{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33732694", "kind": "science-record", "revision": 6, "content_hash": "sha256:86ae0ae1ea733e1b2e78d3b79ba7e2004b3a41458f80719abba4d01f7786819a", "created_at": "2026-11-01T15:41:29Z", "updated_at": "2026-11-01T21:24:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Clinical Significance of a Novel Tumor Progression-Associated Immune Signature in Colorectal Adenocarcinoma.", "doi": "10.3389/fcell.2021.625212", "pmid": "33732694", "authors": ["Rui Mao", "Fan Yang", "Zheng Wang", "Chenxin Xu", "Qian Liu", "Yanjun Liu", "Tongtong Zhang"], "journal": "Frontiers in cell and developmental biology", "year": 2021, "abstract": "BACKGROUND: Some colorectal adenocarcinoma (CRC) patients are susceptible to recurrence, and they rapidly progress to advanced cancer stages and have a poor prognosis. There is an urgent need for efficient screening criteria to identify patients who tend to relapse in order to treat them earlier and more systematically.\nMETHODS: We identified two groups of patients with significantly different outcomes by unsupervised cluster analysis of GSE39582 based on 101 significantly differentially expressed immune genes. To develop an accurate and specific signature based on immune-related genes to predict the recurrence of CRC, a multivariate Cox risk regression model was constructed with a training cohort composed of 519 CRC samples. The model was then validated using 129, 292, and 446 samples in the real-time quantitative reverse transcription PCR (qRT-PCR), test, and validation cohorts, respectively.\nRESULTS: This classification system can also be used to predict the prognosis in clinical subgroups and patients with different mutation states. Four independent datasets, including qRT-PCR and The Cancer Genome Atlas (TCGA), demonstrated that they can also be used to accurately predict the overall survival of CRC patients. Further analysis suggested that high-risk patients were characterized by worse effects of chemotherapy and immunotherapy, as well as lower immune scores. Ultimately, the signature was identified as an independent prognostic factor.\nCONCLUSION: The signature can accurately predict recurrence and overall survival in patients with CRC and may serve as a powerful prognostic tool to further optimize cancer immunotherapy.", "claims": [{"id": "claim-method", "statement": "Next, multivariate Cox regression was applied to identify prognostic signatures with the R packages glment, survminer, and survival.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33732694", "locator": "sections[6] \"Prognostic Evaluation Using the IGBRS\" paragraph 2", "quote": "Next, multivariate Cox regression was applied to identify prognostic signatures with the R packages glment, survminer, and survival."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33732694", "locator": "sections[28] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33732694"], "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:GSE14333"], "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:GSE14333"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33732694", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcell.2021.625212", "sha256": "sha256:40e1a65b97b544d6189555b148f6dfb2ff9836f11e3c099b83826e141af6d02a", "bytes": 72566, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcell.2021.625212", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7959763", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE14333", "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=GSE14333", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14333", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM358341", "GSM358342", "GSM358343", "GSM358344", "GSM358345", "GSM358346", "GSM358347", "GSM358348", "GSM358349", "GSM358350", "GSM358351", "GSM358352", "GSM358353", "GSM358354", "GSM358355", "GSM358356", "GSM358357", "GSM358358", "GSM358359", "GSM358360", "GSM358361", "GSM358362", "GSM358363", "GSM358364", "GSM358365", "GSM358366", "GSM358367", "GSM358368", "GSM358369", "GSM358370", "GSM358371", "GSM358372", "GSM358373", "GSM358374", "GSM358375", "GSM358376", "GSM358377", "GSM358378", "GSM358379", "GSM358380", "GSM358381", "GSM358382", "GSM358383", "GSM358384", "GSM358385", "GSM358386", "GSM358387", "GSM358388", "GSM358389", "GSM358390", "GSM358391", "GSM358392", "GSM358393", "GSM358394", "GSM358395", "GSM358396", "GSM358397", "GSM358398", "GSM358399", "GSM358400", "GSM358401", "GSM358402", "GSM358403", "GSM358404", "GSM358405", "GSM358406", "GSM358407", "GSM358408", "GSM358409", "GSM358410", "GSM358411", "GSM358412", "GSM358413", "GSM358414", "GSM358415", "GSM358416", "GSM358417", "GSM358418", "GSM358419", "GSM358420", "GSM358421", "GSM358422", "GSM358423", "GSM358424", "GSM358425", "GSM358426", "GSM358427", "GSM358428", "GSM358429", "GSM358430", "GSM358431", "GSM358432", "GSM358433", "GSM358434", "GSM358435", "GSM358436", "GSM358437", "GSM358438", "GSM358439", "GSM358440", "GSM358441", "GSM358442", "GSM358443", "GSM358444", "GSM358445", "GSM358446", "GSM358447", "GSM358448", "GSM358449", "GSM358450", "GSM358451", "GSM358452", "GSM358453", "GSM358454", "GSM358455", "GSM358456", "GSM358457", "GSM358458", "GSM358459", "GSM358460", "GSM358461", "GSM358462", "GSM358463", "GSM358464", "GSM358465", "GSM358466", "GSM358467", "GSM358468", "GSM358469", "GSM358470", "GSM358471", "GSM358472", "GSM358473", "GSM358474", "GSM358475", "GSM358476", "GSM358477", "GSM358478", "GSM358479", "GSM358480", "GSM358481", "GSM358482", "GSM358483", "GSM358484", "GSM358485", "GSM358486", "GSM358487", "GSM358488", "GSM358489", "GSM358490", "GSM358491", "GSM358492", "GSM358493", "GSM358494", "GSM358495", "GSM358496", "GSM358497", "GSM358498", "GSM358499", "GSM358500", "GSM358501", "GSM358502", "GSM358503", "GSM358504", "GSM358505", "GSM358506", "GSM358507", "GSM358508", "GSM358509", "GSM358510", "GSM358511", "GSM358512", "GSM358513", "GSM358514", "GSM358515", "GSM358516", "GSM358517", "GSM358518", "GSM358519", "GSM358520", "GSM358521", "GSM358522", "GSM358523", "GSM358524", "GSM358525", "GSM358526", "GSM358527", "GSM358528", "GSM358529", "GSM358530", "GSM358531", "GSM358532", "GSM358533", "GSM358534", "GSM358535", "GSM358536", "GSM358537", "GSM358538", "GSM358539", "GSM358540", "GSM358541", "GSM358542", "GSM358543", "GSM358544", "GSM358545", "GSM358546", "GSM358547", "GSM358548", "GSM358549", "GSM358550", "GSM358551", "GSM358552", "GSM358553", "GSM358554", "GSM358555", "GSM358556", "GSM358557", "GSM358558", "GSM358559", "GSM358560", "GSM358561", "GSM358562", "GSM358563", "GSM358564", "GSM358565", "GSM358566", "GSM358567", "GSM358568", "GSM358569", "GSM358570", "GSM358571", "GSM358572", "GSM358573", "GSM358574", "GSM358575", "GSM358576", "GSM358577", "GSM358578", "GSM358579", "GSM358580", "GSM358581", "GSM358582", "GSM358583", "GSM358584", "GSM358585", "GSM358586", "GSM358587", "GSM358588", "GSM358589", "GSM358590", "GSM358591", "GSM358592", "GSM358593", "GSM358594", "GSM358595", "GSM358596", "GSM358597", "GSM358598", "GSM358599", "GSM358600", "GSM358601", "GSM358602", "GSM358603", "GSM358604", "GSM358605", "GSM358606", "GSM358607", "GSM358608", "GSM358609", "GSM358610", "GSM358611", "GSM358612", "GSM358613", "GSM358614", "GSM358615", "GSM358616", "GSM358617", "GSM358618", "GSM358619", "GSM358620", "GSM358621", "GSM358622", "GSM358623", "GSM358624", "GSM358625", "GSM358626", "GSM358627", "GSM358628", "GSM358629", "GSM358630"], "sample_count": 290, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from 290 primary colorectal cancers", "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:GSE17538", "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=GSE17538", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17538", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM437093", "GSM437094", "GSM437095", "GSM437096", "GSM437097", "GSM437098", "GSM437099", "GSM437100", "GSM437101", "GSM437102", "GSM437103", "GSM437104", "GSM437105", "GSM437106", "GSM437107", "GSM437108", "GSM437109", "GSM437110", "GSM437111", "GSM437112", "GSM437113", "GSM437114", "GSM437115", "GSM437116", "GSM437117", "GSM437118", "GSM437119", "GSM437120", "GSM437121", "GSM437122", "GSM437123", "GSM437124", "GSM437125", "GSM437126", "GSM437127", "GSM437128", "GSM437129", "GSM437130", "GSM437131", "GSM437132", "GSM437133", "GSM437134", "GSM437135", "GSM437136", "GSM437137", "GSM437138", "GSM437139", "GSM437140", "GSM437141", "GSM437142", "GSM437143", "GSM437144", "GSM437145", "GSM437146", "GSM437147", "GSM437148", "GSM437149", "GSM437150", "GSM437151", "GSM437152", "GSM437153", "GSM437154", "GSM437155", "GSM437156", "GSM437157", "GSM437158", "GSM437159", "GSM437160", "GSM437161", "GSM437162", "GSM437163", "GSM437164", "GSM437165", "GSM437166", "GSM437167", "GSM437168", "GSM437169", "GSM437170", "GSM437171", "GSM437172", "GSM437173", "GSM437174", "GSM437175", "GSM437176", "GSM437177", "GSM437178", "GSM437179", "GSM437180", "GSM437181", "GSM437182", "GSM437183", "GSM437184", "GSM437185", "GSM437186", "GSM437187", "GSM437188", "GSM437189", "GSM437190", "GSM437191", "GSM437192", "GSM437193", "GSM437194", "GSM437195", "GSM437196", "GSM437197", "GSM437198", "GSM437199", "GSM437200", "GSM437201", "GSM437202", "GSM437203", "GSM437204", "GSM437205", "GSM437206", "GSM437207", "GSM437208", "GSM437209", "GSM437210", "GSM437211", "GSM437212", "GSM437213", "GSM437214", "GSM437215", "GSM437216", "GSM437217", "GSM437218", "GSM437219", "GSM437220", "GSM437221", "GSM437222", "GSM437223", "GSM437224", "GSM437225", "GSM437226", "GSM437227", "GSM437228", "GSM437229", "GSM437230", "GSM437231", "GSM437232", "GSM437233", "GSM437234", "GSM437235", "GSM437236", "GSM437237", "GSM437238", "GSM437239", "GSM437240", "GSM437241", "GSM437242", "GSM437243", "GSM437244", "GSM437245", "GSM437246", "GSM437247", "GSM437248", "GSM437249", "GSM437250", "GSM437251", "GSM437252", "GSM437253", "GSM437254", "GSM437255", "GSM437256", "GSM437257", "GSM437258", "GSM437259", "GSM437260", "GSM437261", "GSM437262", "GSM437263", "GSM437264", "GSM437265", "GSM437266", "GSM437267", "GSM437268", "GSM437269", "GSM437270", "GSM437271", "GSM437272", "GSM437273", "GSM437274", "GSM437275", "GSM437276", "GSM437277", "GSM437278", "GSM437279", "GSM437280", "GSM437281", "GSM437282", "GSM437283", "GSM437284", "GSM437285", "GSM437286", "GSM437287", "GSM437288", "GSM437289", "GSM437290", "GSM437291", "GSM437292", "GSM437293", "GSM437294", "GSM437295", "GSM437296", "GSM437297", "GSM437298", "GSM437299", "GSM437300", "GSM437301", "GSM437302", "GSM437303", "GSM437304", "GSM437305", "GSM437306", "GSM437307", "GSM437308", "GSM437309", "GSM437310", "GSM437311", "GSM437312", "GSM437313", "GSM437314", "GSM437315", "GSM437316", "GSM437317", "GSM437318", "GSM437319", "GSM437320", "GSM437321", "GSM437322", "GSM437323", "GSM437324", "GSM472192", "GSM472193", "GSM472194", "GSM472195", "GSM472196", "GSM472197", "GSM472198", "GSM472199", "GSM472200", "GSM472201", "GSM472202", "GSM472203"], "sample_count": 244, "group_sizes": null, "group_sizes_basis": null, "platform": "570;1261", "taxon": "Mus musculus; Homo sapiens", "title": "Experimentally Derived Metastasis Gene Expression Profile Predicts Recurrence and Death in Colon Cancer 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:GSE33113", "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=GSE33113", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33113", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1100477", "GSM1100478", "GSM1100479", "GSM1100480", "GSM1100481", "GSM1100482", "GSM820048", "GSM820049", "GSM820050", "GSM820051", "GSM820052", "GSM820053", "GSM820054", "GSM820055", "GSM820056", "GSM820057", "GSM820058", "GSM820059", "GSM820060", "GSM820061", "GSM820062", "GSM820063", "GSM820064", "GSM820065", "GSM820066", "GSM820067", "GSM820068", "GSM820069", "GSM820070", "GSM820071", "GSM820072", "GSM820073", "GSM820074", "GSM820075", "GSM820076", "GSM820077", "GSM820078", "GSM820079", "GSM820080", "GSM820081", "GSM820082", "GSM820083", "GSM820084", "GSM820085", "GSM820086", "GSM820087", "GSM820088", "GSM820089", "GSM820090", "GSM820091", "GSM820092", "GSM820093", "GSM820094", "GSM820095", "GSM820096", "GSM820097", "GSM820098", "GSM820099", "GSM820100", "GSM820101", "GSM820102", "GSM820103", "GSM820104", "GSM820105", "GSM820106", "GSM820107", "GSM820108", "GSM820109", "GSM820110", "GSM820111", "GSM820112", "GSM820113", "GSM820114", "GSM820115", "GSM820116", "GSM820117", "GSM820118", "GSM820119", "GSM820120", "GSM820121", "GSM820122", "GSM820123", "GSM820124", "GSM820125", "GSM820126", "GSM820127", "GSM820128", "GSM820129", "GSM820130", "GSM820131", "GSM820132", "GSM820133", "GSM820134", "GSM820135", "GSM820136", "GSM820137"], "sample_count": 96, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "AMC colon cancer AJCCII", "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:GSE35640", "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=GSE35640", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE35640", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM872328", "GSM872329", "GSM872330", "GSM872331", "GSM872332", "GSM872333", "GSM872334", "GSM872335", "GSM872336", "GSM872337", "GSM872338", "GSM872339", "GSM872340", "GSM872341", "GSM872342", "GSM872343", "GSM872344", "GSM872345", "GSM872346", "GSM872347", "GSM872348", "GSM872349", "GSM872350", "GSM872351", "GSM872352", "GSM872353", "GSM872354", "GSM872355", "GSM872356", "GSM872357", "GSM872358", "GSM872359", "GSM872360", "GSM872361", "GSM872362", "GSM872363", "GSM872364", "GSM872365", "GSM872366", "GSM872367", "GSM872368", "GSM872369", "GSM872370", "GSM872371", "GSM872372", "GSM872373", "GSM872374", "GSM872375", "GSM872376", "GSM872377", "GSM872378", "GSM872379", "GSM872380", "GSM872381", "GSM872382", "GSM872383", "GSM872384", "GSM872385", "GSM872386", "GSM872387", "GSM872388", "GSM872389", "GSM872390", "GSM872391", "GSM872392"], "sample_count": 65, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Identification of a predictive gene signature to recMAGE A3 antigen-specific cancer immunotherapy in metastatic melanoma and non-small-cell lung cancer", "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:GSE37892", "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=GSE37892", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37892", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM929494", "GSM929495", "GSM929496", "GSM929497", "GSM929498", "GSM929499", "GSM929500", "GSM929501", "GSM929502", "GSM929503", "GSM929504", "GSM929505", "GSM929506", "GSM929507", "GSM929508", "GSM929509", "GSM929510", "GSM929511", "GSM929512", "GSM929513", "GSM929514", "GSM929515", "GSM929516", "GSM929517", "GSM929518", "GSM929519", "GSM929520", "GSM929521", "GSM929522", "GSM929523", "GSM929524", "GSM929525", "GSM929526", "GSM929527", "GSM929528", "GSM929529", "GSM929530", "GSM929531", "GSM929532", "GSM929533", "GSM929534", "GSM929535", "GSM929536", "GSM929537", "GSM929538", "GSM929539", "GSM929540", "GSM929541", "GSM929542", "GSM929543", "GSM929544", "GSM929545", "GSM929546", "GSM929547", "GSM929548", "GSM929549", "GSM929550", "GSM929551", "GSM929552", "GSM929553", "GSM929554", "GSM929555", "GSM929556", "GSM929557", "GSM929558", "GSM929559", "GSM929560", "GSM929561", "GSM929562", "GSM929563", "GSM929564", "GSM929565", "GSM929566", "GSM929567", "GSM929568", "GSM929569", "GSM929570", "GSM929571", "GSM929572", "GSM929573", "GSM929574", "GSM929575", "GSM929576", "GSM929577", "GSM929578", "GSM929579", "GSM929580", "GSM929581", "GSM929582", "GSM929583", "GSM929584", "GSM929585", "GSM929586", "GSM929587", "GSM929588", "GSM929589", "GSM929590", "GSM929591", "GSM929592", "GSM929593", "GSM929594", "GSM929595", "GSM929596", "GSM929597", "GSM929598", "GSM929599", "GSM929600", "GSM929601", "GSM929602", "GSM929603", "GSM929604", "GSM929605", "GSM929606", "GSM929607", "GSM929608", "GSM929609", "GSM929610", "GSM929611", "GSM929612", "GSM929613", "GSM929614", "GSM929615", "GSM929616", "GSM929617", "GSM929618", "GSM929619", "GSM929620", "GSM929621", "GSM929622", "GSM929623"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "A seven-gene signature aggregates a subgroup of stage II colon cancers with stage III.", "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:GSE38832", "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=GSE38832", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38832", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM950411", "GSM950412", "GSM950413", "GSM950414", "GSM950415", "GSM950416", "GSM950417", "GSM950418", "GSM950419", "GSM950420", "GSM950421", "GSM950422", "GSM950423", "GSM950424", "GSM950425", "GSM950426", "GSM950427", "GSM950428", "GSM950429", "GSM950430", "GSM950431", "GSM950432", "GSM950433", "GSM950434", "GSM950435", "GSM950436", "GSM950437", "GSM950438", "GSM950439", "GSM950440", "GSM950441", "GSM950442", "GSM950443", "GSM950444", "GSM950445", "GSM950446", "GSM950447", "GSM950448", "GSM950449", "GSM950450", "GSM950451", "GSM950452", "GSM950453", "GSM950454", "GSM950455", "GSM950456", "GSM950457", "GSM950458", "GSM950459", "GSM950460", "GSM950461", "GSM950462", "GSM950463", "GSM950464", "GSM950465", "GSM950466", "GSM950467", "GSM950468", "GSM950469", "GSM950470", "GSM950471", "GSM950472", "GSM950473", "GSM950474", "GSM950475", "GSM950476", "GSM950477", "GSM950478", "GSM950479", "GSM950480", "GSM950481", "GSM950482", "GSM950483", "GSM950484", "GSM950485", "GSM950486", "GSM950487", "GSM950488", "GSM950489", "GSM950490", "GSM950491", "GSM950492", "GSM950493", "GSM950494", "GSM950495", "GSM950496", "GSM950497", "GSM950498", "GSM950499", "GSM950500", "GSM950501", "GSM950502", "GSM950503", "GSM950504", "GSM950505", "GSM950506", "GSM950507", "GSM950508", "GSM950509", "GSM950510", "GSM950511", "GSM950512", "GSM950513", "GSM950514", "GSM950515", "GSM950516", "GSM950517", "GSM950518", "GSM950519", "GSM950520", "GSM950521", "GSM950522", "GSM950523", "GSM950524", "GSM950525", "GSM950526", "GSM950527", "GSM950528", "GSM950529", "GSM950530", "GSM950531", "GSM950532"], "sample_count": 122, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "NFAT transcriptional activity is associated with metastatic capacity in colon cancer", "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:GSE63557", "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=GSE63557", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63557", "version": null, "note": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1552218", "GSM1552219", "GSM1552220", "GSM1552221", "GSM1552222", "GSM1552223", "GSM1552224", "GSM1552225", "GSM1552226", "GSM1552227", "GSM1552228", "GSM1552229", "GSM1552230", "GSM1552231", "GSM1552232", "GSM1552233", "GSM1552234", "GSM1552235", "GSM1552236", "GSM1552237", "GSM1552238", "GSM1552239", "GSM1552240", "GSM1552241", "GSM1552242", "GSM1552243", "GSM1552244", "GSM1552245", "GSM1552246", "GSM1552247"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "19103", "taxon": "Mus musculus", "title": "Gene expression patterns in responding versus non-responding AB1-HA tumors from mice during immunotherapy", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33732694:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0781941fdeeb601449aa458dc09eec4f23d75bbc4d6b40e5e606f7d812a21173", "bytes": 3299, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#T1", "version": null, "note": "Univariable and multivariable Cox regression analysis of IGBRS and characteristics with RFS and OS in GSE39582.", "structure": {"pmcid": "PMC7959763", "section_index": 24, "section_title": "Identification of IGBRS as an Independent Risk Factor for CRC Patients", "row_count": 28, "column_count": 13}, "table": {"label": "TABLE 1", "caption": "Univariable and multivariable Cox regression analysis of IGBRS and characteristics with RFS and OS in GSE39582.", "rows": [["Variable", "Relapse-free survival", "Overall survival"], ["", "Univariate cox", "Multivariate cox", "Univariate cox", "Multivariate cox"], ["", "p-value", "HR", "95% CI", "p-value", "HR", "95% CI", "p-value", "HR", "95% CI", "p-value", "HR", "95% CI"], ["Age", "", "", "", "", "", "", "", "", "", "", "", ""], [">65 Vs. ≤65 (reference)", "0.9150", "1.0180", "0.7296–1.4210", "0.4706", "1.5273", "0.8056–1.6270", "0.0138", "1.4620", "1.0800–1.9780", "<0.0001", "1.7394", "1.2626–2.3960"], ["Sex", "", "", "", "", "", "", "", "", "", "", "", ""], ["Male Vs. female (reference)", "0.1410", "1.2840", "0.9206–1.7900", "0.0968", "0.9815", "0.9482–1.9160", "0.0684", "1.3100", "0.9799–1.7500", "0.0758", "1.3111", "0.9722–1.7680"], ["TNM stage", "", "", "", "", "", "", "", "", "", "", "", ""], ["I (reference)", "", "", "", "", "", "", "", "", "", "", "", ""], ["II", "0.0393", "7.9980", "1.1070–57.7800", "0.0814", "5.8670", "0.7998–42.6740", "0.2980", "1.5550", "0.6772–3.5700", "0.4615", "1.3804", "0.5853–3.2560"], ["III", "0.0054", "16.3930", "2.2810–117.8100", "0.0239", "10.1700", "1.3776–73.1500", "0.1280", "1.9130", "0.8299–4.4120", "0.2490", "1.6627", "0.7005–3.9460"], ["IV", "0.0091", "15.3930", "1.9900–127.5000", "0.0178", "12.7800", "1.5563–103.7330", "<0.0001", "7.8110", "3.3021–18.4750", "<0.0001", "7.1807", "2.9121–17.060"], ["Location", "", "", "", "", "", "", "", "", "", "", "", ""], ["Proximal vs. distal (reference)", "0.8416", "0.3200", "0.5993–1.1820", "0.2340", "0.7871", "0.5333–1.1690", "0.6510", "1.0700", "0.7988–1.4320", "0.9041", "1.0206", "0.7323–1.4230"], ["MMR status", "", "", "", "", "", "", "", "", "", "", "", ""], ["dMMR Vs. pMMR (reference)", "0.0112", "0.4345", "0.2282–0.8272", "0.6168", "0.8076", "0.3498–1.8600", "0.3038", "0.7739", "0.4748–1.2610", "0.6928", "1.1328", "0.6103–2.1020"], ["CIMP", "", "", "", "", "", "", "", "", "", "", "", ""], ["Positive vs. negative (reference)", "0.4220", "0.8092", "0.4827–1.3570", "0.7896", "0.9077", "0.4454–1.8470", "0.7860", "1.0570", "0.7077–1.5790", "0.4663", "1.2375", "0.6975–2.1960"], ["CIN", "", "", "", "", "", "", "", "", "", "", "", ""], ["Positive vs. negative (reference)", "0.3020", "1.3170", "0.7808–2.2220", "0.6872", "0.8826", "1.0516–4.6260", "0.1880", "0.7767", "0.5331–1.1320", "0.3441", "0.8138", "0.5310–1.2470"], ["TP53 status", "", "", "", "", "", "", "", "", "", "", "", ""], ["MUT vs. WT (reference)", "0.1570", "1.3223", "0.8984–1.9460", "0.5764", "1.1240", "0.7455–1.6930", "0.3140", "1.1960", "0.8439–1.6960", "0.4809", "1.1417", "0.7898–1.6510"], ["KRAS status", "", "", "", "", "", "", "", "", "", "", "", ""], ["MUT vs. WT (reference)", "0.0774", "1.3550", "0.9672–1.8980", "0.0245", "1.5410", "1.0567–2.2450", "0.0377", "1.3597", "1.0176–1.8170", "0.1583", "1.2646", "0.9127–1.7520"], ["BRAF status", "", "", "", "", "", "", "", "", "", "", "", ""], ["MUT Vs. WT (reference)", "0.9404", "1.0240", "0.5504–1.9050", "0.1250", "2.0880", "0.8161–5.3380", "0.6920", "1.1098", "0.6628–1.8580", "0.5860", "0.8085", "0.3761–1.7380"], ["Risk score", "", "", "", "", "", "", "", "", "", "", "", ""], ["Increasing", "<0.0001", "2.8280", "1.9780–4.0420", "<0.0001", "2.7080", "1.8515–3.9480", "<0.0001", "2.5470", "1.8820–3.4470", "<0.0001", "2.4176", "1.7628–3.3160"]], "row_count": 28, "column_count": 13, "numeric_cells": 162, "header_rows": 3, "locator": "section[24]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE14333 not downloaded", "asset:data:geo:GSE14333 licence not read", "asset:data:geo:GSE17538 not downloaded", "asset:data:geo:GSE17538 licence not read", "asset:data:geo:GSE33113 not downloaded", "asset:data:geo:GSE33113 licence not read", "asset:data:geo:GSE35640 not downloaded", "asset:data:geo:GSE35640 licence not read", "asset:data:geo:GSE37892 not downloaded", "asset:data:geo:GSE37892 licence not read", "asset:data:geo:GSE38832 not downloaded", "asset:data:geo:GSE38832 licence not read", "asset:data:geo:GSE63557 not downloaded", "asset:data:geo:GSE63557 licence not read"]}, "analysis": {"state": "complete", "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": "Next, multivariate Cox regression was applied to identify prognostic signatures with the R packages glment, survminer, and survival."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["GSE14333", "GSE17538", "GSE33113", "GSE37892", "GSE38832", "GSE35640", "GSE63557", "and GSE39582"], "resolved_accessions": ["GSE14333", "GSE17538", "GSE33113", "GSE37892", "GSE38832", "GSE35640", "GSE63557"], "statements": ["The original contributions generated for this study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."], "basis": "The paper names GSE14333, GSE17538, GSE33113, GSE37892, GSE38832, GSE35640, GSE63557 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": ["cox_ph"], "assets": ["source:pmid:33732694", "data:geo:GSE14333", "asset:table:pmid:33732694:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE14333"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:28:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 57225, "completion_tokens": 2016, "cached_tokens": 792}}, "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:33732694", "type": "paper", "label": "pmid:33732694"}, {"id": "source:pmid:33732694", "type": "manuscript", "label": "PMID 33732694 full text"}, {"id": "data:geo:GSE14333", "type": "dataset", "label": "GEO GSE14333"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33732694", "type": "paper", "label": "pmid:33732694"}, {"id": "source:pmid:33732694", "type": "manuscript", "label": "PMID 33732694 full text"}, {"id": "data:geo:GSE14333", "type": "dataset", "label": "GEO GSE14333"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33732694", "type": "extraction", "used": ["source:pmid:33732694"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE14333", "type": "accession_resolution", "used": ["data:geo:GSE14333"], "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:33732694", "parent_hash": "sha256:3380e3042c0e013dbd7b926c10375767515c90727e29f76e18f17a4aef2d4626", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE14333 licence not read", "asset:data:geo:GSE14333 not downloaded", "asset:data:geo:GSE17538 licence not read", "asset:data:geo:GSE17538 not downloaded", "asset:data:geo:GSE33113 licence not read", "asset:data:geo:GSE33113 not downloaded", "asset:data:geo:GSE35640 licence not read", "asset:data:geo:GSE35640 not downloaded", "asset:data:geo:GSE37892 licence not read", "asset:data:geo:GSE37892 not downloaded", "asset:data:geo:GSE38832 licence not read", "asset:data:geo:GSE38832 not downloaded", "asset:data:geo:GSE63557 licence not read", "asset:data:geo:GSE63557 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["g 129, 292, and 446 samples in the real-time quantitative reverse transcription PCR (qRT-PCR), test, and validation cohorts, res"], "order_basis": "paper_text_order:878", "id": "assay:1"}, {"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": ["Next, multivariate Cox regression was applied to identify prognostic signatures with the R packages glment, survminer, and survival."], "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":"2026-11-04T02:37:21+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}}}