{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38606153", "kind": "science-record", "revision": 4, "content_hash": "sha256:46b393e13fa4d009495aa00f65a426880a30f4e9ccc9cccda8bf78f4b9eb0505", "created_at": "2026-11-01T19:20:34Z", "updated_at": "2026-11-01T22:54:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Potential diagnostic markers shared between non-alcoholic fatty liver disease and atherosclerosis determined by machine learning and bioinformatic analysis.", "doi": "10.3389/fmed.2024.1322102", "pmid": "38606153", "authors": ["Lihong Wang", "Wenhui He", "Xilin Wang", "Jianrong Wang", "Xiaojuan Wei", "Dongzhi Wu", "Yundan Wu"], "journal": "Frontiers in medicine", "year": 2024, "abstract": "Background: Evidence indicates that chronic non-alcoholic fatty liver disease (NAFLD) can increase the risk of atherosclerosis (AS), but the underlying mechanism remains unclear.\nObjective: This study is intended for confirming key genes shared between NAFLD and AS, and their clinical diagnostic value to establish a foundation for searching novel therapeutic targets.\nMethods: We downloaded the Gene Expression Omnibus (GEO) datasets, GSE48452 and GSE89632 for NAFLD and GSE100927, GSE40231 and GSE28829 for AS. The progression of NAFLD co-expression gene modules were recognized via weighted gene co-expression network analysis (WGCNA). We screened for differentially expressed genes (DEGs) associated with AS and identified common genes associated with NAFLD and AS using Venn diagrams. We investigated the most significant core genes between NAFLD and AS using machine learning algorithms. We then constructed a diagnostic model by creating a nomogram and evaluating its performance using ROC curves. Furthermore, the CIBERSORT algorithm was utilized to explore the immune cell infiltration between the two diseases, and evaluate the relationship between diagnostic genes and immune cells.\nResults: The WGCNA findings associated 1,129 key genes with NAFLD, and the difference analysis results identified 625 DEGs in AS, and 47 genes that were common to both diseases. We screened the core RPS6KA1 and SERPINA3 genes associated with NAFLD and AS using three machine learning algorithms. A nomogram and ROC curves demonstrated that these genes had great clinical meaning. We found differential expression of RPS6KA1 in patients with steatosis and NASH, and of SERPINA3 only in those with NASH compared with normal individuals. Immune infiltration findings revealed that macrophage and mast cell infiltration play important roles in the development of NAFLD and AS. Notably, SERPINA3 correlated negatively, whereas RPS6KA1 correlated positively with macrophages and mast cells.\nConclusion: We identified RPS6KA1 and SERPINA3 as potential diagnostic markers for NAFLD and AS. The most promising marker for a diagnosis of NAFLD and AS might be RPS6KA1, whereas SERPINA3 is the most closely related gene for NASH and AS. We believe that further exploration of these core genes will reveal the etiology and a pathological relationship between NAFLD and AS.", "claims": [{"id": "claim-method", "statement": "We constructed a gene co-expression network for NAFLD by the WGCNA version 1.72.1 package in R version 4.3.1.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38606153", "locator": "sections[4] \"Gene expression analyzed using WGCNA\" paragraph 2", "quote": "We constructed a gene co-expression network for NAFLD by the WGCNA version 1.72.1 package in R version 4.3.1."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38606153", "locator": "sections[25] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The analysis identified 47 genes common to NAFLD and AS.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38606153", "locator": "sections[15] \"Identification of DEGs in AS\" paragraph 2", "quote": "The Venn diagram revealed 47 intersecting genes between AS and NAFLD (Figure 2F). Thus, these two diseases have 47 genes in common."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The analysis identified 47 genes common to NAFLD and AS.", "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:38606153"], "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:GSE100927"], "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:GSE100927"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38606153", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmed.2024.1322102", "sha256": "sha256:ab2b2bace242ad0c09fd209166e54cd9d965542fe286f15c454c7f6722f2bfba", "bytes": 32397, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmed.2024.1322102", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11007109", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE100927", "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=GSE100927", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE100927", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2696609", "GSM2696610", "GSM2696611", "GSM2696612", "GSM2696613", "GSM2696614", "GSM2696615", "GSM2696616", "GSM2696617", "GSM2696618", "GSM2696619", "GSM2696620", "GSM2696621", "GSM2696622", "GSM2696623", "GSM2696624", "GSM2696625", "GSM2696626", "GSM2696627", "GSM2696628", "GSM2696629", "GSM2696630", "GSM2696631", "GSM2696632", "GSM2696633", "GSM2696634", "GSM2696635", "GSM2696636", "GSM2696637", "GSM2696638", "GSM2696639", "GSM2696640", "GSM2696641", "GSM2696642", "GSM2696643", "GSM2696644", "GSM2696645", "GSM2696646", "GSM2696647", "GSM2696648", "GSM2696649", "GSM2696650", "GSM2696651", "GSM2696652", "GSM2696653", "GSM2696654", "GSM2696655", "GSM2696656", "GSM2696657", "GSM2696658", "GSM2696659", "GSM2696660", "GSM2696661", "GSM2696662", "GSM2696663", "GSM2696664", "GSM2696665", "GSM2696666", "GSM2696667", "GSM2696668", "GSM2696669", "GSM2696670", "GSM2696671", "GSM2696672", "GSM2696673", "GSM2696674", "GSM2696675", "GSM2696676", "GSM2696677", "GSM2696678", "GSM2696679", "GSM2696680", "GSM2696681", "GSM2696682", "GSM2696683", "GSM2696684", "GSM2696685", "GSM2696686", "GSM2696687", "GSM2696688", "GSM2696689", "GSM2696690", "GSM2696691", "GSM2696692", "GSM2696693", "GSM2696694", "GSM2696695", "GSM2696696", "GSM2696697", "GSM2696698", "GSM2696699", "GSM2696700", "GSM2696701", "GSM2696702", "GSM2696703", "GSM2696704", "GSM2696705", "GSM2696706", "GSM2696707", "GSM2696708", "GSM2696709", "GSM2696710", "GSM2696711", "GSM2696712"], "sample_count": 104, "group_sizes": null, "group_sizes_basis": null, "platform": "17077", "taxon": "Homo sapiens", "title": "Atherosclerotic and control peripheral artery gene expression", "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:GSE130970", "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=GSE130970", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE130970", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3758005", "GSM3758006", "GSM3758007", "GSM3758008", "GSM3758009", "GSM3758010", "GSM3758011", "GSM3758012", "GSM3758013", "GSM3758014", "GSM3758015", "GSM3758016", "GSM3758017", "GSM3758018", "GSM3758019", "GSM3758020", "GSM3758021", "GSM3758022", "GSM3758023", "GSM3758024", "GSM3758025", "GSM3758026", "GSM3758027", "GSM3758028", "GSM3758029", "GSM3758030", "GSM3758031", "GSM3758032", "GSM3758033", "GSM3758034", "GSM3758035", "GSM3758036", "GSM3758037", "GSM3758038", "GSM3758039", "GSM3758040", "GSM3758041", "GSM3758042", "GSM3758043", "GSM3758044", "GSM3758045", "GSM3758046", "GSM3758047", "GSM3758048", "GSM3758049", "GSM3758050", "GSM3758051", "GSM3758052", "GSM3758053", "GSM3758054", "GSM3758055", "GSM3758056", "GSM3758057", "GSM3758058", "GSM3758059", "GSM3758060", "GSM3758061", "GSM3758062", "GSM3758063", "GSM3758064", "GSM3758065", "GSM3758066", "GSM3758067", "GSM3758068", "GSM3758069", "GSM3758070", "GSM3758071", "GSM3758072", "GSM3758073", "GSM3758074", "GSM3758075", "GSM3758076", "GSM3758077", "GSM3758078", "GSM3758079", "GSM3758080", "GSM3758081", "GSM3758082"], "sample_count": 78, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Gene expression predicts histological severity and reveals distinct molecular profiles of nonalcoholic fatty liver disease", "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:GSE135251", "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=GSE135251", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135251", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3998167", "GSM3998168", "GSM3998169", "GSM3998170", "GSM3998171", "GSM3998172", "GSM3998173", "GSM3998174", "GSM3998175", "GSM3998176", "GSM3998177", "GSM3998178", "GSM3998179", "GSM3998180", "GSM3998181", "GSM3998182", "GSM3998183", "GSM3998184", "GSM3998185", "GSM3998186", "GSM3998187", "GSM3998188", "GSM3998189", "GSM3998190", "GSM3998191", "GSM3998192", "GSM3998193", "GSM3998194", "GSM3998195", "GSM3998196", "GSM3998197", "GSM3998198", "GSM3998199", "GSM3998200", "GSM3998201", "GSM3998202", "GSM3998203", "GSM3998204", "GSM3998205", "GSM3998206", "GSM3998207", "GSM3998208", "GSM3998209", "GSM3998210", "GSM3998211", "GSM3998212", "GSM3998213", "GSM3998214", "GSM3998215", "GSM3998216", "GSM3998217", "GSM3998218", "GSM3998219", "GSM3998220", "GSM3998221", "GSM3998222", "GSM3998223", "GSM3998224", "GSM3998225", "GSM3998226", "GSM3998227", "GSM3998228", "GSM3998229", "GSM3998230", "GSM3998231", "GSM3998232", "GSM3998233", "GSM3998234", "GSM3998235", "GSM3998236", "GSM3998237", "GSM3998238", "GSM3998239", "GSM3998240", "GSM3998241", "GSM3998242", "GSM3998243", "GSM3998244", "GSM3998245", "GSM3998246", "GSM3998247", "GSM3998248", "GSM3998249", "GSM3998250", "GSM3998251", "GSM3998252", "GSM3998253", "GSM3998254", "GSM3998255", "GSM3998256", "GSM3998257", "GSM3998258", "GSM3998259", "GSM3998260", "GSM3998261", "GSM3998262", "GSM3998263", "GSM3998264", "GSM3998265", "GSM3998266", "GSM3998267", "GSM3998268", "GSM3998269", "GSM3998270", "GSM3998271", "GSM3998272", "GSM3998273", "GSM3998274", "GSM3998275", "GSM3998276", "GSM3998277", "GSM3998278", "GSM3998279", "GSM3998280", "GSM3998281", "GSM3998282", "GSM3998283", "GSM3998284", "GSM3998285", "GSM3998286", "GSM3998287", "GSM3998288", "GSM3998289", "GSM3998290", "GSM3998291", "GSM3998292", "GSM3998293", "GSM3998294", "GSM3998295", "GSM3998296", "GSM3998297", "GSM3998298", "GSM3998299", "GSM3998300", "GSM3998301", "GSM3998302", "GSM3998303", "GSM3998304", "GSM3998305", "GSM3998306", "GSM3998307", "GSM3998308", "GSM3998309", "GSM3998310", "GSM3998311", "GSM3998312", "GSM3998313", "GSM3998314", "GSM3998315", "GSM3998316", "GSM3998317", "GSM3998318", "GSM3998319", "GSM3998320", "GSM3998321", "GSM3998322", "GSM3998323", "GSM3998324", "GSM3998325", "GSM3998326", "GSM3998327", "GSM3998328", "GSM3998329", "GSM3998330", "GSM3998331", "GSM3998332", "GSM3998333", "GSM3998334", "GSM3998335", "GSM3998336", "GSM3998337", "GSM3998338", "GSM3998339", "GSM3998340", "GSM3998341", "GSM3998342", "GSM3998343", "GSM3998344", "GSM3998345", "GSM3998346", "GSM3998347", "GSM3998348", "GSM3998349", "GSM3998350", "GSM3998351", "GSM3998352", "GSM3998353", "GSM3998354", "GSM3998355", "GSM3998356", "GSM3998357", "GSM3998358", "GSM3998359", "GSM3998360", "GSM3998361", "GSM3998362", "GSM3998363", "GSM3998364", "GSM3998365", "GSM3998366", "GSM3998367", "GSM3998368", "GSM3998369", "GSM3998370", "GSM3998371", "GSM3998372", "GSM3998373", "GSM3998374", "GSM3998375", "GSM3998376", "GSM3998377", "GSM3998378", "GSM3998379", "GSM3998380", "GSM3998381", "GSM3998382"], "sample_count": 216, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "TRANSCRIPTOMIC PROFILING ACROSS THE SPECTRUM OF NON-ALCOHOLIC FATTY LIVER DISEASE", "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:GSE163154", "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=GSE163154", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE163154", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4973394", "GSM4973395", "GSM4973397", "GSM4973398", "GSM4973400", "GSM4973401", "GSM4973403", "GSM4973404", "GSM4973406", "GSM4973408", "GSM4973409", "GSM4973411", "GSM4973412", "GSM4973414", "GSM4973415", "GSM4973417", "GSM4973418", "GSM4973419", "GSM4973421", "GSM4973422", "GSM4973424", "GSM4973425", "GSM4973427", "GSM4973429", "GSM4973430", "GSM4973432", "GSM4973433", "GSM4973435", "GSM4973436", "GSM4973438", "GSM4973439", "GSM4973440", "GSM4973441", "GSM4973443", "GSM4973444", "GSM4973445", "GSM4973446", "GSM4973448", "GSM4973449", "GSM4973451", "GSM4973452", "GSM4973454", "GSM4973456"], "sample_count": 43, "group_sizes": null, "group_sizes_basis": null, "platform": "6104", "taxon": "Homo sapiens", "title": "Maastricht Human Plaque Study (MaasHPS)", "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:GSE28829", "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=GSE28829", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE28829", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM714070", "GSM714071", "GSM714072", "GSM714073", "GSM714074", "GSM714075", "GSM714076", "GSM714077", "GSM714078", "GSM714079", "GSM714080", "GSM714081", "GSM714082", "GSM714083", "GSM714084", "GSM714085", "GSM714086", "GSM714087", "GSM714088", "GSM714089", "GSM714090", "GSM714091", "GSM714092", "GSM714093", "GSM714094", "GSM714095", "GSM714096", "GSM714097", "GSM714098"], "sample_count": 29, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression in early and advanced atherosclerotic plaque from human carotid", "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:GSE40231", "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=GSE40231", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40231", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM988656", "GSM988657", "GSM988658", "GSM988659", "GSM988660", "GSM988661", "GSM988662", "GSM988663", "GSM988664", "GSM988665", "GSM988666", "GSM988667", "GSM988668", "GSM988669", "GSM988670", "GSM988671", "GSM988672", "GSM988673", "GSM988674", "GSM988675", "GSM988676", "GSM988677", "GSM988678", "GSM988679", "GSM988680", "GSM988681", "GSM988682", "GSM988683", "GSM988684", "GSM988685", "GSM988686", "GSM988687", "GSM988688", "GSM988689", "GSM988690", "GSM988691", "GSM988692", "GSM988693", "GSM988694", "GSM988695", "GSM988696", "GSM988697", "GSM988698", "GSM988699", "GSM988700", "GSM988701", "GSM988702", "GSM988703", "GSM988704", "GSM988705", "GSM988706", "GSM988707", "GSM988708", "GSM988709", "GSM988710", "GSM988711", "GSM988712", "GSM988713", "GSM988714", "GSM988715", "GSM988716", "GSM988717", "GSM988718", "GSM988719", "GSM988720", "GSM988721", "GSM988722", "GSM988723", "GSM988724", "GSM988725", "GSM988726", "GSM988727", "GSM988728", "GSM988729", "GSM988730", "GSM988731", "GSM988732", "GSM988733", "GSM988734", "GSM988735", "GSM988736", "GSM988737", "GSM988738", "GSM988739", "GSM988740", "GSM988741", "GSM988742", "GSM988743", "GSM988744", "GSM988745", "GSM988746", "GSM988747", "GSM988748", "GSM988749", "GSM988750", "GSM988751", "GSM988752", "GSM988753", "GSM988754", "GSM988755", "GSM988756", "GSM988757", "GSM988758", "GSM988759", "GSM988760", "GSM988761", "GSM988762", "GSM988763", "GSM988764", "GSM988765", "GSM988766", "GSM988767", "GSM988768", "GSM988769", "GSM988770", "GSM988771", "GSM988772", "GSM988773", "GSM988774", "GSM988775", "GSM988776", "GSM988777", "GSM988778", "GSM988779", "GSM988780", "GSM988781", "GSM988782", "GSM988783", "GSM988784", "GSM988785", "GSM988786", "GSM988787", "GSM988788", "GSM988789", "GSM988790", "GSM988791", "GSM988792", "GSM988793", "GSM988794", "GSM988795", "GSM988796", "GSM988797", "GSM988798", "GSM988799", "GSM988800", "GSM988801", "GSM988802", "GSM988803", "GSM988804", "GSM988805", "GSM988806", "GSM988807", "GSM988808", "GSM988809", "GSM988810", "GSM988811", "GSM988812", "GSM988813", "GSM988814", "GSM988815", "GSM988816", "GSM988817", "GSM988818", "GSM988819", "GSM988820", "GSM988821", "GSM988822", "GSM988823", "GSM988824", "GSM988825", "GSM988826", "GSM988827", "GSM988828", "GSM988829", "GSM988830", "GSM988831", "GSM988832", "GSM988833", "GSM988834", "GSM988835", "GSM988836", "GSM988837", "GSM988838", "GSM988839", "GSM988840", "GSM988841", "GSM988842", "GSM988843", "GSM988844", "GSM988845", "GSM988846", "GSM988847", "GSM988848", "GSM988849", "GSM988850", "GSM988851", "GSM988852", "GSM988853", "GSM988854", "GSM988855", "GSM988856", "GSM988857", "GSM988858", "GSM988859", "GSM988860", "GSM988861", "GSM988862", "GSM988863", "GSM988864", "GSM988865", "GSM988866", "GSM988867", "GSM988868", "GSM988869", "GSM988870", "GSM988871", "GSM988872", "GSM988873", "GSM988874", "GSM988875", "GSM988876", "GSM988877", "GSM988878", "GSM988879", "GSM988880", "GSM988881", "GSM988882", "GSM988883", "GSM988884", "GSM988885", "GSM988886", "GSM988887", "GSM988888", "GSM988889", "GSM988890", "GSM988891", "GSM988892", "GSM988893", "GSM988894", "GSM988895", "GSM988896", "GSM988897", "GSM988898", "GSM988899", "GSM988900", "GSM988901", "GSM988902", "GSM988903", "GSM988904", "GSM988905", "GSM988906", "GSM988907", "GSM988908", "GSM988909", "GSM988910", "GSM988911", "GSM988912", "GSM988913", "GSM988914", "GSM988915", "GSM988916", "GSM988917", "GSM988918", "GSM988919", "GSM988920", "GSM988921", "GSM988922", "GSM988923", "GSM988924", "GSM988925", "GSM988926", "GSM988927", "GSM988928", "GSM988929", "GSM988930", "GSM988931", "GSM988932", "GSM988933"], "sample_count": 278, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "The Stockholm Atherosclerosis Gene Expression (STAGE) study: Global Gene Expression data from coronary and carotid artery disease 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:GSE48452", "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=GSE48452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48452", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1178970", "GSM1178971", "GSM1178972", "GSM1178973", "GSM1178974", "GSM1178975", "GSM1178976", "GSM1178977", "GSM1178978", "GSM1178979", "GSM1178980", "GSM1178981", "GSM1178982", "GSM1178983", "GSM1178984", "GSM1178985", "GSM1178986", "GSM1178987", "GSM1178988", "GSM1178989", "GSM1178990", "GSM1178991", "GSM1178992", "GSM1178993", "GSM1178994", "GSM1178995", "GSM1178996", "GSM1178997", "GSM1178998", "GSM1178999", "GSM1179000", "GSM1179001", "GSM1179002", "GSM1179003", "GSM1179004", "GSM1179005", "GSM1179006", "GSM1179007", "GSM1179008", "GSM1179009", "GSM1179010", "GSM1179011", "GSM1179012", "GSM1179013", "GSM1179014", "GSM1179015", "GSM1179016", "GSM1179017", "GSM1179018", "GSM1179019", "GSM1179020", "GSM1179021", "GSM1179022", "GSM1179023", "GSM1179024", "GSM1179025", "GSM1179026", "GSM1179027", "GSM1179028", "GSM1179029", "GSM1179030", "GSM1179031", "GSM1179032", "GSM1179033", "GSM1179034", "GSM1179035", "GSM1179036", "GSM1179037", "GSM1179038", "GSM1179039", "GSM1179040", "GSM1179041", "GSM1179042"], "sample_count": 73, "group_sizes": null, "group_sizes_basis": null, "platform": "11532", "taxon": "Homo sapiens", "title": "Human liver biopsy of different phases from control to 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:GSE57691", "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=GSE57691", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57691", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1386783", "GSM1386784", "GSM1386785", "GSM1386786", "GSM1386787", "GSM1386788", "GSM1386789", "GSM1386790", "GSM1386791", "GSM1386792", "GSM1386793", "GSM1386794", "GSM1386795", "GSM1386796", "GSM1386797", "GSM1386798", "GSM1386799", "GSM1386800", "GSM1386801", "GSM1386802", "GSM1386803", "GSM1386804", "GSM1386805", "GSM1386806", "GSM1386807", "GSM1386808", "GSM1386809", "GSM1386810", "GSM1386811", "GSM1386812", "GSM1386813", "GSM1386814", "GSM1386815", "GSM1386816", "GSM1386817", "GSM1386818", "GSM1386819", "GSM1386820", "GSM1386821", "GSM1386822", "GSM1386823", "GSM1386824", "GSM1386825", "GSM1386826", "GSM1386827", "GSM1386828", "GSM1386829", "GSM1386830", "GSM1386831", "GSM1386832", "GSM1386833", "GSM1386834", "GSM1386835", "GSM1386836", "GSM1386837", "GSM1386838", "GSM1386839", "GSM1386840", "GSM1386841", "GSM1386842", "GSM1386843", "GSM1386844", "GSM1386845", "GSM1386846", "GSM1386847", "GSM1386848", "GSM1386849", "GSM1386850"], "sample_count": 68, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Differential gene expression in human abdominal aortic aneurysm and atherosclerosis", "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:GSE58979", "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=GSE58979", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58979", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1423267", "GSM1423268", "GSM1423269", "GSM1423270", "GSM1423271", "GSM1423272", "GSM1423273", "GSM1423274", "GSM1423275", "GSM1423276", "GSM1423277", "GSM1423278", "GSM1423279", "GSM1423280", "GSM1423281", "GSM1423282", "GSM1423283", "GSM1423284", "GSM1423285", "GSM1423286", "GSM1423287", "GSM1423288", "GSM1423289", "GSM1423290", "GSM1423291", "GSM1423292", "GSM1423293", "GSM1423294", "GSM1423295", "GSM1423296", "GSM1423297", "GSM1423298", "GSM1423299", "GSM1423300", "GSM1423301", "GSM1423302", "GSM1423303", "GSM1423304", "GSM1423305", "GSM1423306", "GSM1423307", "GSM1423308", "GSM1423309", "GSM1423310", "GSM1423311", "GSM1423312", "GSM1423313", "GSM1423314", "GSM1423315", "GSM1423316", "GSM1423317", "GSM1423318", "GSM1423319"], "sample_count": 53, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Gene expression in subcutaneous and visceral fat predicts liver histology in morbidly obese 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: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": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_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": "data:geo:GSE97210", "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=GSE97210", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE97210", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2559712", "GSM2559713", "GSM2559714", "GSM2559715", "GSM2559716", "GSM2559717"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "16956", "taxon": "Homo sapiens", "title": "LncRNA/mRNA expression profiling for human normal arterial intimae and advanced atherosclerotic plaques", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE100927 not downloaded", "asset:data:geo:GSE100927 licence not read", "asset:data:geo:GSE130970 not downloaded", "asset:data:geo:GSE130970 licence not read", "asset:data:geo:GSE135251 not downloaded", "asset:data:geo:GSE135251 licence not read", "asset:data:geo:GSE163154 not downloaded", "asset:data:geo:GSE163154 licence not read", "asset:data:geo:GSE28829 not downloaded", "asset:data:geo:GSE28829 licence not read", "asset:data:geo:GSE40231 not downloaded", "asset:data:geo:GSE40231 licence not read", "asset:data:geo:GSE48452 not downloaded", "asset:data:geo:GSE48452 licence not read", "asset:data:geo:GSE57691 not downloaded", "asset:data:geo:GSE57691 licence not read", "asset:data:geo:GSE58979 not downloaded", "asset:data:geo:GSE58979 licence not read", "asset:data:geo:GSE89632 not downloaded", "asset:data:geo:GSE89632 licence not read", "asset:data:geo:GSE97210 not downloaded", "asset:data:geo:GSE97210 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We constructed a gene co-expression network for NAFLD by the WGCNA version 1.72.1 package in R version 4.3.1."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "analysis of variance"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE48452", "GSE89632", "GSE100927", "GSE130970", "GSE135251", "GSE58979", "GSE40231", "GSE28829", "GSE97210", "GSE57691", "GSE163154"], "resolved_accessions": ["GSE48452", "GSE89632", "GSE100927", "GSE130970", "GSE135251", "GSE58979", "GSE40231", "GSE28829", "GSE97210", "GSE57691", "GSE163154"], "statements": ["The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE48452, GSE89632, GSE100927, GSE130970, GSE135251, GSE58979, GSE40231, GSE28829, GSE97210, GSE57691, GSE163154 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:38606153", "data:geo:GSE100927"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE100927"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:15:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9492, "completion_tokens": 2367, "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:38606153", "type": "paper", "label": "pmid:38606153"}, {"id": "source:pmid:38606153", "type": "manuscript", "label": "PMID 38606153 full text"}, {"id": "data:geo:GSE100927", "type": "dataset", "label": "GEO GSE100927"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38606153", "type": "paper", "label": "pmid:38606153"}, {"id": "source:pmid:38606153", "type": "manuscript", "label": "PMID 38606153 full text"}, {"id": "data:geo:GSE100927", "type": "dataset", "label": "GEO GSE100927"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38606153", "type": "extraction", "used": ["source:pmid:38606153"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE100927", "type": "accession_resolution", "used": ["data:geo:GSE100927"], "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:38606153", "parent_hash": "sha256:f3bbd734bc5c3290739a19ae239084503c91c20075597f04780ec0626beb2965", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE100927 licence not read", "asset:data:geo:GSE100927 not downloaded", "asset:data:geo:GSE130970 licence not read", "asset:data:geo:GSE130970 not downloaded", "asset:data:geo:GSE135251 licence not read", "asset:data:geo:GSE135251 not downloaded", "asset:data:geo:GSE163154 licence not read", "asset:data:geo:GSE163154 not downloaded", "asset:data:geo:GSE28829 licence not read", "asset:data:geo:GSE28829 not downloaded", "asset:data:geo:GSE40231 licence not read", "asset:data:geo:GSE40231 not downloaded", "asset:data:geo:GSE48452 licence not read", "asset:data:geo:GSE48452 not downloaded", "asset:data:geo:GSE57691 licence not read", "asset:data:geo:GSE57691 not downloaded", "asset:data:geo:GSE58979 licence not read", "asset:data:geo:GSE58979 not downloaded", "asset:data:geo:GSE89632 licence not read", "asset:data:geo:GSE89632 not downloaded", "asset:data:geo:GSE97210 licence not read", "asset:data:geo:GSE97210 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["ptor signaling, and FoxO signaling pathways, apoptosis, fatty acid metabolism, lipid and atheroscle"], "order_basis": "paper_text_order:4595", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We constructed a gene co-expression network for NAFLD by the WGCNA version 1.72.1 package in R version 4.3.1."], "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":"2026-11-04T01:48:48+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}}}