{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38701314", "kind": "science-record", "revision": 4, "content_hash": "sha256:7e2bdbb725f88fb17e2073ed153134cbc858a55f108c222829d26672843d4ed7", "created_at": "2026-11-01T19:20:40Z", "updated_at": "2026-11-01T22:11:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Exploring the role of CDCA4 in liver hepatocellular carcinoma using bioinformatics analysis and experiments.", "doi": "10.1097/MD.0000000000038028", "pmid": "38701314", "authors": ["Changfu Liang", "Kaijun Long", "Wenhao Zheng", "Riqiang Zhong", "Zhangrui Li", "Shengwei Zhu", "Shijing Gu", "Chuangshi Zhu", "Yan Yang"], "journal": "Medicine", "year": 2024, "abstract": "Liver hepatocellular carcinoma (LIHC) encompasses diverse therapeutic approaches, among which targeted therapy has gained significant prominence in recent years. The identification of numerous targets and the increasing clinical application of targeted drugs have greatly improved LIHC treatment. However, the precise role of CDCA4 (Cell Division Cycle Associated 4), as well as its underlying mechanisms and prognostic implications in LIHC, remains unclear. CDCA4 expression levels in LIHC were analyzed using multiple databases including the cancer genome atlas (TCGA), gene expression profiling interactive analysis (GEPIA), and ULCAN, as well as the datasets E_TABM_36, GSE144269, GSE14520, and GSE54236. The prognostic value of CDCA4 was then evaluated. Subsequently, the association between CDCA4 and immune cells was investigated. Enrichment analysis (GSEA) was utilized to investigate the functional roles and pathways linked to CDCA4. Additionally, the methylation patterns and drug sensitivity of CDCA4 were examined. A predictive model incorporating immune genes related to CDCA4 was developed. The TISCH dataset was used to investigate the single-cell expression patterns of CDCA4. Finally, validation of CDCA4 expression levels was conducted through RT-PCR, Western blotting, and immunohistochemistry. CDCA4 exhibited significant overexpression in LIHC and demonstrated significant correlations with clinical features. High expression of CDCA4 is associated with a poorer prognosis. Analysis of immune infiltration and enrichment revealed its association with the immune microenvironment. Furthermore, its expression is correlated with methylation and mutation patterns. CDCA4 is associated with 19 drugs. Prognostic models utilizing CDCA4 demonstrate favorable effectiveness. T cell subtypes were found to be associated with CDCA4 through single-cell analysis. The conclusive experiment provided evidence of significant upregulation of CDCA4 in LIHC. The high expression of CDCA4 in LIHC is associated with prognostic significance and is highly expressed in T cell subtypes, providing a new therapeutic target and potential therapeutic strategy for LIHC.", "claims": [{"id": "claim-method", "statement": "Univariate Cox regression analysis was carried out to assess the impact of CDCA4 on patient prognosis, specifically in LIHC. The association between CDCA4 and overall survival (OS) was investigated using the Kaplan–Meier method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38701314", "locator": "sections[4] \"2.2. Prognostic analysis of CDCA4\" paragraph 2", "quote": "Univariate Cox regression analysis was carried out to assess the impact of CDCA4 on patient prognosis, specifically in LIHC. The association between CDCA4 and overall survival (OS) was investigated using the Kaplan–Meier method."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38701314", "locator": "sections[34] \"fn-group\" paragraph 1", "quote": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:38701314"], "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:GSE125449"], "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:GSE125449"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38701314", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000038028", "sha256": "sha256:2bc153a95eb0b5e0966ac985fa118fe23302c99561c5484afab5ccd4b01c3fca", "bytes": 49061, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000038028", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11062718", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE125449", "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=GSE125449", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE125449", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4050085", "GSM4050086", "GSM4050087", "GSM4050088", "GSM4050089", "GSM4050090", "GSM4050091", "GSM4050092", "GSM4050093", "GSM4050094", "GSM4050095", "GSM4050096", "GSM4050098", "GSM4050100", "GSM4050102", "GSM4050104", "GSM4050106", "GSM4050108", "GSM4050110"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "18573;20301", "taxon": "Homo sapiens", "title": "Tumor cell biodiversity drives microenvironmental reprogramming in liver cancer", "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:GSE144269", "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=GSE144269", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE144269", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4284605", "GSM4284606", "GSM4284607", "GSM4284608", "GSM4284609", "GSM4284610", "GSM4284611", "GSM4284612", "GSM4284613", "GSM4284614", "GSM4284615", "GSM4284616", "GSM4284617", "GSM4284618", "GSM4284619", "GSM4284620", "GSM4284621", "GSM4284622", "GSM4284623", "GSM4284624", "GSM4284625", "GSM4284626", "GSM4284627", "GSM4284628", "GSM4284629", "GSM4284630", "GSM4284631", "GSM4284632", "GSM4284633", "GSM4284634", "GSM4284635", "GSM4284636", "GSM4284637", "GSM4284638", "GSM4284639", "GSM4284640", "GSM4284641", "GSM4284642", "GSM4284643", "GSM4284644", "GSM4284645", "GSM4284646", "GSM4284647", "GSM4284648", "GSM4284649", "GSM4284650", "GSM4284651", "GSM4284652", "GSM4284653", "GSM4284654", "GSM4284655", "GSM4284656", "GSM4284657", "GSM4284658", "GSM4284659", "GSM4284660", "GSM4284661", "GSM4284662", "GSM4284663", "GSM4284664", "GSM4284665", "GSM4284666", "GSM4284667", "GSM4284668", "GSM4284669", "GSM4284670", "GSM4284671", "GSM4284672", "GSM4284673", "GSM4284674", "GSM4284675", "GSM4284676", "GSM4284677", "GSM4284678", "GSM4284679", "GSM4284680", "GSM4284681", "GSM4284682", "GSM4284683", "GSM4284684", "GSM4284685", "GSM4284686", "GSM4284687", "GSM4284688", "GSM4284689", "GSM4284690", "GSM4284691", "GSM4284692", "GSM4284693", "GSM4284694", "GSM4284695", "GSM4284696", "GSM4284697", "GSM4284698", "GSM4284699", "GSM4284700", "GSM4284701", "GSM4284702", "GSM4284703", "GSM4284704", "GSM4284705", "GSM4284706", "GSM4284707", "GSM4284708", "GSM4284709", "GSM4284710", "GSM4284711", "GSM4284712", "GSM4284713", "GSM4284714", "GSM4284715", "GSM4284716", "GSM4284717", "GSM4284718", "GSM4284719", "GSM4284720", "GSM4284721", "GSM4284722", "GSM4284723", "GSM4284724", "GSM4284725", "GSM4284726", "GSM4284727", "GSM4284728", "GSM4284729", "GSM4284730", "GSM4284731", "GSM4284732", "GSM4284733", "GSM4284734", "GSM4284735", "GSM4284736", "GSM4284737", "GSM4284738", "GSM4284739", "GSM4284740", "GSM4284741", "GSM4284742", "GSM4284743", "GSM4284744"], "sample_count": 140, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "The genomic landscape of Mongolian hepatocellular carcinoma", "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:GSE14520", "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=GSE14520", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14520", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM362947", "GSM362948", "GSM362949", "GSM362950", "GSM362951", "GSM362952", "GSM362953", "GSM362954", "GSM362955", "GSM362956", "GSM362957", "GSM362958", "GSM362959", "GSM362960", "GSM362961", "GSM362962", "GSM362963", "GSM362964", "GSM362965", "GSM362966", "GSM362967", "GSM362968", "GSM362969", "GSM362970", "GSM362971", "GSM362972", "GSM362973", "GSM362974", "GSM362975", "GSM362976", "GSM362977", "GSM362978", "GSM362979", "GSM362980", "GSM362981", "GSM362982", "GSM362983", "GSM362984", "GSM362985", "GSM362986", "GSM362987", "GSM362988", "GSM362989", "GSM362990", "GSM362991", "GSM362992", "GSM362993", "GSM362994", "GSM362995", "GSM362996", "GSM362997", "GSM362998", "GSM362999", "GSM363000", "GSM363001", "GSM363002", "GSM363003", "GSM363004", "GSM363005", "GSM363006", "GSM363007", "GSM363008", "GSM363009", "GSM363010", "GSM363011", "GSM363012", "GSM363013", "GSM363014", "GSM363015", "GSM363016", "GSM363017", "GSM363018", "GSM363019", "GSM363020", "GSM363021", "GSM363022", "GSM363023", "GSM363024", "GSM363025", "GSM363026", "GSM363027", "GSM363028", "GSM363029", "GSM363030", "GSM363031", "GSM363032", "GSM363033", "GSM363034", "GSM363035", "GSM363036", "GSM363037", "GSM363038", "GSM363039", "GSM363040", "GSM363041", "GSM363042", "GSM363043", "GSM363044", "GSM363045", "GSM363046", "GSM363047", "GSM363048", "GSM363049", "GSM363050", "GSM363051", "GSM363052", "GSM363053", "GSM363054", "GSM363055", "GSM363056", "GSM363057", "GSM363058", "GSM363059", "GSM363060", "GSM363061", "GSM363062", "GSM363063", "GSM363064", "GSM363065", "GSM363066", "GSM363067", "GSM363068", "GSM363069", "GSM363070", "GSM363071", "GSM363072", "GSM363073", "GSM363074", "GSM363075", "GSM363076", "GSM363077", "GSM363078", "GSM363079", "GSM363080", "GSM363081", "GSM363082", "GSM363083", "GSM363084", "GSM363085", "GSM363086", "GSM363087", "GSM363088", "GSM363089", "GSM363090", "GSM363091", "GSM363092", "GSM363093", "GSM363094", "GSM363095", "GSM363096", "GSM363097", "GSM363098", "GSM363099", "GSM363100", "GSM363101", "GSM363102", "GSM363103", "GSM363104", "GSM363105", "GSM363106", "GSM363107", "GSM363108", "GSM363109", "GSM363110", "GSM363111", "GSM363112", "GSM363113", "GSM363114", "GSM363115", "GSM363116", "GSM363117", "GSM363118", "GSM363119", "GSM363120", "GSM363121", "GSM363122", "GSM363123", "GSM363124", "GSM363125", "GSM363126", "GSM363127", "GSM363128", "GSM363129", "GSM363130", "GSM363131", "GSM363132", "GSM363133", "GSM363134", "GSM363135", "GSM363136", "GSM363137", "GSM363138", "GSM363139", "GSM363140", "GSM363141", "GSM363142", "GSM363143", "GSM363144", "GSM363145", "GSM363146", "GSM363147", "GSM363148", "GSM363149", "GSM363150", "GSM363151", "GSM363152", "GSM363153", "GSM363154", "GSM363155", "GSM363156", "GSM363157", "GSM363158", "GSM363159", "GSM363160", "GSM363161", "GSM363162", "GSM363163", "GSM363164", "GSM363165", "GSM363166", "GSM363167", "GSM363168", "GSM363169", "GSM363170", "GSM363171", "GSM363172", "GSM363173", "GSM363174", "GSM363175", "GSM363176", "GSM363177", "GSM363178", "GSM363179", "GSM363180", "GSM363181", "GSM363182", "GSM363183", "GSM363184", "GSM363185", "GSM363186", "GSM363187", "GSM363188", "GSM363189", "GSM363190", "GSM363191", "GSM363192", "GSM363193", "GSM363194", "GSM363195", "GSM363196", "GSM363197", "GSM363198", "GSM363199", "GSM363200", "GSM363201", "GSM363202", "GSM363203", "GSM363204", "GSM363205", "GSM363206", "GSM363207", "GSM363208", "GSM363209", "GSM363210", "GSM363211", "GSM363212", "GSM363213", "GSM363214", "GSM363215", "GSM363216", "GSM363217", "GSM363218", "GSM363219", "GSM363220", "GSM363221", "GSM363222", "GSM363223", "GSM363224", "GSM363225", "GSM363226", "GSM363227", "GSM363228", "GSM363229", "GSM363230", "GSM363231", "GSM363232", "GSM363233", "GSM363234", "GSM363235", "GSM363236", "GSM363237", "GSM363238", "GSM363239", "GSM363240", "GSM363241", "GSM363242", "GSM363243", "GSM363244", "GSM363245", "GSM363246", "GSM363247", "GSM363248", "GSM363249", "GSM363250", "GSM363251", "GSM363252", "GSM363253", "GSM363254", "GSM363255", "GSM363256", "GSM363257", "GSM363258", "GSM363259", "GSM363260", "GSM363261", "GSM363262", "GSM363263", "GSM363264", "GSM363265", "GSM363266", "GSM363267", "GSM363268", "GSM363269", "GSM363270", "GSM363271", "GSM363272", "GSM363273", "GSM363274", "GSM363275", "GSM363276", "GSM363277", "GSM363278", "GSM363279", "GSM363280", "GSM363281", "GSM363282", "GSM363283", "GSM363284", "GSM363285", "GSM363286", "GSM363287", "GSM363288", "GSM363289", "GSM363290", "GSM363291", "GSM363292", "GSM363293", "GSM363294", "GSM363295", "GSM363296", "GSM363297", "GSM363298", "GSM363299", "GSM363300", "GSM363301", "GSM363302", "GSM363303", "GSM363304", "GSM363305", "GSM363306", "GSM363307", "GSM363308", "GSM363309", "GSM363310", "GSM363311", "GSM363312", "GSM363313", "GSM363314", "GSM363315", "GSM363316", "GSM363317", "GSM363318", "GSM363319", "GSM363320", "GSM363321", "GSM363322", "GSM363323", "GSM363324", "GSM363325", "GSM363326", "GSM363327", "GSM363328", "GSM363329", "GSM363330", "GSM363331", "GSM363332", "GSM363333", "GSM363334", "GSM363335", "GSM363336", "GSM363337", "GSM363338", "GSM363339", "GSM363340", "GSM363341", "GSM363342", "GSM363343", "GSM363344", "GSM363345", "GSM363346", "GSM363347", "GSM363348", "GSM363349", "GSM363350", "GSM363351", "GSM363352", "GSM363353", "GSM363354", "GSM363355", "GSM363356", "GSM363357", "GSM363358", "GSM363359", "GSM363360", "GSM363361", "GSM363362", "GSM363363", "GSM363364", "GSM363365", "GSM363366", "GSM363367", "GSM363368", "GSM363369", "GSM363370", "GSM363371", "GSM363372", "GSM363373", "GSM363374", "GSM363375", "GSM363376", "GSM363378", "GSM363380", "GSM363381", "GSM363382", "GSM363384", "GSM363386", "GSM363388", "GSM363391", "GSM363393", "GSM363397", "GSM363400", "GSM363402", "GSM363404", "GSM363407", "GSM363417", "GSM363420", "GSM363421", "GSM363422", "GSM363423", "GSM363424", "GSM363425", "GSM363426", "GSM363427", "GSM363428", "GSM363429", "GSM363430", "GSM363431", "GSM363432", "GSM363433", "GSM363434", "GSM363435", "GSM363436", "GSM363437", "GSM363438", "GSM363439", "GSM363440", "GSM363441", "GSM363442", "GSM363443", "GSM363444", "GSM363445", "GSM363446", "GSM363447", "GSM363448", "GSM363449", "GSM363450", "GSM363451", "GSM712532", "GSM712533", "GSM712534", "GSM712535", "GSM712536", "GSM712537", "GSM712538", "GSM712539", "GSM712540", "GSM712541", "GSM712542"], "sample_count": 488, "group_sizes": null, "group_sizes_basis": null, "platform": "3921;571", "taxon": "Homo sapiens", "title": "Gene expression data of human hepatocellular carcinoma (HCC)", "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:GSE146115", "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=GSE146115", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE146115", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4365547", "GSM4365548", "GSM4365549", "GSM4365550", "GSM4365551", "GSM4365552", "GSM4365553", "GSM4365554", "GSM4365555", "GSM4365556", "GSM4365557", "GSM4365558", "GSM4365559", "GSM4365560", "GSM4365561", "GSM4365562"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "20795", "taxon": "Homo sapiens", "title": "Single-cell transcriptomic analysis of human hepatocellular carcinoma", "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:GSE146409", "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=GSE146409", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE146409", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4384856", "GSM4384857", "GSM4384858", "GSM4384859", "GSM4384860", "GSM4384861", "GSM4384862", "GSM4384863", "GSM4384864", "GSM4384865", "GSM4384866", "GSM4384867", "GSM4384909", "GSM4384910", "GSM4384911", "GSM4384912", "GSM4384913", "GSM4384914", "GSM4384915", "GSM4384916", "GSM4384917", "GSM4384918", "GSM4384919", "GSM4384920", "GSM4384921", "GSM4384922", "GSM4384923", "GSM4384924", "GSM4384925", "GSM4384926", "GSM4384927", "GSM4384928", "GSM4384929", "GSM4384930", "GSM4384931", "GSM4384932", "GSM4384933", "GSM4384934", "GSM4384935", "GSM4384936", "GSM4384937", "GSM4384938", "GSM4384939", "GSM4384940", "GSM4384941", "GSM4384942", "GSM4384943", "GSM4384944", "GSM4384945", "GSM4384946", "GSM4384947", "GSM4384948", "GSM4384949", "GSM4384950", "GSM4384951", "GSM4384952", "GSM4384953", "GSM4384954", "GSM4384955", "GSM4384956", "GSM4384957", "GSM4384958", "GSM4384959", "GSM4384960", "GSM4384961", "GSM4384962", "GSM4384963", "GSM4384964", "GSM4384965", "GSM4384966", "GSM4384967", "GSM4384968", "GSM4384969", "GSM4384970", "GSM4384971", "GSM4384972", "GSM4384973", "GSM4384974", "GSM4384975", "GSM4384976", "GSM4384977", "GSM4384978", "GSM4384979", "GSM4384980", "GSM4384981", "GSM4384982", "GSM4384983", "GSM4384984", "GSM4798979", "GSM4798980", "GSM4798981", "GSM4798982", "GSM4798983", "GSM4798984", "GSM4798985", "GSM4798986", "GSM4798987", "GSM4798988", "GSM4798989", "GSM4798990", "GSM4798991", "GSM4798992", "GSM4798993", "GSM4798994", "GSM4798995", "GSM4798996", "GSM4798997", "GSM4798998", "GSM4798999", "GSM4799000", "GSM4799001", "GSM4799002", "GSM4799003", "GSM4799004", "GSM4799005", "GSM4799006", "GSM4799007", "GSM4799008", "GSM4799009", "GSM4799010", "GSM4799011", "GSM4799012", "GSM4799013", "GSM4799014", "GSM4799015", "GSM4799016", "GSM4799017", "GSM4799018", "GSM4799019", "GSM4799020", "GSM4799021", "GSM4799022", "GSM4799023", "GSM4799024", "GSM4799025", "GSM4799026", "GSM4799027", "GSM4799028", "GSM4799029", "GSM4799030", "GSM4799031", "GSM4799032", "GSM4799033", "GSM4799034", "GSM4799035", "GSM4799036", "GSM4799037", "GSM4799038", "GSM4799039", "GSM4799040", "GSM4799041"], "sample_count": 151, "group_sizes": null, "group_sizes_basis": null, "platform": "21697", "taxon": "Homo sapiens", "title": "A single cell atlas of the human liver tumor microenvironment", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE166635", "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=GSE166635", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE166635", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5076749", "GSM5076750"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "TNFR2 HnRNPK-YAP Signaling Axis Promotes Primary Liver Cancer Development in Hepatic Progenitor Cells", "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:GSE179795", "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=GSE179795", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE179795", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5434232", "GSM5434233", "GSM5434234", "GSM5434235", "GSM5434236", "GSM5434237", "GSM5434238", "GSM5434239", "GSM5434240", "GSM5434241", "GSM5434242", "GSM5434243", "GSM5434244", "GSM5434245", "GSM5434246", "GSM5434247", "GSM5434248", "GSM5434249", "GSM5434250", "GSM5434251", "GSM5434252", "GSM5434253", "GSM5434254", "GSM5434255"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "The Tumor Microenvironment Shapes Innate Lymphoid Cells in Patients with Hepatocellular Carcinoma", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE54236", "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=GSE54236", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54236", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1310570", "GSM1310571", "GSM1310572", "GSM1310573", "GSM1310574", "GSM1310575", "GSM1310576", "GSM1310577", "GSM1310578", "GSM1310579", "GSM1310580", "GSM1310581", "GSM1310582", "GSM1310583", "GSM1310584", "GSM1310585", "GSM1310586", "GSM1310587", "GSM1310588", "GSM1310589", "GSM1310590", "GSM1310591", "GSM1310592", "GSM1310593", "GSM1310594", "GSM1310595", "GSM1310596", "GSM1310597", "GSM1310598", "GSM1310599", "GSM1310600", "GSM1310601", "GSM1310602", "GSM1310603", "GSM1310604", "GSM1310605", "GSM1310606", "GSM1310607", "GSM1310608", "GSM1310609", "GSM1310610", "GSM1310611", "GSM1310612", "GSM1310613", "GSM1310614", "GSM1310615", "GSM1310616", "GSM1310617", "GSM1310618", "GSM1310619", "GSM1310620", "GSM1310621", "GSM1310622", "GSM1310623", "GSM1310624", "GSM1310625", "GSM1310626", "GSM1310627", "GSM1310628", "GSM1310629", "GSM1310630", "GSM1310631", "GSM1310632", "GSM1310633", "GSM1310634", "GSM1310635", "GSM1310636", "GSM1310637", "GSM1310638", "GSM1310639", "GSM1310640", "GSM1310641", "GSM1310642", "GSM1310643", "GSM1310644", "GSM1310645", "GSM1310646", "GSM1310647", "GSM1310648", "GSM1310649", "GSM1310650", "GSM1310651", "GSM1310652", "GSM1310653", "GSM1310654", "GSM1310655", "GSM1310656", "GSM1310657", "GSM1310658", "GSM1310659", "GSM1310660", "GSM1310661", "GSM1310662", "GSM1310663", "GSM1310664", "GSM1310665", "GSM1310666", "GSM1310667", "GSM1310668", "GSM1310669", "GSM1310670", "GSM1310671", "GSM1310672", "GSM1310673", "GSM1310674", "GSM1310675", "GSM1310676", "GSM1310677", "GSM1310678", "GSM1310679", "GSM1310680", "GSM1310681", "GSM1310682", "GSM1310683", "GSM1310684", "GSM1310685", "GSM1310686", "GSM1310687", "GSM1310688", "GSM1310689", "GSM1310690", "GSM1310691", "GSM1310692", "GSM1310693", "GSM1310694", "GSM1310695", "GSM1310696", "GSM1310697", "GSM1310698", "GSM1310699", "GSM1310700", "GSM1310701", "GSM1310702", "GSM1310703", "GSM1310704", "GSM1310705", "GSM1310706", "GSM1310707", "GSM1310708", "GSM1310709", "GSM1310710", "GSM1310711", "GSM1310712", "GSM1310713", "GSM1310714", "GSM1310715", "GSM1310716", "GSM1310717", "GSM1310718", "GSM1310719", "GSM1310720", "GSM1310721", "GSM1310722", "GSM1310723", "GSM1310724", "GSM1310725", "GSM1310726", "GSM1310727", "GSM1310728", "GSM1310729", "GSM1310730"], "sample_count": 161, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Prospective gene expression analysis of  human RNA samples from Hepatocellular Carcinoma in relation with growth rate and survival", "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:GSE98638", "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=GSE98638", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE98638", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2602294", "GSM2602295", "GSM2602296", "GSM2602297", "GSM2602298", "GSM2602299"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Landscape of infiltrating T cells in liver cancer revealed by single-cell sequencing", "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:GSE125449 not downloaded", "asset:data:geo:GSE125449 licence not read", "asset:data:geo:GSE144269 not downloaded", "asset:data:geo:GSE144269 licence not read", "asset:data:geo:GSE14520 not downloaded", "asset:data:geo:GSE14520 licence not read", "asset:data:geo:GSE146115 not downloaded", "asset:data:geo:GSE146115 licence not read", "asset:data:geo:GSE146409 not downloaded", "asset:data:geo:GSE146409 licence not read", "asset:data:geo:GSE166635 not downloaded", "asset:data:geo:GSE166635 licence not read", "asset:data:geo:GSE179795 not downloaded", "asset:data:geo:GSE179795 licence not read", "asset:data:geo:GSE54236 not downloaded", "asset:data:geo:GSE54236 licence not read", "asset:data:geo:GSE98638 not downloaded", "asset:data:geo:GSE98638 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Univariate Cox regression analysis was carried out to assess the impact of CDCA4 on patient prognosis, specifically in LIHC. The association between CDCA4 and overall survival (OS) was investigated using the Kaplan–Meier method."}}, {"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": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "KM"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-5", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "chi-square"}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE144269", "GSE14520", "GSE54236", "GSE98638", "GSE125449", "GSE140228_10X", "GSE140228_Smartseq2", "GSE146115", "GSE146409", "GSE166635", "GSE179795"], "resolved_accessions": ["GSE144269", "GSE14520", "GSE54236", "GSE98638", "GSE125449", "GSE146115", "GSE146409", "GSE166635", "GSE179795"], "statements": ["Data sharing not applicable to this article as no datasets were generated or analyzed during the current study."], "basis": "The paper names GSE144269, GSE14520, GSE54236, GSE98638, GSE125449, GSE146115, GSE146409, GSE166635, GSE179795 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:38701314", "data:geo:GSE125449"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE125449"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:18:01Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13534, "completion_tokens": 4077, "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:38701314", "type": "paper", "label": "pmid:38701314"}, {"id": "source:pmid:38701314", "type": "manuscript", "label": "PMID 38701314 full text"}, {"id": "data:geo:GSE125449", "type": "dataset", "label": "GEO GSE125449"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38701314", "type": "paper", "label": "pmid:38701314"}, {"id": "source:pmid:38701314", "type": "manuscript", "label": "PMID 38701314 full text"}, {"id": "data:geo:GSE125449", "type": "dataset", "label": "GEO GSE125449"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38701314", "type": "extraction", "used": ["source:pmid:38701314"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE125449", "type": "accession_resolution", "used": ["data:geo:GSE125449"], "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:38701314", "parent_hash": "sha256:7ae7815a371914059158c5dec93cd9abb2613921b0a81ae86607e9954ae94343", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE125449 licence not read", "asset:data:geo:GSE125449 not downloaded", "asset:data:geo:GSE144269 licence not read", "asset:data:geo:GSE144269 not downloaded", "asset:data:geo:GSE14520 licence not read", "asset:data:geo:GSE14520 not downloaded", "asset:data:geo:GSE146115 licence not read", "asset:data:geo:GSE146115 not downloaded", "asset:data:geo:GSE146409 licence not read", "asset:data:geo:GSE146409 not downloaded", "asset:data:geo:GSE166635 licence not read", "asset:data:geo:GSE166635 not downloaded", "asset:data:geo:GSE179795 licence not read", "asset:data:geo:GSE179795 not downloaded", "asset:data:geo:GSE54236 licence not read", "asset:data:geo:GSE54236 not downloaded", "asset:data:geo:GSE98638 licence not read", "asset:data:geo:GSE98638 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": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ression levels was conducted through RT-PCR, Western blotting, and immunohistochemistry. CDCA4 exhibited s"], "order_basis": "paper_text_order:1335", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ducted through RT-PCR, Western blotting, and immunohistochemistry. CDCA4 exhibited significant overexpression", "ding RT-PCR (Fig. 14A), WB (Fig. 14B–C), and immunohistochemical analysis (Fig. 14D), we observed significant", "n in Figure 15. (D) RT-PCR, (A-B) WB and (C) immunohistochemical analyses showed that CDCA4 was significantly"], "order_basis": "paper_text_order:1357", "id": "assay:2"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["f CDCA4 The TME is the specific focus of the scRNA-seq database TISCH2 (http://tisch.comp-genomics."], "order_basis": "paper_text_order:5472", "id": "assay:3"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Univariate Cox regression analysis was carried out to assess the impact of CDCA4 on patient prognosis, specifically in LIHC. The association between CDCA4 and overall survival (OS) was investigated using the Kaplan–Meier method."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:34:31+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}}}