{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39991573", "kind": "science-record", "revision": 2, "content_hash": "sha256:09a54814013228127a0b1b53a1cc91127132afcdb7fe8101a5701e5c6f564a87", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:37Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrative multi-omics and machine learning identify a robust signature for discriminating prognosis and therapeutic targets in bladder cancer.", "doi": "10.7150/jca.105066", "pmid": "39991573", "authors": null, "journal": "Journal of Cancer", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 5.0, "unit": "prognostic genes", "tolerance": null, "source": "chars 1732-1922 of source sha256 0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b"}, "evidence": [{"asset": "source:pmid:39991573", "locator": "chars 1732-1922 of source sha256 0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b", "quote": "Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39991573"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:39991573", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39991573' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39991573", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.105066", "sha256": "sha256:0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.105066", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39991573:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:16ae5caec2368307f33f4f02c81efd209b9b958a6ed950b8067470d95b23a5db", "bytes": 741, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T1", "version": null, "note": "Cellular filtration for each sample", "structure": {"pmcid": "PMC11843231", "section_index": 5, "section_title": "2.3 Totally 13 cell clusters were merged into 5 cell types", "row_count": 9, "column_count": 8}, "table": {"label": "Table 1", "caption": "Cellular filtration for each sample", "rows": [["Sample", "Rawdata", "ByLibSize", "ByFeature", "ByMT", "ByDoubletScore", "Remaining", "percent"], ["GSM4006644", "3272", "52", "52", "0", "165", "3003", "0.918"], ["GSM4006645", "5177", "156", "156", "0", "246", "4619", "0.892"], ["GSM4006646", "3157", "50", "50", "0", "103", "2954", "0.936"], ["GSM4006647", "5313", "160", "160", "0", "226", "4767", "0.897"], ["GSM4006648", "9350", "528", "526", "0", "721", "7575", "0.810"], ["GSM4751267", "6519", "283", "283", "0", "301", "5652", "0.867"], ["GSM4751268", "5696", "172", "172", "0", "288", "5064", "0.889"], ["GSM5329919", "6360", "278", "278", "0", "363", "5441", "0.856"]], "row_count": 9, "column_count": 8, "numeric_cells": 64, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:39991573:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d9bc700e9e3caddc2c0b41d232362b5ad2706c3cc1c8a687c29358c6a81bb5bc", "bytes": 545, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[2]#T2", "version": null, "note": "Marker genes of different cell types", "structure": {"pmcid": "PMC11843231", "section_index": 5, "section_title": "2.3 Totally 13 cell clusters were merged into 5 cell types", "row_count": 6, "column_count": 3}, "table": {"label": "Table 2", "caption": "Marker genes of different cell types", "rows": [["Cell Type", "Cluster", "Genes"], ["Urothelial cells", "Cluster0, Cluster1, Cluster2, Cluster3, Cluster4, Cluster5, Cluster7, Cluster8", "EPCAM, KRT8, KRT18"], ["Fibroblasts", "Cluster6", "PDPN, TAGLN, CD44"], ["Myeloid/macrophage", "Cluster9, Cluster11", "CD14, CSF1R, AIF1"], ["T cells", "Cluster10", "CD2, CD3D, CD3E"], ["Endothelial cells", "Cluster12", "PECAM1, FLT1, A2M"]], "row_count": 6, "column_count": 3, "numeric_cells": 6, "header_rows": 1, "locator": "section[5]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:39991573:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c26e2722d3d2fbdda9d0533bb4685d565de0101a553bd7d39ab92007c23dcfab", "bytes": 1235, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T3", "version": null, "note": "Expression of key genes in different cell types", "structure": {"pmcid": "PMC11843231", "section_index": 7, "section_title": "2.5 Fibroblasts and myeloid macrophages were crucial cell types", "row_count": 22, "column_count": 4}, "table": {"label": "Table 3", "caption": "Expression of key genes in different cell types", "rows": [["Gene", "avg_log2FC", "cluster", "Regulation"], ["ABHD11", "-0.267794688", "urothelial cells", "DOWN"], ["BIN1", "0.337796024", "myeloid/macrophage", "UP"], ["CALD1", "0.646281636", "fibroblasts", "UP"], ["CALD1", "-1.101214915", "myeloid/macrophage", "DOWN"], ["CFD", "-0.466170807", "endothelial cells", "DOWN"], ["CFD", "0.354230015", "fibroblasts", "UP"], ["CFD", "-0.466170807", "T cells", "DOWN"], ["FABP5", "0.436666572", "myeloid/macrophage", "UP"], ["FILIP1L", "0.410392469", "fibroblasts", "UP"], ["GSN", "0.602132628", "fibroblasts", "UP"], ["GSN", "-0.301609858", "urothelial cells", "DOWN"], ["ISYNA1", "0.341101688", "fibroblasts", "UP"], ["LPCAT4", "-0.366323428", "urothelial cells", "DOWN"], ["MYH11", "0.863408357", "fibroblasts", "UP"], ["OLFML3", "0.551111708", "myeloid/macrophage", "UP"], ["S100A14", "-0.399176017", "myeloid/macrophage", "DOWN"], ["TGFB1I1", "0.642138789", "fibroblasts", "UP"], ["TINAGL1", "0.66843065", "fibroblasts", "UP"], ["TINAGL1", "-0.29114086", "myeloid/macrophage", "DOWN"], ["TPM1", "0.885118002", "fibroblasts", "UP"], ["TPM1", "-0.693462753", "myeloid/macrophage", "DOWN"]], "row_count": 22, "column_count": 4, "numeric_cells": 24, "header_rows": 1, "locator": "section[7]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:39991573:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:347e7d8589f304c0e6f138e507234f0ba3dc8446f66228799744e35c8c45a7c2", "bytes": 1301, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T4", "version": null, "note": "The information and functions of five prognostic genes encoded proteins", "structure": {"pmcid": "PMC11843231", "section_index": 10, "section_title": "2.8 Establishment and validation of the risk model", "row_count": 6, "column_count": 6}, "table": {"label": "Table 4", "caption": "The information and functions of five prognostic genes encoded proteins", "rows": [["Gene", "Ensembl", "Protein name", "Gene Ontology", "Location", "Diseases"], ["XAGE2", "ENSG00000155622", "X Antigen Family Member 2", "Enables protein binding", "Nucleus, Cytoskeleton, Extracellular", "Germ Cell Tumor, Sarcoma"], ["MAP1A", "ENSG00000166963", "Microtubule Associated Protein 1A", "Enables actin binding, Enables protein binding", "Cytosol, Nucleus, Cytoskeleton", "Macular Degeneration, Age-Related, and Amyotrophic Lateral Sclerosis"], ["CASQ2", "ENSG00000118729", "Calsequestrin 2", "Enables calcium ion binding, Enables protein binding", "Endoplasmic reticulum, Cytosol, Mitochondrion", "Ventricular Tachycardia, Catecholaminergic Polymorphic, and Catecholaminergic Polymorphic Ventricular Tachycardia"], ["FXYD6", "ENSG00000137726", "FXYD Domain Containing Ion Transport Regulator 6", "Enables molecular_function, Enables protein binding", "Plasma membrane", "Hypomagnesemia, Renal"], ["CTSE", "ENSG00000196188", "Cathepsin E", "Enables aspartic-type endopeptidase activity, Enables peptidase activity", "Endosome, Lysosome", "Langerhans Cell Histiocytosis and Gastric Papillary Adenocarcinoma"]], "row_count": 6, "column_count": 6, "numeric_cells": 9, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T4"}}], "gaps": ["asset:source:pmid:39991573 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39991573", "asset:table:pmid:39991573:1", "asset:table:pmid:39991573:2", "asset:table:pmid:39991573:3", "asset:table:pmid:39991573:4"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39991573"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "23d74bbf0880ae61c90b8577abccf15047d3dcefbaa1b136fd0cab00f3139cac", "source_hash": "0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b", "raw_response_sha256": "sha256:383d0d46bbaaa9a879a122e9c6719a8534390f5498f7629d2e105fc254ddafd9", "raw_response_chars": 5537}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "c77a4b3775c616c964ff039fb85724fd06a492c48e123bcec43eb12be6ce35e1", "source_hash": "0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b", "raw_response_sha256": "sha256:ea9bd086346dfcf18042e4ec00b849d88b2cf075db0d6083cda158176887787b", "raw_response_chars": 68710}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "3f0162bf1ee582df0b654e7c944bee9374e6a1833ceba7ac843d266d5f38c9c2", "source_hash": "0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b", "raw_response": "{\"parent_value\":5,\"unit\":\"prognostic genes\",\"evidence\":\"Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.\",\"target_result\":\"The main risk model was developed using five prognostic genes.\",\"number_stated\":true}", "reading": {"parent_value": 5, "unit": "prognostic genes", "evidence": "Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.", "target_result": "The main risk model was developed using five prognostic genes.", "number_stated": true, "source_locator": "chars 1732-1922 of source sha256 0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b"}, "recorded_at": "2026-10-31T15:31:37.229795+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "beb498451e708fb29a0ccbb3238226422fbee41d630cf732897f2696b1ba4d83", "source_hash": "0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b", "raw_response": "<think>We need produce JSON only based source text. Need find single numerical result replication registered target main finding headline numerical result paper states. Need carefully infer likely expected answer from supplied abstract and excerpts. Main finding five prognostic genes, 15 key genes. \"headline numerical result\" target = headline numerical result paper states for main finding. Need decide which number and unit. Source text main result maybe risk model performance omitted? We only have given source. Need extract numerical result attached target. They emphasize \"value paper itself states for registered target\" and exact contiguous quote attribution via parenthetical list respectively etc. Registered target phrasing vague \"the headline numerical result the paper states for its main finding\". Need select maybe \"five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6)\" headline number 5? Unit \"prognostic genes\". Or \"15 key genes\" main finding? Need analyze.\n\nPaper title \"Integrative multi-omics and machine learning identify a robust signature for discriminating prognosis and therapeutic targets in bladder cancer\". Abstract results key: \"A total of 15 key genes were obtained by crossing 284 candidate genes with 510 scRNA-DEGs. Patients in the TCGA-BLCA dataset were categorized into two subtypes based on the 15 key genes. Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score. A total of 1089 GO entries and 49 KEGG pathways... Immunization score, matrix score, ESTIMATE score ...\". Main headline numerical maybe C-index of nomogram? Not supplied. They likely want 5? Need understand generic task format. We have instruction from developer claims extraction. User asks \"Read supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\"\n\nWe need fulfill JSON fields. Need target numerical result main finding. Perhaps five genes. Headline main finding is prognostic five-gene signature. It has number five. Unit \"prognostic genes\". Evidence quote \"Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.\" Or abstract \"Conclusion: CTSE, XAGE2, MAP1A, CASQ2 and FXYD6 were selected as prognostic genes in BLCA, risk model and nomogram model predicting the prognosis of BLCA patients were constructed.\" Not numerical. Results contains five directly. If user emphasizes \"value ... not calculated, converted...\" maybe wants not count parenthetical but number in text. They deliberately use five spelled number. Parent_value 5. Unit likely \"prognostic genes\". Could unit be \"genes\"? They say unit must be unit paper prints. \"five prognostic genes\" is unit phrase. Could output unit \"prognostic genes\". target_result explanation \"The paper reports a risk model using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6).\" number true. Evidence exact clause entire sentence.\n\nBut let's not rush. Need consider \"headline numerical result\" could 15 key genes as main result. Main finding \"identify a robust signature\". Five prognostic genes used risk model. They might want \"15\" key genes rather than \"5\". Which \"registered target\" \"the headline numerical result the paper states for its main finding\" indicates usually extraction benchmark with headline registered target e.g. \"the number of lncRNAs in the signature\". Here no specific target name. They likely expect main result risk model comprising five prognostic genes. Could also be number \"43\" drugs, \"81\", \"N=401\". They explicitly call headline. Most headline numerical result in abstract maybe \"five prognostic genes\". Need reason linguistic \"single numerical result that a replication of the registered target has to reproduce.\" Registered target is \"the headline numerical result the paper states for its main finding\". If main finding five gene risk signature, replicate five. 15 key genes also candidate, but final signature five. Title robust signature, conclusion 5 genes. Need report 5 not 15. They might expect \"five prognostic genes\" exactly. Unit \"genes\" perhaps.\n\nWe can choose evidence clause \"Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.\" Full sentence. Or quote second part of conclusion doesn't include number. First sentence best.\n\nWe need reply JSON only no markdown. parent_value 5 number, unit \"prognostic genes\", evidence exact, target_result string \"The paper reports a risk model developed using five prognostic genes: CTSE, XAGE2, MAP1A, CASQ2, and FXYD6.\" Does \"headline number only\" imply target_result no other numerical results, okay mentions five again not 15. Maybe target_result concise \"The risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6).\" It has five, no extra values. Good.\n\nBut maybe unit should be \"genes\". They ask unit as printed. Printed \"prognostic genes\". Use that. JSON no extra props. Need avoid unquoted number? parent 5.\n\nWe must be certain there is no better headline number like N=401 or 1089 GO. Those are supporting results not main. Five is most headline. Need not list alternative. We can say \"The main risk model uses five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6).\" Good.\n\nLet's thoroughly examine source for other main performance result maybe no, but not supplied. Their conditional no number instruction generic. There is number. Five directly. Don't calculate count of list; source itself \"five prognostic genes\". Great.\n\nNeed evidence exact contiguous quotation from source. Full sentence exactly:\n\"Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.\"\nYes matches. Should quote without outer quotation? evidence string plain with quotes only JSON. exact contiguous. Could include preceding \"Next,\" okay. Need not shorten, whole clause for attribution. They instruct \"When that is how the text links them, quote the whole clause so a reader can check attribution for themselves.\" Whole sentence safest.\n\nWe can final JSON.</think>\n\n{\n  \"parent_value\": 5,\n  \"unit\": \"prognostic genes\",\n  \"evidence\": \"Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.\",\n  \"target_result\": \"The main risk model was developed using five prognostic genes: CTSE, XAGE2, MAP1A, CASQ2, and FXYD6.\",\n  \"number_stated\": true\n}", "reading": {"parent_value": 5, "unit": "prognostic genes", "evidence": "Next, a risk model was developed using five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6), and a nomogram model was developed using age, pathologic T, pathologic N, and risk score.", "target_result": "The main risk model was developed using five prognostic genes: CTSE, XAGE2, MAP1A, CASQ2, and FXYD6.", "number_stated": true, "source_locator": "chars 1732-1922 of source sha256 0d33282e6672bc558ef71b3890116698a55a01e7f29048cdda8305b2cf38f83b"}, "recorded_at": "2026-10-31T15:31:53.027683+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A 15-gene key-gene signature was identified, from which five prognostic genes (CTSE, XAGE2, MAP1A, CASQ2, and FXYD6) were selected to construct a bladder-cancer risk model and nomogram.", "minimax_alt": "The main finding is a five-gene prognostic signature comprising CTSE, XAGE2, MAP1A, CASQ2, and FXYD6, used to develop a bladder cancer risk model and a nom incorporating age, pathologic T, pathologic N, and risk score.", "decisive": false}, "work_type": {"minimax": "physical_data_generation", "minimax_alt": "analysis_only_for_target", "decisive": true}, "physical_methods": {"minimax": ["Transcriptomic sequencing of six bladder cancer tumor tissues and six paraneoplastic tissue samples", "Proteomic sequencing of six bladder cancer tumor tissues and six paraneoplastic tissue samples", "Protein acetylation sequencing of six bladder cancer tumor tissues and six paraneoplastic tissue samples"], "minimax_alt": ["transcriptomic sequencing", "proteomic sequencing", "protein acetylation sequencing"], "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis with DESeq2", "Differential protein expression analysis with MaxQuant-Andromeda", "Differential acetylated-protein analysis", "Consistency clustering analysis", "Cox regression analysis", "Least absolute shrinkage and selection operator (LASSO) Cox regression", "Independent prognostic analysis using univariate and multivariate Cox regression", "Nomogram construction", "Gene set enrichment analysis (GSEA)", "Immune cell infiltration analysis", "Mutation analysis", "Drug sensitivity analysis", "Wilcoxon rank-sum test", "Log-rank test"], "minimax_alt": ["DESeq2 differential expression analysis", "MaxQuant-Andromeda differential protein expression analysis", "intersection of acetylation-regulated candidate genes with scRNA-DEGs", "consistency clustering analysis", "Cox regression analysis", "least absolute shrinkage and selection operator (LASSO) Cox regression", "univariate Cox regression analysis", "Proportional Hazards (PH) hypothesis test", "multivariate Cox regression analysis", "nomogram modeling", "ROC analysis", "calibration analysis", "log-rank test", "Wilcoxon rank-sum test", "gene set enrichment analysis (GSEA)", "immune cell infiltration analysis", "mutation analysis", "drug sensitivity analysis"], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:f474876e6dc6e6206260f1f9e2a7e47416812020e67062895a7f4d0d61d490a8", "type": "sep_package", "label": "SEP v1 package for pmid:39991573"}], "activities": [{"id": "activity:conversion:pmid:39991573", "type": "conversion", "used": ["package:f474876e6dc6e6206260f1f9e2a7e47416812020e67062895a7f4d0d61d490a8"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39991573", "parent_hash": "sha256:116417bef2243ffac02e9bb5b8b25bb44897400a83ed6ec41835db475267da76", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39991573 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39991573' does not resolve to a declared asset", "targets"]},"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":"2026-11-04T03:50:35+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}}}