{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26292924", "kind": "science-record", "revision": 9, "content_hash": "sha256:70a04c7c4d2de3d11650c34b2b5e1060c28031a541cfcbfad1c0dffdc5be3591", "created_at": "2026-11-01T15:40:10Z", "updated_at": "2026-11-01T22:42:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Large-scale RNA-Seq Transcriptome Analysis of 4043 Cancers and 548 Normal Tissue Controls across 12 TCGA Cancer Types.", "doi": "10.1038/srep13413", "pmid": "26292924", "authors": ["Li Peng", "Xiu Wu Bian", "Di Kang Li", "Chuan Xu", "Guang Ming Wang", "Qing You Xia", "Qing Xiong"], "journal": "Scientific reports", "year": 2015, "abstract": "The Cancer Genome Atlas (TCGA) has accrued RNA-Seq-based transcriptome data for more than 4000 cancer tissue samples across 12 cancer types, translating these data into biological insights remains a major challenge. We analyzed and compared the transcriptomes of 4043 cancer and 548 normal tissue samples from 21 TCGA cancer types, and created a comprehensive catalog of gene expression alterations for each cancer type. By clustering genes into co-regulated gene sets, we identified seven cross-cancer gene signatures altered across a diverse panel of primary human cancer samples. A 14-gene signature extracted from these seven cross-cancer gene signatures precisely differentiated between cancerous and normal samples, the predictive accuracy of leave-one-out cross-validation (LOOCV) were 92.04%, 96.23%, 91.76%, 90.05%, 88.17%, 94.29%, and 99.10% for BLCA, BRCA, COAD, HNSC, LIHC, LUAD, and LUSC, respectively. A lung cancer-specific gene signature, containing SFTPA1 and SFTPA2 genes, accurately distinguished lung cancer from other cancer samples, the predictive accuracy of LOOCV for TCGA and GSE5364 data were 95.68% and 100%, respectively. These gene signatures provide rich insights into the transcriptional programs that trigger tumorigenesis and metastasis, and many genes in the signature gene panels may be of significant value to the diagnosis and treatment of cancer.", "claims": [{"id": "claim-method", "statement": "We employed leave-one-out cross-validation (LOOCV) to assess whether or not this 14-gene signature can be used to differentiate between the normal and cancerous tissue samples of those seven cancer types. Machine learning techniques, for example support vector machines, have been playing a vital role in sample classification141,142,143,144. LOOCV was performed using SVM-light145 (http://svmlight.joachims.org/) that is an imple", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26292924", "locator": "sections[20] \"Leave-one-out cross validation\" paragraph 2", "quote": "We employed leave-one-out cross-validation (LOOCV) to assess whether or not this 14-gene signature can be used to differentiate between the normal and cancerous tissue samples of those seven cancer types. Machine learning techniques, for example support vector machines, have been playing a vital role in sample classification141,142,143,144. LOOCV was performed using SVM-light145 (http://svmlight.joachims.org/) that is an imple"}], "state": "complete"}, {"id": "claim-data-access", "statement": "Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26292924", "locator": "sections[26] \"Data sets\" paragraph 2", "quote": "Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp)."}], "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:26292924"], "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:GSE40419"], "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:GSE40419"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26292924", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/srep13413", "sha256": "sha256:81d043b7dac64c7575b6ca59fa03cc40673c0a46b5a39fe2faaa0ae2aca45658", "bytes": 75536, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/srep13413", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4544034", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE40419", "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=GSE40419", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40419", "version": null, "note": "Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM993606", "GSM993607", "GSM993608", "GSM993610", "GSM993611", "GSM993612", "GSM993613", "GSM993614", "GSM993616", "GSM993617", "GSM993618", "GSM993619", "GSM993620", "GSM993621", "GSM993622", "GSM993623", "GSM993624", "GSM993625", "GSM993626", "GSM993627", "GSM993628", "GSM993629", "GSM993630", "GSM993631", "GSM993632", "GSM993633", "GSM993634", "GSM993635", "GSM993636", "GSM993637", "GSM993638", "GSM993639", "GSM993640", "GSM993641", "GSM993642", "GSM993643", "GSM993644", "GSM993645", "GSM993646", "GSM993647", "GSM993648", "GSM993649", "GSM993650", "GSM993651", "GSM993652", "GSM993653", "GSM993654", "GSM993655", "GSM993656", "GSM993657", "GSM993658", "GSM993659", "GSM993660", "GSM993661", "GSM993662", "GSM993663", "GSM993664", "GSM993665", "GSM993666", "GSM993667", "GSM993668", "GSM993669", "GSM993670", "GSM993671", "GSM993672", "GSM993673", "GSM993674", "GSM993675", "GSM993676", "GSM993677", "GSM993678", "GSM993679", "GSM993680", "GSM993681", "GSM993682", "GSM993683", "GSM993684", "GSM993685", "GSM993686", "GSM993687", "GSM993688", "GSM993689", "GSM993690", "GSM993691", "GSM993692", "GSM993693", "GSM993694", "GSM993695", "GSM993696", "GSM993697", "GSM993698", "GSM993699", "GSM993700", "GSM993701", "GSM993702", "GSM993703", "GSM993704", "GSM993705", "GSM993706", "GSM993707", "GSM993708", "GSM993709", "GSM993710", "GSM993711", "GSM993712", "GSM993713", "GSM993714", "GSM993715", "GSM993716", "GSM993717", "GSM993718", "GSM993719", "GSM993720", "GSM993721", "GSM993722", "GSM993723", "GSM993724", "GSM993725", "GSM993726", "GSM993727", "GSM993728", "GSM993729", "GSM993730", "GSM993731", "GSM993732", "GSM993733", "GSM993734", "GSM993735", "GSM993736", "GSM993737", "GSM993738", "GSM993739", "GSM993740", "GSM993741", "GSM993742", "GSM993743", "GSM993744", "GSM993745", "GSM993746", "GSM993747", "GSM993748", "GSM993749", "GSM993750", "GSM993751", "GSM993752", "GSM993753", "GSM993754", "GSM993755", "GSM993756", "GSM993757", "GSM993758", "GSM993759", "GSM993760", "GSM993761", "GSM993762", "GSM993763", "GSM993764", "GSM993765", "GSM993766", "GSM993767", "GSM993768", "GSM993769", "GSM993770", "GSM993771"], "sample_count": 164, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "The transcriptional landscape and mutational profile of lung adenocarcinoma", "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:GSE50760", "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=GSE50760", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50760", "version": null, "note": "Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1228184", "GSM1228185", "GSM1228186", "GSM1228187", "GSM1228188", "GSM1228189", "GSM1228190", "GSM1228191", "GSM1228192", "GSM1228193", "GSM1228194", "GSM1228195", "GSM1228196", "GSM1228197", "GSM1228198", "GSM1228199", "GSM1228200", "GSM1228201", "GSM1228202", "GSM1228203", "GSM1228204", "GSM1228205", "GSM1228206", "GSM1228207", "GSM1228208", "GSM1228209", "GSM1228210", "GSM1228211", "GSM1228212", "GSM1228213", "GSM1228214", "GSM1228215", "GSM1228216", "GSM1228217", "GSM1228218", "GSM1228219", "GSM1228220", "GSM1228221", "GSM1228222", "GSM1228223", "GSM1228224", "GSM1228225", "GSM1228226", "GSM1228227", "GSM1228228", "GSM1228229", "GSM1228230", "GSM1228231", "GSM1228232", "GSM1228233", "GSM1228234", "GSM1228235", "GSM1228236", "GSM1228237"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Gene expression profiling study by RNA-seq in colorectal 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": "asset:table:pmid:26292924:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3c74aabbddd7427ca76137ad4c86d2a82cb76a0e53126484cf5a304729e27f2f", "bytes": 277, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t1", "version": null, "note": "The percentage of common genes and gene sets in top 3% most differentially expressed genes and gene sets between 12 cancer types*.", "structure": {"pmcid": "PMC4544034", "section_index": 4, "section_title": "Gene-level differential expression analysis of transcriptomes", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "The percentage of common genes and gene sets in top 3% most differentially expressed genes and gene sets between 12 cancer types*.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[4]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:26292924:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0be43b13746c73da1cd38d3ba2bb702d267892bd1a3f4c62b304f81ca69307ac", "bytes": 208, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#t2", "version": null, "note": "Significant gene sets at FDR < 0.15 from 12 types of cancers.", "structure": {"pmcid": "PMC4544034", "section_index": 6, "section_title": "Gene set association analysis of TCGA data", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Significant gene sets at FDR < 0.15 from 12 types of cancers.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[6]/table-wrap[1]#t2"}}, {"id": "asset:table:pmid:26292924:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a848b794f8fc85ee023c778e01148a98d596a10a683906477a8bea0cf624499c", "bytes": 1048, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#t3", "version": null, "note": "List of lung disease-associated genes in CLUSTER1520.", "structure": {"pmcid": "PMC4544034", "section_index": 16, "section_title": "Gene signatures for lung cancers.", "row_count": 9, "column_count": 3}, "table": {"label": "Table 3", "caption": "List of lung disease-associated genes in CLUSTER1520.", "rows": [["Symbol", "Full name", "Lung diseases"], ["SFTPA2", "surfactant, pulmonary-associated protein A2", "lung cancer101,102,103,104, acute and chronic lung disease105,106"], ["SFTPA1", "surfactant, pulmonary-associated protein A1", "lung cancer103, acute and chronic lung disease107,108,109"], ["ROS1", "ROS proto-oncogene 1, receptor tyrosine kinase", "lung cancer165,166,"], ["ABCA3", "ATP-binding cassette, sub-family A (ABC1), member 3", "pulmonary fibrosis167, respiratory disease168,169,170"], ["AQP4", "aquaporin 4", "lung cancer171,172"], ["HHIP", "hedgehog interacting protein", "lung cancer173, chronic obstructive pulmonary disease174, abnormal lung function175"], ["SLC34A2", "solute carrier family 34, member 2", "pulmonary alveolar microlithiasis176,177"], ["IL6R", "interleukin 6 receptor", "chronic obstructive pulmonary disease178, abnormal lung function179"]], "row_count": 9, "column_count": 3, "numeric_cells": 14, "header_rows": 1, "locator": "section[16]/table-wrap[1]#t3"}}, {"id": "asset:table:pmid:26292924:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0891ae514e09f3866d02171e0ba5a9a929afd0f7cf86a2fce0d8dce868fce945", "bytes": 864, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#t4", "version": null, "note": "Number of cancer and normal samples of 12 cancer types.", "structure": {"pmcid": "PMC4544034", "section_index": 26, "section_title": "Data sets", "row_count": 13, "column_count": 4}, "table": {"label": "Table 4", "caption": "Number of cancer and normal samples of 12 cancer types.", "rows": [["Abbreviation", "Full Name", "Number of Cancers", "Number of Normals"], ["BLCA", "bladder urothelial carcinoma", "185", "16"], ["BRCA", "breast invasive carcinoma", "955", "106"], ["COAD", "colon adenocarcinoma", "244", "23"], ["HNSC", "head and neck squamous cell carcinoma", "353", "39"], ["LIHC", "liver hepatocellular carcinoma", "123", "46"], ["LUAD", "lung adenocarcinoma", "450", "58"], ["LUSC", "lung squamous cell carcinoma", "398", "44"], ["KICH", "kidney chromophobe", "66", "25"], ["KIRC", "kidney renal clear cell carcinoma", "497", "72"], ["KIRP", "kidney renal papillary cell carcinoma", "127", "28"], ["PRAD", "prostate adenocarcinoma", "166", "38"], ["THCA", "thyroid carcinoma", "479", "53"]], "row_count": 13, "column_count": 4, "numeric_cells": 24, "header_rows": 1, "locator": "section[26]/table-wrap[1]#t4"}}], "gaps": ["asset:data:geo:GSE40419 not downloaded", "asset:data:geo:GSE40419 licence not read", "asset:data:geo:GSE50760 not downloaded", "asset:data:geo:GSE50760 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We employed leave-one-out cross-validation (LOOCV) to assess whether or not this 14-gene signature can be used to differentiate between the normal and cancerous tissue samples of those seven cancer types. Machine learning techniques, for example support vector machines, have been playing a vital role in sample classification141,142,143,144. LOOCV was performed using SVM-light145 (http://svmlight.joachims.org/) that is an imple"}}, {"id": "method-2", "family": "differential_expression", "specific": "edger", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "edgeR"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE40419", "GSE50760"], "resolved_accessions": ["GSE40419", "GSE50760"], "statements": ["Transcriptome data and clinical data were obtained from the TCGA Data Portal (https://tcga-data.nci.nih.gov/tcga/tcgaHome2.jsp)."], "basis": "The paper names GSE40419, GSE50760 in TCGA Data Portal; non-TCGA data sets GSE40419 and GSE50760 and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:26292924", "data:geo:GSE40419", "asset:table:pmid:26292924:1", "asset:table:pmid:26292924:2", "asset:table:pmid:26292924:3", "asset:table:pmid:26292924:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE40419"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:26292924", "type": "paper", "label": "pmid:26292924"}, {"id": "source:pmid:26292924", "type": "manuscript", "label": "PMID 26292924 full text"}, {"id": "data:geo:GSE40419", "type": "dataset", "label": "GEO GSE40419"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26292924", "type": "paper", "label": "pmid:26292924"}, {"id": "source:pmid:26292924", "type": "manuscript", "label": "PMID 26292924 full text"}, {"id": "data:geo:GSE40419", "type": "dataset", "label": "GEO GSE40419"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26292924", "type": "extraction", "used": ["source:pmid:26292924"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE40419", "type": "accession_resolution", "used": ["data:geo:GSE40419"], "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:26292924", "parent_hash": "sha256:0af10611a5caeac53f301fa1f815292bab1352fb28e7bf4d57c2e4fe85a07eb9", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE40419 licence not read", "asset:data:geo:GSE40419 not downloaded", "asset:data:geo:GSE50760 licence not read", "asset:data:geo:GSE50760 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We employed leave-one-out cross-validation (LOOCV) to assess whether or not this 14-gene signature can be used to differentiate between the normal and cancerous tissue samples of those seven cancer types. Machine learning techniques, for example support vector machines, have been playing a vital role in sample classification141,142,143,144. LOOCV was performed using SVM-light145 (http://svmlight.joachims.org/) that is an imple"], "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":"2026-11-04T01:50:35+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}}}