{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32266115", "kind": "science-record", "revision": 5, "content_hash": "sha256:2eebed7e114e9efc22d7f22856068fe68f0820d36b390bf776ee16675aac948c", "created_at": "2026-11-01T15:40:59Z", "updated_at": "2026-11-01T22:01:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of core genes associated with prostate cancer progression and outcome via bioinformatics analysis in multiple databases.", "doi": "10.7717/peerj.8786", "pmid": "32266115", "authors": ["Yutao Wang", "Jianfeng Wang", "Kexin Yan", "Jiaxing Lin", "Zhenhua Zheng", "Jianbin Bi"], "journal": "PeerJ", "year": 2020, "abstract": "ABSTRACT: The morbidity and mortality of prostate carcinoma has increased in recent years and has become the second most common ale malignant carcinoma worldwide. The interaction mechanisms between different genes and signaling pathways, however, are still unclear.\nMETHODS: Variation analysis of GSE38241, GSE69223, GSE46602 and GSE104749 were realized by GEO2R in Gene Expression Omnibus database. Function enrichment was analyzed by DAVID.6.8. Furthermore, the PPI network and the significant module were analyzed by Cytoscape, STRING and MCODE.GO. Pathway analysis showed that the 20 candidate genes were closely related to mitosis, cell division, cell cycle phases and the p53 signaling pathway. A total of six independent prognostic factors were identified in GSE21032 and TCGA PRAD. Oncomine database and The Human Protein Atlas were applied to explicit that six core genes were over expression in prostate cancer compared to normal prostate tissue in the process of transcriptional and translational. Finally, gene set enrichment were performed to identified the related pathway of core genes involved in prostate cancer.\nRESULT: Hierarchical clustering analysis revealed that these 20 core genes were mostly related to carcinogenesis and development. CKS2, TK1, MKI67, TOP2A, CCNB1 and RRM2 directly related to the recurrence and prognosis of prostate cancer. This result was verified by TCGA database and GSE21032.\nCONCLUSION: These core genes play a crucial role in tumor carcinogenesis, development, recurrence, metastasis and progression. Identifying these genes could help us to understand the molecular mechanisms and provide potential biomarkers for the diagnosis and treatment of prostate cancer.", "claims": [{"id": "claim-method", "statement": "The GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used to screen DEGs between prostate carcinoma samples and noncancerous samples GSE104749, GSE38241, GSE69223, GSE46602 datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32266115", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "The GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used to screen DEGs between prostate carcinoma samples and noncancerous samples GSE104749, GSE38241, GSE69223, GSE46602 datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32266115", "locator": "sections[27] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749."}], "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:32266115"], "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:GSE104749"], "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:GSE104749"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32266115", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.8786", "sha256": "sha256:cee611b6d9a8d03aa649e4e280b2f661401f8b04048b2dfc56d4a0a001c93b1b", "bytes": 54856, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.8786", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7120053", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE104749", "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=GSE104749", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE104749", "version": null, "note": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2807157", "GSM2807158", "GSM2807159", "GSM2807160", "GSM2807161", "GSM2807162", "GSM2807163", "GSM2807164"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Molecular analyses of prostate tumors for diagnosis of malignancy on Fine-Needle Aspiration biopsies", "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:GSE21032", "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=GSE21032", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21032", "version": null, "note": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM525575", "GSM525576", "GSM525577", "GSM525578", "GSM525579", "GSM525580", "GSM525581", "GSM525582", "GSM525583", "GSM525584", "GSM525585", "GSM525586", "GSM525587", "GSM525588", "GSM525589", "GSM525590", "GSM525591", "GSM525592", "GSM525593", "GSM525594", "GSM525595", "GSM525596", "GSM525597", "GSM525598", "GSM525599", "GSM525600", "GSM525601", "GSM525602", "GSM525603", "GSM525604", "GSM525605", "GSM525606", "GSM525607", "GSM525608", "GSM525609", "GSM525610", "GSM525611", "GSM525612", "GSM525613", "GSM525614", "GSM525615", "GSM525616", "GSM525617", "GSM525618", "GSM525619", "GSM525620", "GSM525621", "GSM525622", "GSM525623", "GSM525624", "GSM525625", "GSM525626", "GSM525627", "GSM525628", "GSM525629", "GSM525630", "GSM525631", "GSM525632", "GSM525633", "GSM525634", "GSM525635", "GSM525636", "GSM525637", "GSM525638", "GSM525639", "GSM525640", "GSM525641", "GSM525642", "GSM525643", "GSM525644", "GSM525645", "GSM525646", "GSM525647", "GSM525648", "GSM525649", "GSM525650", "GSM525651", "GSM525652", "GSM525653", "GSM525654", "GSM525655", "GSM525656", "GSM525657", "GSM525658", "GSM525659", "GSM525660", "GSM525661", "GSM525662", "GSM525663", "GSM525664", "GSM525665", "GSM525666", "GSM525667", "GSM525668", "GSM525669", "GSM525670", "GSM525671", "GSM525672", "GSM525673", "GSM525674", "GSM525675", "GSM525676", "GSM525677", "GSM525678", "GSM525679", "GSM525680", "GSM525681", "GSM525682", "GSM525683", "GSM525684", "GSM525685", "GSM525686", "GSM525687", "GSM525688", "GSM525689", "GSM525690", "GSM525691", "GSM525692", "GSM525693", "GSM525694", "GSM525695", "GSM525696", "GSM525697", "GSM525698", "GSM525699", "GSM525700", "GSM525701", "GSM525702", "GSM525703", "GSM525704", "GSM525705", "GSM525706", "GSM525707", "GSM525708", "GSM525709", "GSM525710", "GSM525711", "GSM525712", "GSM525713", "GSM525714", "GSM525715", "GSM525716", "GSM525717", "GSM525718", "GSM525719", "GSM525720", "GSM525721", "GSM525722", "GSM525723", "GSM525724", "GSM525725", "GSM525726", "GSM525727", "GSM525728", "GSM525729", "GSM525730", "GSM525731", "GSM525732", "GSM525733", "GSM525734", "GSM525735", "GSM525736", "GSM525737", "GSM525738", "GSM525739", "GSM525740", "GSM525741", "GSM525742", "GSM525743", "GSM525744", "GSM525745", "GSM525746", "GSM525747", "GSM525748", "GSM525749", "GSM525750", "GSM525751", "GSM525752", "GSM525753", "GSM525754", "GSM525755", "GSM525756", "GSM525757", "GSM525758", "GSM525759", "GSM525760", "GSM525761", "GSM525762", "GSM525763", "GSM525764", "GSM525765", "GSM525766", "GSM525767", "GSM525768", "GSM525769", "GSM525770", "GSM525771", "GSM525772", "GSM525773", "GSM525774", "GSM525775", "GSM525776", "GSM525777", "GSM525778", "GSM525779", "GSM525780", "GSM525781", "GSM525782", "GSM525783", "GSM525784", "GSM525785", "GSM525786", "GSM525787", "GSM525788", "GSM525789", "GSM525790", "GSM525791", "GSM525792", "GSM525793", "GSM525794", "GSM525795", "GSM525796", "GSM525797", "GSM525798", "GSM525799", "GSM525800", "GSM525801", "GSM525802", "GSM525803", "GSM525804", "GSM525805", "GSM526134", "GSM526135", "GSM526136", "GSM526137", "GSM526138", "GSM526139", "GSM526140", "GSM526141", "GSM526142", "GSM526143", "GSM526144", "GSM526145", "GSM526146", "GSM526147", "GSM526148", "GSM526149", "GSM526150", "GSM526151", "GSM526152", "GSM526153", "GSM526154", "GSM526155", "GSM526156", "GSM526157", "GSM526158", "GSM526159", "GSM526160", "GSM526161", "GSM526162", "GSM526163", "GSM526164", "GSM526165", "GSM526166", "GSM526167", "GSM526168", "GSM526169", "GSM526170", "GSM526171", "GSM526172", "GSM526173", "GSM526174", "GSM526175", "GSM526176", "GSM526177", "GSM526178", "GSM526179", "GSM526180", "GSM526181", "GSM526182", "GSM526183", "GSM526184", "GSM526185", "GSM526186", "GSM526187", "GSM526188", "GSM526189", "GSM526190", "GSM526191", "GSM526192", "GSM526193", "GSM526194", "GSM526195", "GSM526196", "GSM526197", "GSM526198", "GSM526199", "GSM526200", "GSM526201", "GSM526202", "GSM526203", "GSM526204", "GSM526205", "GSM526206", "GSM526207", "GSM526208", "GSM526209", "GSM526210", "GSM526211", "GSM526212", "GSM526213", "GSM526214", "GSM526215", "GSM526216", "GSM526217", "GSM526218", "GSM526219", "GSM526220", "GSM526221", "GSM526222", "GSM526223", "GSM526224", "GSM526225", "GSM526226", "GSM526227", "GSM526228", "GSM526229", "GSM526230", "GSM526231", "GSM526232", "GSM526233", "GSM526234", "GSM526235", "GSM526236", "GSM526237", "GSM526238", "GSM526239", "GSM526240", "GSM526241", "GSM526242", "GSM526243", "GSM526244", "GSM526245", "GSM526246", "GSM526247", "GSM526248", "GSM526249", "GSM526250", "GSM526251", "GSM526252", "GSM526253", "GSM526254", "GSM526255", "GSM526256", "GSM526257", "GSM526258", "GSM526259", "GSM526260", "GSM526261", "GSM526262", "GSM526263", "GSM526264", "GSM526265", "GSM526266", "GSM526267", "GSM526268", "GSM526269", "GSM526270", "GSM526271", "GSM526272", "GSM526273", "GSM526274", "GSM526275", "GSM526276", "GSM526277", "GSM526278", "GSM526279", "GSM526280", "GSM526281", "GSM526282", "GSM526283", "GSM526284", "GSM526285", "GSM526286", "GSM526287", "GSM526288", "GSM526289", "GSM526290", "GSM526291", "GSM526292", "GSM526293", "GSM526294", "GSM526295", "GSM526296", "GSM526297", "GSM526298", "GSM526299", "GSM526300", "GSM526301", "GSM526302", "GSM526303", "GSM526304", "GSM526305", "GSM526306", "GSM526307", "GSM526308", "GSM526309", "GSM526310", "GSM526311", "GSM526312", "GSM526313", "GSM526314", "GSM526315", "GSM526316", "GSM526317", "GSM526318", "GSM526419", "GSM526420", "GSM526421", "GSM526422", "GSM526423", "GSM526424", "GSM526425", "GSM526426", "GSM526427", "GSM526428", "GSM526429", "GSM526430", "GSM526431", "GSM526432", "GSM526433", "GSM526434", "GSM526435", "GSM526436", "GSM526437", "GSM526438", "GSM526439", "GSM526440", "GSM526441", "GSM526442", "GSM526443", "GSM526444", "GSM526445", "GSM526446", "GSM526447", "GSM526448", "GSM526449", "GSM526450", "GSM526451", "GSM526452", "GSM526453", "GSM526454", "GSM526455", "GSM526456", "GSM526457", "GSM526458", "GSM526459", "GSM526460", "GSM526461", "GSM526462", "GSM526463", "GSM526464", "GSM526465", "GSM526466", "GSM526467", "GSM526468", "GSM526469", "GSM526470", "GSM526471", "GSM526472", "GSM526473", "GSM526474", "GSM526475", "GSM526476", "GSM526477", "GSM526478", "GSM526479", "GSM526480", "GSM526481", "GSM526482", "GSM526483", "GSM526484", "GSM526485", "GSM526486", "GSM526487", "GSM526488", "GSM526489", "GSM526490", "GSM526491", "GSM526492", "GSM526493", "GSM526494", "GSM526495", "GSM526496", "GSM526497", "GSM526498", "GSM526499", "GSM526500", "GSM526501", "GSM526502", "GSM526503", "GSM526504", "GSM526505", "GSM526506", "GSM526507", "GSM526508", "GSM526509", "GSM526510", "GSM526511", "GSM526512", "GSM526513", "GSM526514", "GSM526515", "GSM526516", "GSM526517", "GSM526518", "GSM526519", "GSM526520", "GSM526521", "GSM526522", "GSM526523", "GSM526524", "GSM526525", "GSM526526", "GSM526527", "GSM526528", "GSM526529", "GSM526530", "GSM526531", "GSM526532", "GSM526533", "GSM526534", "GSM526535", "GSM526536", "GSM526537", "GSM526538", "GSM526539", "GSM526540", "GSM526541", "GSM526542", "GSM526543", "GSM526544", "GSM526545", "GSM526546", "GSM526547", "GSM526548", "GSM526549", "GSM526550", "GSM526551", "GSM526552", "GSM526553", "GSM526554", "GSM526555", "GSM526556", "GSM526557", "GSM526558", "GSM526559", "GSM526560", "GSM527858", "GSM527859", "GSM527860", "GSM527861", "GSM527862", "GSM527863", "GSM527864", "GSM527865", "GSM527866", "GSM527867", "GSM527868", "GSM527869", "GSM527870", "GSM527871", "GSM527872", "GSM527873", "GSM527874", "GSM527875", "GSM527876", "GSM527877", "GSM527878", "GSM527879", "GSM527880", "GSM527881", "GSM527882", "GSM527883", "GSM527884", "GSM527885", "GSM527886", "GSM527887", "GSM527888", "GSM527889", "GSM527890", "GSM527891", "GSM527892", "GSM527893", "GSM527894", "GSM527895", "GSM527896", "GSM527897", "GSM527898", "GSM527899", "GSM527900", "GSM527901", "GSM527902", "GSM527903", "GSM527904", "GSM527905", "GSM527906", "GSM527907", "GSM527908", "GSM527909", "GSM527910", "GSM527911", "GSM527912", "GSM527913", "GSM527914", "GSM527915", "GSM527916", "GSM527917", "GSM527918", "GSM527919", "GSM527920", "GSM527921", "GSM527922", "GSM527923", "GSM527924", "GSM527925", "GSM527926", "GSM527927", "GSM527928", "GSM527929", "GSM527930", "GSM527931", "GSM527932", "GSM527933", "GSM527934", "GSM527935", "GSM527936", "GSM527937", "GSM527938", "GSM527939", "GSM527940", "GSM527941", "GSM527942", "GSM527943", "GSM527944", "GSM527945", "GSM527946", "GSM527947", "GSM527948", "GSM527949", "GSM527950", "GSM527951", "GSM527952", "GSM527953", "GSM527954", "GSM527955", "GSM527956", "GSM527957", "GSM527958", "GSM527959", "GSM527960", "GSM527961", "GSM527962", "GSM527963", "GSM527965", "GSM527966", "GSM527968", "GSM527970", "GSM527971", "GSM527972", "GSM527973", "GSM527974", "GSM527975", "GSM527977", "GSM527979", "GSM527980", "GSM527982", "GSM527984", "GSM527985", "GSM527986", "GSM527987", "GSM527988", "GSM527989", "GSM527990", "GSM527991", "GSM527992", "GSM527993", "GSM527994", "GSM527995", "GSM527996", "GSM527997", "GSM527998", "GSM527999", "GSM528000", "GSM528001", "GSM528002", "GSM528003", "GSM528004", "GSM528005", "GSM528006", "GSM528007", "GSM528008", "GSM528009", "GSM528010", "GSM528011", "GSM528012", "GSM528013", "GSM528014", "GSM528015", "GSM528016", "GSM528017", "GSM528018", "GSM528019", "GSM528020", "GSM528021", "GSM528022", "GSM528023", "GSM528024", "GSM528025", "GSM528026", "GSM528027", "GSM528028", "GSM528029", "GSM528030", "GSM528031", "GSM528032", "GSM528033", "GSM528034", "GSM528035", "GSM528036", "GSM528037", "GSM528038", "GSM528039", "GSM528040", "GSM528041", "GSM528042", "GSM528043", "GSM528044", "GSM528045", "GSM528046", "GSM528047", "GSM528048", "GSM528049"], "sample_count": 743, "group_sizes": null, "group_sizes_basis": null, "platform": "10264;8227;5188;4091", "taxon": "Homo sapiens", "title": "Integrative genomic profiling of human prostate 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:GSE38241", "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=GSE38241", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38241", "version": null, "note": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM937270", "GSM937271", "GSM937272", "GSM937273", "GSM937274", "GSM937275", "GSM937276", "GSM937277", "GSM937278", "GSM937279", "GSM937280", "GSM937281", "GSM937282", "GSM937283", "GSM937284", "GSM937285", "GSM937286", "GSM937287", "GSM937288", "GSM937289", "GSM937290", "GSM937291", "GSM937292", "GSM937293", "GSM937294", "GSM937295", "GSM937296", "GSM937297", "GSM937298", "GSM937299", "GSM937300", "GSM937301", "GSM937302", "GSM937303", "GSM937304", "GSM937305", "GSM937306", "GSM937307", "GSM937308"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Gene expression profiling of normal prostates and prostate cancer metastases", "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:GSE46602", "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=GSE46602", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46602", "version": null, "note": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1133136", "GSM1133137", "GSM1133138", "GSM1133139", "GSM1133140", "GSM1133141", "GSM1133142", "GSM1133143", "GSM1133144", "GSM1133145", "GSM1133146", "GSM1133147", "GSM1133148", "GSM1133149", "GSM1133150", "GSM1133151", "GSM1133152", "GSM1133153", "GSM1133154", "GSM1133155", "GSM1133156", "GSM1133157", "GSM1133158", "GSM1133159", "GSM1133160", "GSM1133161", "GSM1133162", "GSM1133163", "GSM1133164", "GSM1133165", "GSM1133166", "GSM1133167", "GSM1133168", "GSM1133169", "GSM1133170", "GSM1133171", "GSM1133172", "GSM1133173", "GSM1133174", "GSM1133175", "GSM1133176", "GSM1133177", "GSM1133178", "GSM1133179", "GSM1133180", "GSM1133181", "GSM1133182", "GSM1133183", "GSM1133184", "GSM1133185"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from prostate cancer and benign prostate glands", "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:GSE69223", "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=GSE69223", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69223", "version": null, "note": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1695583", "GSM1695584", "GSM1695585", "GSM1695586", "GSM1695587", "GSM1695588", "GSM1695589", "GSM1695590", "GSM1695591", "GSM1695592", "GSM1695593", "GSM1695594", "GSM1695595", "GSM1695596", "GSM1695597", "GSM1695598", "GSM1695599", "GSM1695600", "GSM1695601", "GSM1695602", "GSM1695603", "GSM1695604", "GSM1695605", "GSM1695606", "GSM1695607", "GSM1695608", "GSM1695609", "GSM1695610", "GSM1695611", "GSM1695612"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression patterns in human prostate cancer (PCa)", "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:32266115:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:329d970a620a8ddd558795c540633774ecd1aeef671cf4de9a68388be785cdfc", "bytes": 1162, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table-1", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in prostate cancer samples.KEGG pathway analysis revealed that the DEGs were mainly enriched in focal adhesion and Glutathione metabolism pathway.", "structure": {"pmcid": "PMC7120053", "section_index": 12, "section_title": "KEGG and GO enrichment analyses of DEGs", "row_count": 14, "column_count": 4}, "table": {"label": "Table 1", "caption": "GO and KEGG pathway enrichment analysis of DEGs in prostate cancer samples.KEGG pathway analysis revealed that the DEGs were mainly enriched in focal adhesion and Glutathione metabolism pathway.", "rows": [["Pathway ID", "Term", "Count", "P-value"], ["GO:0007155", "Cell adhesion", "39", "1.86E−06"], ["GO:0007155", "Biological adhesion", "39", "1.88E−06"], ["GO:0048762", "Mesenchymal cell differentiation", "9", "2.52E−05"], ["GO:0014031", "Mesenchymal cell development", "9", "2.52E−05"], ["GO:0044421", "Extracellular region part", "63", "3.08E−14"], ["GO:0031012", "Extracellular matrix", "32", "6.05E−11"], ["GO:0005578", "Proteinaceous extracellular matrix", "29", "9.94E−10"], ["GO:0005578", "Extracellular region", "87", "1.37E−09"], ["GO:0004364", "Glutathione transferase activity", "6", "7.31E−05"], ["GO:0005201", "Extracellular matrix structural constituent", "10", "1.57E−04"], ["hsa04510", "Focal adhesion", "17", "4.85E−05"], ["hsa04510", "Drug metabolism", "9", "1.64E−04"], ["hsa04510", "Glutathione metabolism", "8", "2.54E−04"]], "row_count": 14, "column_count": 4, "numeric_cells": 39, "header_rows": 1, "locator": "section[12]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:32266115:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:18b45872bea5387d1a70c2ad91948593074cb6d460bac57dde11b1facfbc8bea", "bytes": 1074, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#table-2", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module.The genes in the most significant module were mainly enriched in the function of cell cycle phase, mitosis, cell division, microtubule cytoskeleton, spindle, p53 signaling pathway, Oocyte meiosis.", "structure": {"pmcid": "PMC7120053", "section_index": 13, "section_title": "PPI and module analysis", "row_count": 13, "column_count": 4}, "table": {"label": "Table 2", "caption": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module.The genes in the most significant module were mainly enriched in the function of cell cycle phase, mitosis, cell division, microtubule cytoskeleton, spindle, p53 signaling pathway, Oocyte meiosis.", "rows": [["Pathway ID", "Term", "Count", "P-value"], ["GO:0000279", "M phase", "14", "6.27E−18"], ["GO:0022403", "Cell cycle phase", "14", "1.27E−16"], ["GO:0007067", "Mitosis", "11", "4.12E−14"], ["GO:0000280", "Nuclear division", "11", "4.12E−14"], ["GO:0051301", "Cell division", "10", "4.04E−11"], ["GO:0015630", "Microtubule cytoskeleton", "9", "1.90E−07"], ["GO:0005819", "Spindle", "6", "1.04E−06"], ["GO:0051276", "Chromosome organization", "8", "1.65E−06"], ["GO:0044430", "Cytoskeletal part", "9", "1.22E−05"], ["GO:0003682", "Chromatin binding", "4", "6.21E−04"], ["hsa04115", "p53 Signaling pathway", "3", "0.003543755"], ["hsa04114", "Oocyte meiosis", "3", "0.009071242"]], "row_count": 13, "column_count": 4, "numeric_cells": 37, "header_rows": 1, "locator": "section[13]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:32266115:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:81d5ff3a83daea02b44698fa1e5e78f871896d0144ed48d50570cff50bbc42af", "bytes": 946, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#table-3", "version": null, "note": "GSEA results of core genes in TCGA PRAD.The P-value of the P53_signaling_pathway, GNRH signaling pathway, DNA replication, cell cycle in the 5 core genes were listed.", "structure": {"pmcid": "PMC7120053", "section_index": 16, "section_title": "Clinical relevance and GSEA", "row_count": 7, "column_count": 9}, "table": {"label": "Table 3", "caption": "GSEA results of core genes in TCGA PRAD.The P-value of the P53_signaling_pathway, GNRH signaling pathway, DNA replication, cell cycle in the 5 core genes were listed.", "rows": [["", "P53_signaling_pathway", "GNRH_signaling_pathway", "DNA_replication", "Cell_cycle"], ["", "NOM P-val", "FDR q-val", "NOM P-val", "FDR q-val", "NOM P-val", "FDR q-val", "NOM P-val", "FDR q-val"], ["RRM2", "<0.001", "0.0012", "<0.001", "4.65E−04", "<0.001", "0.001", "<0.001", "6.04E−04"], ["CKS2", "<0.001", "0.0054", "0.125", "0.1249", "<0.001", "0.0059", "<0.001", "0.00254688"], ["MKI67", "<0.001", "0.0026", "<0.001", "9.34E−04", "<0.001", "0.0023", "<0.001", "0.001120284"], ["TK1", "<0.001", "0.0124", "0.0653", "0.0708", "<0.001", "0.0049", "<0.001", "0.003169282"], ["TOP2A", "0.001992032", "0.0045", "<0.001", "0.0029", "<0.001", "0.004227", "<0.001", "0.00279397"]], "row_count": 7, "column_count": 9, "numeric_cells": 42, "header_rows": 2, "locator": "section[16]/table-wrap[1]#table-3"}}, {"id": "asset:table:pmid:32266115:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d23903618153e6f6ac3dda8460d9940bf1d3cca0573e014d94e034c6c8f6c442", "bytes": 3334, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#table-4", "version": null, "note": "Functional roles of 20 core genes with degree ≥20.These biological functions are closely related to the prostate cancer. A total of 20 core genes were screened with degree ≥20. The full name and the function of the 20 core genes were listed.", "structure": {"pmcid": "PMC7120053", "section_index": 17, "section_title": "Discussion", "row_count": 21, "column_count": 4}, "table": {"label": "Table 4", "caption": "Functional roles of 20 core genes with degree ≥20.These biological functions are closely related to the prostate cancer. A total of 20 core genes were screened with degree ≥20. The full name and the function of the 20 core genes were listed.", "rows": [["No.", "Gene symbol", "Full name", "Function"], ["1", "CKS2", "Cyclin kinase subunit 2", "Overexpressed CKS2 promotes cell growth and protects cell from apoptosis"], ["2", "TK1", "Thymidine kinase 1", "TK1 is related to DNA precursor synthesis, acts as a proliferating biomarker of prostate and breast cancer"], ["3", "MKI67", "Marker of proliferation Ki-67", "KI-67 is a marker of tumor cell proliferation and the epithelial-mesenchymal transition"], ["4", "TOP2A", "Topoisomerase IIα", "TOP2A controls the topology structure of DNA and cell cycle progression"], ["5", "CCNB1", "Cyclin B1", "A high cyclin B1 level contributes to the development of polyploidy and was a prognosis biomarker of prostate cancer for chemotherapy"], ["6", "RRM2", "Ribonucleotide-reductase regulatory subunit M2", "RRM2 limits the rate of DNA synthesis and repair. It was considered to be a biomarker to predict recurrence in PCa patients with low-risk"], ["7", "EZH2", "Enhancer of Zeste homolog 2", "Drug targeting therapy EZH2 may be a new therapeutic strategy for advanced PCa and docetaxel-resistant PCa patients"], ["8", "AURKA", "Aurora kinase A", "AURKA was considered to be a potential prognostic biomarker for the progression of high-risk small-cell prostate cancer"], ["9", "BIRC5", "Baculoviral IAP Repeat containing 5", "BIRC5 may prevent apoptotic cell death, by survivin, a protein that inhibits apoptosis"], ["10", "CCNB2", "Cyclin B2", "CDC2 specifically binds to Cyclin B2 to increase cell migration which is related to the development of CRPC"], ["11", "CDCA8", "Cell division cycle associated 8", "Overexpressed CDCA8 is related to mitosis and cell growth and acts as a prognosis biomarker of breast cancer"], ["12", "TPX2", "Targeting protein for Xenopus kinesin-like protein 2", "TPX2 is a microtubule-associated protein linked to mitosis and spindle assembly and targeting TPX2 is a strategy of PCa"], ["13", "CENPF", "Centromere protein F", "CENPF acts in the centromere-kinetochore complex and chromosomal segregation, it is related to aggressive prostate cancer"], ["14", "NVAPG", "Non-SMC condensin I complex subunit G", "NCAPG acts as a target of miR-99a-3p in PCa cells, overexpression of NCAPG is related to CRPC"], ["15", "NUSAP1", "Nucleolar and spindle-associated protein 1", "NUSAP1 is a prognosis biomarker in the early stage of PCa patients"], ["16", "ANLN", "Anillin actin binding protein", "ANLN was found to be related to cell cycle and growth of PCa cells"], ["17", "CDCA5", "Cell division cycle associated 5", "Knockdown CDCA5 may cause cell cycle arrest in the G2/M phase"], ["18", "ECT2", "Epithelial cell transforming sequence 2", "ECT2 is a guanine nucleotide exchange factor that is related to the progression of tumors"], ["19", "HMMR", "Hyaluronan-mediated motility receptor", "Hyaluronan-mediated motility receptor (HMMR) binds native and fragmented HA, promotes HA uptake"], ["20", "CENPU", "Centromere protein U", "CENPU upregulation can increase the invasiveness of prostate cancer"]], "row_count": 21, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[17]/table-wrap[1]#table-4"}}], "gaps": ["asset:data:geo:GSE104749 not downloaded", "asset:data:geo:GSE104749 licence not read", "asset:data:geo:GSE21032 not downloaded", "asset:data:geo:GSE21032 licence not read", "asset:data:geo:GSE38241 not downloaded", "asset:data:geo:GSE38241 licence not read", "asset:data:geo:GSE46602 not downloaded", "asset:data:geo:GSE46602 licence not read", "asset:data:geo:GSE69223 not downloaded", "asset:data:geo:GSE69223 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Hierarchical clustering"}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R differential expression analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used to screen DEGs between prostate carcinoma samples and noncancerous samples GSE104749, GSE38241, GSE69223, GSE46602 datasets."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["hierarchical_cluster"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: hierarchical."}, "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": ["GSE104749", "GSE38241", "GSE69223", "GSE46602", "GSE21032"], "resolved_accessions": ["GSE104749", "GSE38241", "GSE69223", "GSE46602", "GSE21032"], "statements": ["The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE38241, GSE69223, GSE46602, GSE104749."], "basis": "The paper names GSE104749, GSE38241, GSE69223, GSE46602, GSE21032 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["hierarchical_cluster"], "assets": ["source:pmid:32266115", "data:geo:GSE104749", "asset:table:pmid:32266115:1", "asset:table:pmid:32266115:2", "asset:table:pmid:32266115:3", "asset:table:pmid:32266115:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE104749"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:19:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 46910, "completion_tokens": 2201, "cached_tokens": 776}}, "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:32266115", "type": "paper", "label": "pmid:32266115"}, {"id": "source:pmid:32266115", "type": "manuscript", "label": "PMID 32266115 full text"}, {"id": "data:geo:GSE104749", "type": "dataset", "label": "GEO GSE104749"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32266115", "type": "paper", "label": "pmid:32266115"}, {"id": "source:pmid:32266115", "type": "manuscript", "label": "PMID 32266115 full text"}, {"id": "data:geo:GSE104749", "type": "dataset", "label": "GEO GSE104749"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32266115", "type": "extraction", "used": ["source:pmid:32266115"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE104749", "type": "accession_resolution", "used": ["data:geo:GSE104749"], "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:32266115", "parent_hash": "sha256:eec27063249f7b146ff2a430eb7b5c36689f83b1e5642d62d69d03e6b261719c", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE104749 licence not read", "asset:data:geo:GSE104749 not downloaded", "asset:data:geo:GSE21032 licence not read", "asset:data:geo:GSE21032 not downloaded", "asset:data:geo:GSE38241 licence not read", "asset:data:geo:GSE38241 not downloaded", "asset:data:geo:GSE46602 licence not read", "asset:data:geo:GSE46602 not downloaded", "asset:data:geo:GSE69223 licence not read", "asset:data:geo:GSE69223 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["hierarchical_cluster"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Hierarchical clustering"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T03:13:20+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}