{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28977887", "kind": "science-record", "revision": 7, "content_hash": "sha256:90f098171a8503412059d98b043965eceab150f8b8614d95ceae636a497c01b3", "created_at": "2026-11-01T15:40:29Z", "updated_at": "2026-11-01T21:21:06Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Risk score based on three mRNA expression predicts the survival of bladder cancer.", "doi": "10.18632/oncotarget.18642", "pmid": "28977887", "authors": ["Qingzuo Liu", "Ruigang Diao", "Guoyan Feng", "Xiaodong Mu", "Aiqun Li"], "journal": "Oncotarget", "year": 2017, "abstract": "Bladder cancer (BLCA) is one of the most malignant cancers worldwide, and its prognosis varies. 1214 BLCA samples in five different datasets and 2 platforms were enrolled in this study. By utilizing the gene expression in The Cancer Genome Atlas (TCGA) dataset, and another two datasets, in GSE13507 and GSE31684, we constructed a risk score staging system with Cox multivariate regression to evaluate predict the outcome of BLCA patients. Three genes consist of RCOR1, ST3GAL5, and COL10A1 were used to predict the survival of BLCA patients. The patients with low risk score have a better survival rate than those with high risk score, significantly. The survival profiles of another two datasets (GSE13507 and GSE31684), which were used for candidate gene selection, were similar as the training dataset (TCGA). Furthermore, survival prediction effect of risk score staging system in another 2 independent datasets, GSE40875 and E-TABM-4321, were also validated. Compared with other clinical observations, and the risk score performs better in evaluating the survival of BLCA patients. Moreover, the correlation between radiation were also evaluated, and we found that patients have a poor survival in high risk group, regardless of radiation. Gene Set Enrichment Analysis was also implemented to find the difference between high-risk and low-risk groups on biological pathways, and focal adhesion and JAK signaling pathway were significantly enriched. In summary, we developed a risk staging model for BLCA patients with three gene expression. The model is independent from and performs better than other clinical information.", "claims": [{"id": "claim-method", "statement": "The significantly altered signaling pathways between high risk group and the low risk group were assessed with Gene Set Enrichment Analysis (GSEA) to investigate why the risk score predicts the survival of BLCA patients.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28977887", "locator": "sections[7] \"Altered pathways in the high risk score patients\" paragraph 2", "quote": "The significantly altered signaling pathways between high risk group and the low risk group were assessed with Gene Set Enrichment Analysis (GSEA) to investigate why the risk score predicts the survival of BLCA patients."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28977887", "locator": "sections[10] \"Data pre-processing\" paragraph 2", "quote": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study constructed a bladder-cancer survival risk score using Cox multivariate regression applied to gene-expression data from TCGA-BLCA, GSE13507, and GSE31684.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28977887", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "By utilizing the gene expression in The Cancer Genome Atlas (TCGA) dataset, and another two datasets, in GSE13507 and GSE31684, we constructed a risk score staging system with Cox multivariate regression to evaluate predict the outcome of BLCA patients."}, {"asset": "source:pmid:28977887", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Three genes consist of RCOR1, ST3GAL5, and COL10A1 were used to predict the survival of BLCA patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study constructed a bladder-cancer survival risk score using Cox multivariate regression applied to gene-expression data from TCGA-BLCA, GSE13507, and GSE31684.", "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:28977887"], "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:GSE13507"], "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:GSE13507"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28977887", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/oncotarget.18642", "sha256": "sha256:5f4e46abf9d8ac94630e8b27cf01c5893ed49a7de07bb9f5444a8dfe8db0f9e2", "bytes": 17937, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/oncotarget.18642", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5617447", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"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": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "access_statement_kind": "repository_route_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": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "access_statement_kind": "repository_route_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:GSE40875", "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=GSE40875", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40875", "version": null, "note": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1003981", "GSM1003982", "GSM1003983", "GSM1003984", "GSM1003985", "GSM1003986", "GSM1003987", "GSM1003988", "GSM1003989", "GSM1003990", "GSM1003991", "GSM1003992", "GSM1003993", "GSM1003994", "GSM1003995", "GSM1003996", "GSM1003997", "GSM1003998", "GSM1003999", "GSM1004000", "GSM1004001", "GSM1004002", "GSM1004003", "GSM1004004", "GSM1004005", "GSM1004006", "GSM1004007", "GSM1004008", "GSM1004009", "GSM1004010", "GSM1004011", "GSM1004012", "GSM1004013", "GSM1004014", "GSM1004015"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "6246", "taxon": "Mus musculus", "title": "Early parity-induced gene expression in mouse mammary cell subtypes", "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": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website.", "access_statement_kind": "repository_route_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}}], "gaps": ["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:GSE40875 not downloaded", "asset:data:geo:GSE40875 licence not read", "asset:data:geo:GSE48075 not downloaded", "asset:data:geo:GSE48075 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Gene Set Enrichment Analysis (GSEA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The significantly altered signaling pathways between high risk group and the low risk group were assessed with Gene Set Enrichment Analysis (GSEA) to investigate why the risk score predicts the survival of BLCA patients."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Gene Set Enrichment Analysis (GSEA)), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE13507", "GSE31684", "GSE48075", "GSE40875"], "resolved_accessions": ["GSE13507", "GSE31684", "GSE48075", "GSE40875"], "statements": ["The TCGA dataset were downloaded from UCSC Xena website (http://xena.ucsc.edu/), the expression value were converted to normalized RSEM values, the detailed pre-processing steps, including mapping and normalization, were described on UCSC Xena website."], "basis": "The paper names GSE13507, GSE31684, GSE48075, GSE40875 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:28977887", "data:geo:GSE13507"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13507"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:25Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 35999, "completion_tokens": 5156, "cached_tokens": 1832}}, "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:28977887", "type": "paper", "label": "pmid:28977887"}, {"id": "source:pmid:28977887", "type": "manuscript", "label": "PMID 28977887 full text"}, {"id": "data:geo:GSE13507", "type": "dataset", "label": "GEO GSE13507"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28977887", "type": "paper", "label": "pmid:28977887"}, {"id": "source:pmid:28977887", "type": "manuscript", "label": "PMID 28977887 full text"}, {"id": "data:geo:GSE13507", "type": "dataset", "label": "GEO GSE13507"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28977887", "type": "extraction", "used": ["source:pmid:28977887"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13507", "type": "accession_resolution", "used": ["data:geo:GSE13507"], "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:28977887", "parent_hash": "sha256:477068da0e35fbf21e95e6d8203eb4a3cd37855e4cb10229c20dbba8f85d3dfc", "fork_of": null, "generation": 6}, "gaps": ["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:GSE40875 licence not read", "asset:data:geo:GSE40875 not downloaded", "asset:data:geo:GSE48075 licence not read", "asset:data:geo:GSE48075 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["g/, v3.0.1) and R packages. Normalization of affymetrix raw data was performed with R package “affy”"], "order_basis": "paper_text_order:2780", "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":"2026-11-04T01:46:44+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}}}