{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35626146", "kind": "science-record", "revision": 5, "content_hash": "sha256:6a036747e980cad595f148b80b4b6a861d53d862f54495b378ff58dbf2780352", "created_at": "2026-11-01T18:14:33Z", "updated_at": "2026-11-01T22:49:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene Expression Monotonicity across Bladder Cancer Stages Informs on the Molecular Pathogenesis and Identifies a Prognostic Eight-Gene Signature.", "doi": "10.3390/cancers14102542", "pmid": "35626146", "authors": ["Rafael Stroggilos", "Maria Frantzi", "Jerome Zoidakis", "Marika Mokou", "Napoleon Moulavasilis", "Emmanouil Mavrogeorgis", "Anna Melidi", "Manousos Makridakis", "Konstantinos Stravodimos", "Maria G Roubelakis", "Harald Mischak", "Antonia Vlahou"], "journal": "Cancers", "year": 2022, "abstract": "Despite advancements in molecular classification, tumor stage and grade still remain the most relevant prognosticators used by clinicians to decide on patient management. Here, we leverage publicly available data to characterize bladder cancer (BLCA)'s stage biology based on increased sample sizes, identify potential therapeutic targets, and extract putative biomarkers. A total of 1135 primary BLCA transcriptomes from 12 microarray studies were compiled in a meta-cohort and analyzed for monotonal alterations in pathway activities, gene expression, and co-expression patterns with increasing stage (Ta-T1-T2-T3-T4), starting from the non-malignant tumor-adjacent urothelium. The TCGA-2017 and IMvigor-210 RNA-Seq data were used to validate our findings. Wnt, MTORC1 signaling, and MYC activity were monotonically increased with increasing stage, while an opposite trend was detected for the catabolism of fatty acids, circadian clock genes, and the metabolism of heme. Co-expression network analysis highlighted stage- and cell-type-specific genes of potentially synergistic therapeutic value. An eight-gene signature, consisting of the genes AKAP7, ANLN, CBX7, CDC14B, ENO1, GTPBP4, MED19, and ZFP2, had independent prognostic value in both the discovery and validation sets. This novel eight-gene signature may increase the granularity of current risk-to-progression estimators.", "claims": [{"id": "claim-method", "statement": "Cox proportional hazards regression was performed with the packages survminer and survival, and statistical significance was determined via the log-rank method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35626146", "locator": "sections[2] \"2. Materials and Methods\" paragraph 12", "quote": "Cox proportional hazards regression was performed with the packages survminer and survival, and statistical significance was determined via the log-rank method."}], "state": "complete"}, {"id": "claim-data-access", "statement": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35626146", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Results demonstrate tumor dependencies on specific cell-cycle and metabolic microprocesses, and highlight an eight-gene signature capable of prognosing 5-year outcomes in both the discovery and validation sets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35626146", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Results demonstrate tumor dependencies on specific cell-cycle and metabolic microprocesses, and highlight an eight-gene signature capable of prognosing 5-year outcomes in both the discovery and validation sets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Results demonstrate tumor dependencies on specific cell-cycle and metabolic microprocesses, and highlight an eight-gene signature capable of prognosing 5-year outcomes in both the discovery and validation sets.", "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:35626146"], "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:E-MTAB-1940"], "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:E-MTAB-1940"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35626146", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers14102542", "sha256": "sha256:f4498c916479d9b8509c20d21f496270f8c3b2cee9bba556dd33f031f4e61bca", "bytes": 78979, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers14102542", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9140126", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-1940", "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=E-MTAB-1940", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-1940", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T18:06:51Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE104922", "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=GSE104922", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE104922", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2810041", "GSM2810042", "GSM2810043", "GSM2810044", "GSM2810045", "GSM2810046", "GSM2810047", "GSM2810048", "GSM2810049", "GSM2810050", "GSM2810051", "GSM2810052", "GSM2810053", "GSM2810054", "GSM2810055", "GSM2810056", "GSM2810057", "GSM2810058", "GSM2810059", "GSM2810060", "GSM2810061", "GSM2810062", "GSM2810063", "GSM2810064", "GSM2810065", "GSM2810066", "GSM2810067", "GSM2810068", "GSM2810069", "GSM2810070", "GSM2810071", "GSM2810072", "GSM2810073", "GSM2810074", "GSM2810075", "GSM2810076", "GSM2810077", "GSM2810078", "GSM2810079", "GSM2810080", "GSM2810081"], "sample_count": 41, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Molecular subtype classification of urothelial carcinoma in Lynch syndrome", "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:GSE121711", "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=GSE121711", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE121711", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3444310", "GSM3444311", "GSM3444312", "GSM3444313", "GSM3444314", "GSM3444315", "GSM3444316", "GSM3444317", "GSM3444318", "GSM3444319", "GSM3444320", "GSM3444321", "GSM3444322", "GSM3444323", "GSM3444324", "GSM3444325", "GSM3444326", "GSM3444327"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "17586", "taxon": "Homo sapiens", "title": "Integrative metabolomic and transcriptomic analysis for the non-invasive study of bladder 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:GSE128959", "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=GSE128959", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE128959", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3688992", "GSM3688993", "GSM3688994", "GSM3688995", "GSM3688996", "GSM3688997", "GSM3688998", "GSM3688999", "GSM3689000", "GSM3689001", "GSM3689002", "GSM3689003", "GSM3689004", "GSM3689005", "GSM3689006", "GSM3689007", "GSM3689008", "GSM3689009", "GSM3689010", "GSM3689011", "GSM3689012", "GSM3689013", "GSM3689014", "GSM3689015", "GSM3689016", "GSM3689017", "GSM3689018", "GSM3689019", "GSM3689020", "GSM3689021", "GSM3689022", "GSM3689023", "GSM3689024", "GSM3689025", "GSM3689026", "GSM3689027", "GSM3689028", "GSM3689029", "GSM3689030", "GSM3689031", "GSM3689032", "GSM3689033", "GSM3689034", "GSM3689035", "GSM3689036", "GSM3689037", "GSM3689038", "GSM3689039", "GSM3689040", "GSM3689041", "GSM3689042", "GSM3689043", "GSM3689044", "GSM3689045", "GSM3689046", "GSM3689047", "GSM3689048", "GSM3689049", "GSM3689050", "GSM3689051", "GSM3689052", "GSM3689053", "GSM3689054", "GSM3689055", "GSM3689056", "GSM3689057", "GSM3689058", "GSM3689059", "GSM3689060", "GSM3689061", "GSM3689062", "GSM3689063", "GSM3689064", "GSM3689065", "GSM3689066", "GSM3689067", "GSM3689068", "GSM3689069", "GSM3689070", "GSM3689071", "GSM3689072", "GSM3689073", "GSM3689074", "GSM3689075", "GSM3689076", "GSM3689077", "GSM3689078", "GSM3689079", "GSM3689080", "GSM3689081", "GSM3689082", "GSM3689083", "GSM3689084", "GSM3689085", "GSM3689086", "GSM3689087", "GSM3689088", "GSM3689089", "GSM3689090", "GSM3689091", "GSM3689092", "GSM3689093", "GSM3689094", "GSM3689095", "GSM3689096", "GSM3689097", "GSM3689098", "GSM3689099", "GSM3689100", "GSM3689101", "GSM3689102", "GSM3689103", "GSM3689104", "GSM3689105", "GSM3689106", "GSM3689107", "GSM3689108", "GSM3689109", "GSM3689110", "GSM3689111", "GSM3689112", "GSM3689113", "GSM3689114", "GSM3689115", "GSM3689116", "GSM3689117", "GSM3689118", "GSM3689119", "GSM3689120", "GSM3689121", "GSM3689122", "GSM3689123", "GSM3689124", "GSM3689125", "GSM3689126", "GSM3689127", "GSM3689128", "GSM3689129", "GSM3689130", "GSM3689131", "GSM3689132", "GSM3689133", "GSM3689134", "GSM3689135", "GSM3689136", "GSM3689137", "GSM3689138", "GSM3689139", "GSM3689140", "GSM3689141", "GSM3689142", "GSM3689143", "GSM3689144", "GSM3689145", "GSM3689146", "GSM3689147", "GSM3689148", "GSM3689149", "GSM3689150", "GSM3689151", "GSM3689152", "GSM3689153", "GSM3689154", "GSM3689155", "GSM3689156", "GSM3689157", "GSM3689158", "GSM3689159", "GSM3689160", "GSM3689161", "GSM3689162", "GSM3689163", "GSM3689164", "GSM3689165", "GSM3689166", "GSM3689167", "GSM3689168", "GSM3689169", "GSM3689170", "GSM3689171", "GSM3689172", "GSM3689173", "GSM3689174", "GSM3689175", "GSM3689176", "GSM3689177", "GSM3689178", "GSM3689179", "GSM3689180", "GSM3689181", "GSM3689182", "GSM3689183", "GSM3689184", "GSM3689185", "GSM3689186", "GSM3689187", "GSM3689188", "GSM3689189", "GSM3689190", "GSM3689191"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Molecular changes during progression from early stage to advanced urothelial 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:GSE13507", "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=GSE13507", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13507", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM340537", "GSM340538", "GSM340539", "GSM340540", "GSM340541", "GSM340542", "GSM340543", "GSM340544", "GSM340545", "GSM340546", "GSM340547", "GSM340548", "GSM340549", "GSM340550", "GSM340551", "GSM340552", "GSM340553", "GSM340554", "GSM340555", "GSM340556", "GSM340557", "GSM340558", "GSM340559", "GSM340560", "GSM340561", "GSM340562", "GSM340563", "GSM340564", "GSM340565", "GSM340566", "GSM340567", "GSM340568", "GSM340569", "GSM340570", "GSM340571", "GSM340572", "GSM340573", "GSM340574", "GSM340575", "GSM340576", "GSM340577", "GSM340578", "GSM340579", "GSM340580", "GSM340581", "GSM340582", "GSM340583", "GSM340584", "GSM340585", "GSM340586", "GSM340587", "GSM340588", "GSM340589", "GSM340590", "GSM340591", "GSM340592", "GSM340593", "GSM340594", "GSM340595", "GSM340596", "GSM340597", "GSM340598", "GSM340599", "GSM340600", "GSM340601", "GSM340602", "GSM340603", "GSM340604", "GSM340605", "GSM340606", "GSM340607", "GSM340608", "GSM340609", "GSM340610", "GSM340611", "GSM340612", "GSM340613", "GSM340614", "GSM340615", "GSM340616", "GSM340617", "GSM340618", "GSM340619", "GSM340620", "GSM340621", "GSM340622", "GSM340623", "GSM340624", "GSM340625", "GSM340626", "GSM340627", "GSM340628", "GSM340629", "GSM340630", "GSM340631", "GSM340632", "GSM340633", "GSM340634", "GSM340635", "GSM340636", "GSM340637", "GSM340638", "GSM340639", "GSM340640", "GSM340641", "GSM340642", "GSM340643", "GSM340644", "GSM340645", "GSM340646", "GSM340647", "GSM340648", "GSM340649", "GSM340650", "GSM340651", "GSM340652", "GSM340653", "GSM340654", "GSM340655", "GSM340656", "GSM340657", "GSM340658", "GSM340659", "GSM340660", "GSM340661", "GSM340662", "GSM340663", "GSM340664", "GSM340665", "GSM340666", "GSM340667", "GSM340668", "GSM340669", "GSM340670", "GSM340671", "GSM340672", "GSM340673", "GSM340674", "GSM340675", "GSM340676", "GSM340677", "GSM340678", "GSM340679", "GSM340680", "GSM340681", "GSM340682", "GSM340683", "GSM340684", "GSM340685", "GSM340686", "GSM340687", "GSM340688", "GSM340689", "GSM340690", "GSM340691", "GSM340692", "GSM340693", "GSM340694", "GSM340695", "GSM340696", "GSM340697", "GSM340698", "GSM340699", "GSM340700", "GSM340701", "GSM340702", "GSM340703", "GSM340704", "GSM340705", "GSM340706", "GSM340707", "GSM340708", "GSM340709", "GSM340710", "GSM340711", "GSM340712", "GSM340713", "GSM340714", "GSM340715", "GSM340716", "GSM340717", "GSM340718", "GSM340719", "GSM340720", "GSM340721", "GSM340722", "GSM340723", "GSM340724", "GSM340725", "GSM340726", "GSM340727", "GSM340728", "GSM340729", "GSM340730", "GSM340731", "GSM340732", "GSM340733", "GSM340734", "GSM340735", "GSM340736", "GSM340737", "GSM340738", "GSM340739", "GSM340740", "GSM340741", "GSM340742", "GSM340743", "GSM340744", "GSM340745", "GSM340746", "GSM340747", "GSM340748", "GSM340749", "GSM340750", "GSM340751", "GSM340752", "GSM340753", "GSM340754", "GSM340755", "GSM340756", "GSM340757", "GSM340758", "GSM340759", "GSM340760", "GSM340761", "GSM340762", "GSM340763", "GSM340764", "GSM340765", "GSM340766", "GSM340767", "GSM340768", "GSM340769", "GSM340770", "GSM340771", "GSM340772", "GSM340773", "GSM340774", "GSM340775", "GSM340776", "GSM340777", "GSM340778", "GSM340779", "GSM340780", "GSM340781", "GSM340782", "GSM340783", "GSM340784", "GSM340785", "GSM340786", "GSM340787", "GSM340788", "GSM340789", "GSM340790", "GSM340791", "GSM340792"], "sample_count": 256, "group_sizes": null, "group_sizes_basis": null, "platform": "6102", "taxon": "Homo sapiens", "title": "Predective Value of Prognosis-Related Gene Expression Study in Primary Bladder 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:GSE31684", "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=GSE31684", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31684", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM786491", "GSM786492", "GSM786493", "GSM786494", "GSM786495", "GSM786496", "GSM786497", "GSM786498", "GSM786499", "GSM786500", "GSM786501", "GSM786502", "GSM786503", "GSM786504", "GSM786505", "GSM786506", "GSM786507", "GSM786508", "GSM786509", "GSM786510", "GSM786511", "GSM786512", "GSM786513", "GSM786514", "GSM786515", "GSM786516", "GSM786517", "GSM786518", "GSM786519", "GSM786520", "GSM786521", "GSM786522", "GSM786523", "GSM786524", "GSM786525", "GSM786526", "GSM786527", "GSM786528", "GSM786529", "GSM786530", "GSM786531", "GSM786532", "GSM786533", "GSM786534", "GSM786535", "GSM786536", "GSM786537", "GSM786538", "GSM786539", "GSM786540", "GSM786541", "GSM786542", "GSM786543", "GSM786544", "GSM786545", "GSM786546", "GSM786547", "GSM786548", "GSM786549", "GSM786550", "GSM786551", "GSM786552", "GSM786553", "GSM786554", "GSM786555", "GSM786556", "GSM786557", "GSM786558", "GSM786559", "GSM786560", "GSM786561", "GSM786562", "GSM786563", "GSM786564", "GSM786565", "GSM786566", "GSM786567", "GSM786568", "GSM786569", "GSM786570", "GSM786571", "GSM786572", "GSM786573", "GSM786574", "GSM786575", "GSM786576", "GSM786577", "GSM786578", "GSM786579", "GSM786580", "GSM786581", "GSM786582", "GSM786583"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Combination of a novel gene expression signature with a clinical nomogram improves the prediction of survival in high-risk bladder 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:GSE48075", "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=GSE48075", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48075", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1167333", "GSM1167334", "GSM1167335", "GSM1167336", "GSM1167337", "GSM1167338", "GSM1167339", "GSM1167340", "GSM1167341", "GSM1167342", "GSM1167343", "GSM1167344", "GSM1167345", "GSM1167346", "GSM1167347", "GSM1167348", "GSM1167349", "GSM1167350", "GSM1167351", "GSM1167352", "GSM1167353", "GSM1167354", "GSM1167355", "GSM1167356", "GSM1167357", "GSM1167358", "GSM1167359", "GSM1167360", "GSM1167361", "GSM1167362", "GSM1167363", "GSM1167364", "GSM1167365", "GSM1167366", "GSM1167367", "GSM1167368", "GSM1167369", "GSM1167370", "GSM1167371", "GSM1167372", "GSM1167373", "GSM1167374", "GSM1167375", "GSM1167376", "GSM1167377", "GSM1167378", "GSM1167379", "GSM1167380", "GSM1167381", "GSM1167382", "GSM1167383", "GSM1167384", "GSM1167385", "GSM1167386", "GSM1167387", "GSM1167388", "GSM1167389", "GSM1167390", "GSM1167391", "GSM1167392", "GSM1167393", "GSM1167394", "GSM1167395", "GSM1167396", "GSM1167397", "GSM1167398", "GSM1167399", "GSM1167400", "GSM1167401", "GSM1167402", "GSM1167403", "GSM1167404", "GSM1167405", "GSM1167406", "GSM1167407", "GSM1167408", "GSM1167409", "GSM1167410", "GSM1167411", "GSM1167412", "GSM1167413", "GSM1167414", "GSM1167415", "GSM1167416", "GSM1167417", "GSM1167418", "GSM1167419", "GSM1167420", "GSM1167421", "GSM1167422", "GSM1167423", "GSM1167424", "GSM1167425", "GSM1167426", "GSM1167427", "GSM1167428", "GSM1167429", "GSM1167430", "GSM1167431", "GSM1167432", "GSM1167433", "GSM1167434", "GSM1167435", "GSM1167436", "GSM1167437", "GSM1167438", "GSM1167439", "GSM1167440", "GSM1167441", "GSM1167442", "GSM1167443", "GSM1167444", "GSM1167445", "GSM1167446", "GSM1167447", "GSM1167448", "GSM1167449", "GSM1167450", "GSM1167451", "GSM1167452", "GSM1167453", "GSM1167454", "GSM1167455", "GSM1167456", "GSM1167457", "GSM1167458", "GSM1167459", "GSM1167460", "GSM1167461", "GSM1167462", "GSM1167463", "GSM1167464", "GSM1167465", "GSM1167466", "GSM1167467", "GSM1167468", "GSM1167469", "GSM1167470", "GSM1167471", "GSM1167472", "GSM1167473", "GSM1167474"], "sample_count": 142, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Identification of subsets of urothelial carcinoma", "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:GSE48276", "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=GSE48276", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48276", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1173901", "GSM1173902", "GSM1173903", "GSM1173904", "GSM1173905", "GSM1173906", "GSM1173907", "GSM1173908", "GSM1173909", "GSM1173910", "GSM1173911", "GSM1173912", "GSM1173913", "GSM1173914", "GSM1173915", "GSM1173916", "GSM1173917", "GSM1173918", "GSM1173919", "GSM1173920", "GSM1173921", "GSM1173922", "GSM1173923", "GSM1173924", "GSM1173925", "GSM1173926", "GSM1173927", "GSM1173928", "GSM1173929", "GSM1173930", "GSM1173931", "GSM1173932", "GSM1173933", "GSM1173934", "GSM1173935", "GSM1173936", "GSM1173937", "GSM1173938", "GSM1173939", "GSM1173940", "GSM1173941", "GSM1173942", "GSM1173943", "GSM1173944", "GSM1173945", "GSM1173946", "GSM1173947", "GSM1173948", "GSM1173949", "GSM1173950", "GSM1173951", "GSM1173952", "GSM1173953", "GSM1173954", "GSM1173955", "GSM1173956", "GSM1173957", "GSM1173968", "GSM1173969", "GSM1173970", "GSM1173971", "GSM1173972", "GSM1173973", "GSM1173974", "GSM1173975", "GSM1173976", "GSM1173977", "GSM1173978", "GSM1173979", "GSM1173980", "GSM1173981", "GSM1173982", "GSM1173983", "GSM1173986", "GSM1173987", "GSM1173988", "GSM1173989", "GSM1173990", "GSM1173991", "GSM1173992", "GSM1173993", "GSM1173994", "GSM1173995", "GSM1173996", "GSM1173997", "GSM1173998", "GSM1173999", "GSM1174000", "GSM1174001", "GSM1174002", "GSM1174003", "GSM1174004", "GSM1174005", "GSM1174006", "GSM1174007", "GSM1174008", "GSM1174009", "GSM1174010", "GSM1174011", "GSM1174012", "GSM1174013", "GSM1174014", "GSM1174015", "GSM1174016", "GSM1174017", "GSM1174018", "GSM1174019", "GSM1174020", "GSM1174021", "GSM1174022", "GSM1174023", "GSM1174024", "GSM1174025", "GSM1174026", "GSM1174027", "GSM1174028"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Gene expression profiling of urothelial carcinoma", "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:GSE52219", "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=GSE52219", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52219", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1261392", "GSM1261393", "GSM1261394", "GSM1261395", "GSM1261396", "GSM1261397", "GSM1261398", "GSM1261399", "GSM1261400", "GSM1261401", "GSM1261402", "GSM1261403", "GSM1261404", "GSM1261405", "GSM1261406", "GSM1261407", "GSM1261408", "GSM1261409", "GSM1261410", "GSM1261411", "GSM1261412", "GSM1261413", "GSM1261414"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Tumors with neoadjuvant chemotherapy", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE69795", "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=GSE69795", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69795", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1709066", "GSM1709067", "GSM1709068", "GSM1709069", "GSM1709070", "GSM1709071", "GSM1709072", "GSM1709073", "GSM1709074", "GSM1709075", "GSM1709076", "GSM1709077", "GSM1709078", "GSM1709079", "GSM1709080", "GSM1709081", "GSM1709082", "GSM1709083", "GSM1709084", "GSM1709085", "GSM1709086", "GSM1709087", "GSM1709088", "GSM1709089", "GSM1709090", "GSM1709091", "GSM1709092", "GSM1709093", "GSM1709094", "GSM1709095", "GSM1709096", "GSM1709097", "GSM1709098", "GSM1709099", "GSM1709100", "GSM1709101", "GSM1709102", "GSM1709103", "GSM1709104", "GSM1709105", "GSM1709106", "GSM1709107", "GSM1709108", "GSM1709109", "GSM1709110", "GSM1709111", "GSM1709112", "GSM1709113", "GSM1709114", "GSM1709115", "GSM1709116", "GSM1709117", "GSM1709118", "GSM1709119", "GSM1709120", "GSM1709121", "GSM1709122", "GSM1709123", "GSM1709124", "GSM1709125", "GSM1709126"], "sample_count": 61, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "a phase 2 trial of DDMVAC and bevacizumab in urothelial cancer", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE83586", "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=GSE83586", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE83586", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2212901", "GSM2212902", "GSM2212903", "GSM2212904", "GSM2212905", "GSM2212906", "GSM2212907", "GSM2212908", "GSM2212909", "GSM2212910", "GSM2212911", "GSM2212912", "GSM2212913", "GSM2212914", "GSM2212915", "GSM2212916", "GSM2212917", "GSM2212918", "GSM2212919", "GSM2212920", "GSM2212921", "GSM2212922", "GSM2212923", "GSM2212924", "GSM2212925", "GSM2212926", "GSM2212927", "GSM2212928", "GSM2212929", "GSM2212930", "GSM2212931", "GSM2212932", "GSM2212933", "GSM2212934", "GSM2212935", "GSM2212936", "GSM2212937", "GSM2212938", "GSM2212939", "GSM2212940", "GSM2212941", "GSM2212942", "GSM2212943", "GSM2212944", "GSM2212945", "GSM2212946", "GSM2212947", "GSM2212948", "GSM2212949", "GSM2212950", "GSM2212951", "GSM2212952", "GSM2212953", "GSM2212954", "GSM2212955", "GSM2212956", "GSM2212957", "GSM2212958", "GSM2212959", "GSM2212960", "GSM2212961", "GSM2212962", "GSM2212963", "GSM2212964", "GSM2212965", "GSM2212966", "GSM2212967", "GSM2212968", "GSM2212969", "GSM2212970", "GSM2212971", "GSM2212972", "GSM2212973", "GSM2212974", "GSM2212975", "GSM2212976", "GSM2212977", "GSM2212978", "GSM2212979", "GSM2212980", "GSM2212981", "GSM2212982", "GSM2212983", "GSM2212984", "GSM2212985", "GSM2212986", "GSM2212987", "GSM2212988", "GSM2212989", "GSM2212990", "GSM2212991", "GSM2212992", "GSM2212993", "GSM2212994", "GSM2212995", "GSM2212996", "GSM2212997", "GSM2212998", "GSM2212999", "GSM2213000", "GSM2213001", "GSM2213002", "GSM2213003", "GSM2213004", "GSM2213005", "GSM2213006", "GSM2213007", "GSM2213008", "GSM2213009", "GSM2213010", "GSM2213011", "GSM2213012", "GSM2213013", "GSM2213014", "GSM2213015", "GSM2213016", "GSM2213017", "GSM2213018", "GSM2213019", "GSM2213020", "GSM2213021", "GSM2213022", "GSM2213023", "GSM2213024", "GSM2213025", "GSM2213026", "GSM2213027", "GSM2213028", "GSM2213029", "GSM2213030", "GSM2213031", "GSM2213032", "GSM2213033", "GSM2213034", "GSM2213035", "GSM2213036", "GSM2213037", "GSM2213038", "GSM2213039", "GSM2213040", "GSM2213041", "GSM2213042", "GSM2213043", "GSM2213044", "GSM2213045", "GSM2213046", "GSM2213047", "GSM2213048", "GSM2213049", "GSM2213050", "GSM2213051", "GSM2213052", "GSM2213053", "GSM2213054", "GSM2213055", "GSM2213056", "GSM2213057", "GSM2213058", "GSM2213059", "GSM2213060", "GSM2213061", "GSM2213062", "GSM2213063", "GSM2213064", "GSM2213065", "GSM2213066", "GSM2213067", "GSM2213068", "GSM2213069", "GSM2213070", "GSM2213071", "GSM2213072", "GSM2213073", "GSM2213074", "GSM2213075", "GSM2213076", "GSM2213077", "GSM2213078", "GSM2213080", "GSM2213081", "GSM2213082", "GSM2213084", "GSM2213086", "GSM2213088", "GSM2213090", "GSM2213092", "GSM2213093", "GSM2213094", "GSM2213095", "GSM2213096", "GSM2213097", "GSM2213098", "GSM2213099", "GSM2213100", "GSM2213101", "GSM2213102", "GSM2213103", "GSM2213104", "GSM2213105", "GSM2213106", "GSM2213107", "GSM2213108", "GSM2213109", "GSM2213110", "GSM2213111", "GSM2213112", "GSM2213113", "GSM2213114", "GSM2213115", "GSM2213116", "GSM2213117", "GSM2213118", "GSM2213119", "GSM2213120", "GSM2213121", "GSM2213122", "GSM2213123", "GSM2213124", "GSM2213125", "GSM2213126", "GSM2213127", "GSM2213128", "GSM2213129", "GSM2213130", "GSM2213131", "GSM2213132", "GSM2213133", "GSM2213134", "GSM2213135", "GSM2213136", "GSM2213137", "GSM2213138", "GSM2213139", "GSM2213140", "GSM2213141", "GSM2213142", "GSM2213143", "GSM2213144", "GSM2213145", "GSM2213146", "GSM2213147", "GSM2213148", "GSM2213149", "GSM2213150", "GSM2213151", "GSM2213152", "GSM2213153", "GSM2213154", "GSM2213155", "GSM2213156", "GSM2213157", "GSM2213158", "GSM2213159", "GSM2213160", "GSM2213161", "GSM2213162", "GSM2213163", "GSM2213164", "GSM2213165", "GSM2213166", "GSM2213167", "GSM2213168", "GSM2213169", "GSM2213170", "GSM2213171", "GSM2213172", "GSM2213173", "GSM2213174", "GSM2213175", "GSM2213176", "GSM2213177", "GSM2213178", "GSM2213179", "GSM2213180", "GSM2213181", "GSM2213182", "GSM2213183", "GSM2213184", "GSM2213185", "GSM2213186", "GSM2213187", "GSM2213188", "GSM2213189", "GSM2213190", "GSM2213191", "GSM2213192", "GSM2213193", "GSM2213194", "GSM2213195", "GSM2213196", "GSM2213197", "GSM2213198", "GSM2213199", "GSM2213200", "GSM2213201", "GSM2213202", "GSM2213203", "GSM2213204", "GSM2213205", "GSM2213206", "GSM2213207", "GSM2213208", "GSM2213209", "GSM2213210", "GSM2213211", "GSM2213212", "GSM2213213"], "sample_count": 307, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Molecular classification of bladder cancer: global mRNA classification versus tumor cell phenotype classification.", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE93527", "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=GSE93527", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE93527", "version": null, "note": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2454209", "GSM2454210", "GSM2454211", "GSM2454212", "GSM2454213", "GSM2454214", "GSM2454215", "GSM2454216", "GSM2454217", "GSM2454218", "GSM2454219", "GSM2454220", "GSM2454221", "GSM2454222", "GSM2454223", "GSM2454224", "GSM2454225", "GSM2454226", "GSM2454227", "GSM2454228", "GSM2454229", "GSM2454230", "GSM2454231", "GSM2454232", "GSM2454233", "GSM2454234", "GSM2454235", "GSM2454236", "GSM2454237", "GSM2454238", "GSM2454239", "GSM2454240", "GSM2454241", "GSM2454242", "GSM2454243", "GSM3699746", "GSM3699747", "GSM3699748", "GSM3699749", "GSM3699750", "GSM3699751", "GSM3699752", "GSM3699753", "GSM3699754", "GSM3699755", "GSM3699756", "GSM3699757", "GSM3699758", "GSM3699759", "GSM3699760", "GSM3699761", "GSM3699762", "GSM3699763", "GSM3699764", "GSM3699765", "GSM3699766", "GSM3699767", "GSM3699768", "GSM3699769", "GSM3699770", "GSM3699771", "GSM3699772", "GSM3699773", "GSM3699774", "GSM3699775", "GSM3699776", "GSM3699777", "GSM3699778", "GSM3699779", "GSM3699780", "GSM3699781", "GSM3699782", "GSM3699783", "GSM3699784", "GSM3699785", "GSM3699786", "GSM3699787", "GSM3699788", "GSM3699789"], "sample_count": 79, "group_sizes": null, "group_sizes_basis": null, "platform": "17586", "taxon": "Homo sapiens", "title": "Expression analysis of human stage Ta bladder tumours", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:E-MTAB-1940 not downloaded", "asset:data:geo:E-MTAB-1940 licence not read", "asset:data:geo:GSE104922 not downloaded", "asset:data:geo:GSE104922 licence not read", "asset:data:geo:GSE121711 not downloaded", "asset:data:geo:GSE121711 licence not read", "asset:data:geo:GSE128959 not downloaded", "asset:data:geo:GSE128959 licence not read", "asset:data:geo:GSE13507 not downloaded", "asset:data:geo:GSE13507 licence not read", "asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE48075 not downloaded", "asset:data:geo:GSE48075 licence not read", "asset:data:geo:GSE48276 not downloaded", "asset:data:geo:GSE48276 licence not read", "asset:data:geo:GSE52219 not downloaded", "asset:data:geo:GSE52219 licence not read", "asset:data:geo:GSE69795 not downloaded", "asset:data:geo:GSE69795 licence not read", "asset:data:geo:GSE83586 not downloaded", "asset:data:geo:GSE83586 licence not read", "asset:data:geo:GSE93527 not downloaded", "asset:data:geo:GSE93527 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": "Cox proportional hazards regression was performed with the packages survminer and survival, and statistical significance was determined via the log-rank method."}}, {"id": "method-2", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Mann-Whitney"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-5", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "centrality"}}], "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": ["GSE121711", "GSE93527", "GSE31684", "GSE104922", "GSE128959", "GSE83586", "GSE48276", "GSE52219", "GSE69795", "GSE13507", "GSE48075", "E-MTAB-1940"], "resolved_accessions": ["GSE121711", "GSE93527", "GSE31684", "GSE104922", "GSE128959", "GSE83586", "GSE48276", "GSE52219", "GSE69795", "GSE13507", "GSE48075", "E-MTAB-1940"], "statements": ["This study used publicly available data. The raw microarrays used here are publicly available in the Gene Expression Omnibus under the accession codes GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, and GSE48075, and in ArrayExpress under the accession code E-MTAB-1940. TCGA-BLCA-2017 molecular and clinical data were downloaded from cBioPortal. IMvigor molecular and clinical data were acquired through the IMvigor210CoreBiologies R package. The processed, ComBat-normalized matrix (discovery set) and the sample clinical data are available as Supplements. The codes used to generate the results and figures are available upon reasonable request."], "basis": "The paper names GSE121711, GSE93527, GSE31684, GSE104922, GSE128959, GSE83586, GSE48276, GSE52219, GSE69795, GSE13507, GSE48075, E-MTAB-1940 in Gene Expression Omnibus 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:35626146", "data:geo:E-MTAB-1940"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-1940"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:47:48Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 21231, "completion_tokens": 3529, "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:35626146", "type": "paper", "label": "pmid:35626146"}, {"id": "source:pmid:35626146", "type": "manuscript", "label": "PMID 35626146 full text"}, {"id": "data:geo:E-MTAB-1940", "type": "dataset", "label": "GEO E-MTAB-1940"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35626146", "type": "paper", "label": "pmid:35626146"}, {"id": "source:pmid:35626146", "type": "manuscript", "label": "PMID 35626146 full text"}, {"id": "data:geo:E-MTAB-1940", "type": "dataset", "label": "GEO E-MTAB-1940"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35626146", "type": "extraction", "used": ["source:pmid:35626146"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-1940", "type": "accession_resolution", "used": ["data:geo:E-MTAB-1940"], "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:35626146", "parent_hash": "sha256:5840285537dd33096a31c27b00aa855cfaf9dc8862f8fb155e09e2cdb87ea797", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:E-MTAB-1940 licence not read", "asset:data:geo:E-MTAB-1940 not downloaded", "asset:data:geo:GSE104922 licence not read", "asset:data:geo:GSE104922 not downloaded", "asset:data:geo:GSE121711 licence not read", "asset:data:geo:GSE121711 not downloaded", "asset:data:geo:GSE128959 licence not read", "asset:data:geo:GSE128959 not downloaded", "asset:data:geo:GSE13507 licence not read", "asset:data:geo:GSE13507 not downloaded", "asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE48075 licence not read", "asset:data:geo:GSE48075 not downloaded", "asset:data:geo:GSE48276 licence not read", "asset:data:geo:GSE48276 not downloaded", "asset:data:geo:GSE52219 licence not read", "asset:data:geo:GSE52219 not downloaded", "asset:data:geo:GSE69795 licence not read", "asset:data:geo:GSE69795 not downloaded", "asset:data:geo:GSE83586 licence not read", "asset:data:geo:GSE83586 not downloaded", "asset:data:geo:GSE93527 licence not read", "asset:data:geo:GSE93527 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": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["nt urothelium. The TCGA-2017 and IMvigor-210 RNA-Seq data were used to validate our findings. Wnt", "ive biomarkers. A total of 1135 primary BLCA transcriptomes from 12 microarray studies were compiled in", "is focused on primary, treatment-naïve tumor transcriptomes. The selection of datasets and samples eligi", "comprised 1054 primary bladder cancer tumor transcriptomes of treatment-naïve patients without any prio"], "order_basis": "paper_text_order:503", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["of 1135 primary BLCA transcriptomes from 12 microarray studies were compiled in a meta-cohort and a", "ell as the processing and integration of raw microarray data, is detailed in Appendix A. Briefly, we", "tailed in Appendix A. Briefly, we compiled a microarray discovery cohort from 12 well-characterized", "s. Left: housekeeping genes defined based on microarray analysis of several cancers. Right: housekee"], "order_basis": "paper_text_order:527", "id": "assay:2"}, {"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": ["Cox proportional hazards regression was performed with the packages survminer and survival, and statistical significance was determined via the log-rank method."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:37:17+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}}}