131", "GSM2433132", "GSM2433133", "GSM2433134", "GSM2433135", "GSM2433136"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "mRNA Sequencing of Ideopathic Pulmonary Fibrosis (IPF) and Control Samples from the Lung Tissue Research Consortium (LTRC)", "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:GSE110147 not downloaded", "asset:data:geo:GSE110147 licence not read", "asset:data:geo:GSE150910 not downloaded", "asset:data:geo:GSE150910 licence not read", "asset:data:geo:GSE213001 not downloaded", "asset:data:geo:GSE213001 licence not read", "asset:data:geo:GSE32537 not downloaded", "asset:data:geo:GSE32537 licence not read", "asset:data:geo:GSE32538 not downloaded", "asset:data:geo:GSE32538 licence not read", "asset:data:geo:GSE53845 not downloaded", "asset:data:geo:GSE53845 licence not read", "asset:data:geo:GSE92592 not downloaded", "asset:data:geo:GSE92592 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify the most critical DEMRGs, we used two machine-learning algorithms: least absolute shrinkage and selection operator (LASSO) regression and support vector machine recursive feature elimination (SVM-RFE)."}}, {"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": "pathway enrichment"}}], "targets": [], "gaps": []}, "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": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE32537", "GSE110147", "GSE150910", "GSE92592", "GSE32538", "GSE53845", "GSE213001"], "resolved_accessions": ["GSE32537", "GSE110147", "GSE150910", "GSE92592", "GSE32538", "GSE53845", "GSE213001"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/; accession number: GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001)."], "basis": "The paper names GSE32537, GSE110147, GSE150910, GSE92592, GSE32538, GSE53845, GSE213001 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": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:36923791", "data:geo:GSE110147"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE110147"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:34:17Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10486, "completion_tokens": 3684, "cached_tokens": 256}}, "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:36923791", "type": "paper", "label": "pmid:36923791"}, {"id": "source:pmid:36923791", "type": "manuscript", "label": "PMID 36923791 full text"}, {"id": "data:geo:GSE110147", "type": "dataset", "label": "GEO GSE110147"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36923791", "type": "paper", "label": "pmid:36923791"}, {"id": "source:pmid:36923791", "type": "manuscript", "label": "PMID 36923791 full text"}, {"id": "data:geo:GSE110147", "type": "dataset", "label": "GEO GSE110147"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36923791", "type": "extraction", "used": ["source:pmid:36923791"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE110147", "type": "accession_resolution", "used": ["data:geo:GSE110147"], "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:36923791", "parent_hash": "sha256:8f954cfa13d68772607739689e7a9b467895884b1d6f72b02cc81b8c83b60464", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE110147 licence not read", "asset:data:geo:GSE110147 not downloaded", "asset:data:geo:GSE150910 licence not read", "asset:data:geo:GSE150910 not downloaded", "asset:data:geo:GSE213001 licence not read", "asset:data:geo:GSE213001 not downloaded", "asset:data:geo:GSE32537 licence not read", "asset:data:geo:GSE32537 not downloaded", "asset:data:geo:GSE32538 licence not read", "asset:data:geo:GSE32538 not downloaded", "asset:data:geo:GSE53845 licence not read", "asset:data:geo:GSE53845 not downloaded", "asset:data:geo:GSE92592 licence not read", "asset:data:geo:GSE92592 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["in two external independent datasets and an in vivo experiment. Results: A total of 101 DEMRGs (", "Laboratory Animal Co., Ltd. (Hunan, China). Mice were housed in pathogen-free conditions with a 12", "onary fibrosis model (Moeller et al., 2008). Mice were randomly divided into two groups: 1) Sham gr", "ne containing BLM (5 mg/kg). Before surgery, mice were anesthetized by intraperitoneal injection of"], "order_basis": "paper_text_order:1347", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To identify the most critical DEMRGs, we used two machine-learning algorithms: least absolute shrinkage and selection operator (LASSO) regression and support vector machine recursive feature elimination (SVM-RFE)."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T01:50:20+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}}}