{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31138213", "kind": "science-record", "revision": 8, "content_hash": "sha256:de39fd9804ed6a4d8c0463bb9c29a503dd0e70afe1d6793757ed4500a5011c79", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T22:43:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Assessment of risk based on variant pathways and establishment of an artificial neural network model of thyroid cancer.", "doi": "10.1186/s12881-019-0829-4", "pmid": "31138213", "authors": ["Yinlong Zhao", "Lingzhi Zhao", "Tiezhu Mao", "Lili Zhong"], "journal": "BMC medical genetics", "year": 2019, "abstract": "BACKGROUND: This study aimed to establish an artificial neural network (ANN) model based on variant pathways to predict the risk of thyroid cancer.\nMETHODS: The RNASeq data of 482 thyroid cancer samples were downloaded from the TCGA database. The samples were divided into low-risk and high-risk groups, followed by identification of differentially expressed genes (DEGs). Co-expression analysis and pathway enrichment analysis were then performed. The variant pathways were screened according to the functional deviation score of each pathway, and an ANN model was established. Finally, the efficiency of the ANN model for risk assessment was validated by survival analysis and analysis of an independent microarray dataset (GSE34289) for thyroid cancer.\nRESULTS: In total, 190 DEGs (85 up-regulated and 105 down-regulated) were identified between the low-risk and high-risk groups. Ten risk-related variant pathways were identified between the low-risk and high-risk groups, which were related to inflammatory and immune responses. Based on these variant pathways, an ANN model was built, consisting of an input layer, two hidden layers, and an output layer, corresponding to 15, 8, 5, and 1 neuron, respectively. Survival analysis showed that this model could effectively distinguish the samples with different risks. Analysis of microarray dataset GSE34289 showed that the accuracy of this model for predicating low-risk and high-risk samples was 77.5 and 86.0%, respectively.\nCONCLUSIONS: This study suggests that the ANN model based on variant pathways can be used for effectively evaluating the risk of thyroid cancer.", "claims": [{"id": "claim-method", "statement": "The DEGs between high-risk samples and low-risk samples were then identified using the limma package (version 3.10.3, http://www.bioconductor.org/packages/2.9/bioc/html/limma.html) [21].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31138213", "locator": "sections[5] \"Data normalization and identification of DEGs\" paragraph 2", "quote": "The DEGs between high-risk samples and low-risk samples were then identified using the limma package (version 3.10.3, http://www.bioconductor.org/packages/2.9/bioc/html/limma.html) [21]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data GSE34289 was downloaded from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31138213", "locator": "sections[24] \"notes\" paragraph 1", "quote": "The microarray data GSE34289 was downloaded from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi)."}], "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:31138213"], "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:GSE34289"], "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:GSE34289"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31138213", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12881-019-0829-4", "sha256": "sha256:a5cd0d3d09d0327a9fecfe60b62bcb2a46ae22935b5a6019ecc2513881fc8fe0", "bytes": 25499, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12881-019-0829-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6537382", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE34289", "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=GSE34289", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE34289", "version": null, "note": "The microarray data GSE34289 was downloaded from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data GSE34289 was downloaded from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM846410", "GSM846411", "GSM846412", "GSM846413", "GSM846414", "GSM846415", "GSM846416", "GSM846417", "GSM846418", "GSM846419", "GSM846420", "GSM846421", "GSM846422", "GSM846423", "GSM846424", "GSM846425", "GSM846426", "GSM846427", "GSM846428", "GSM846429", "GSM846430", "GSM846431", "GSM846432", "GSM846433", "GSM846434", "GSM846435", "GSM846436", "GSM846437", "GSM846438", "GSM846439", "GSM846440", "GSM846441", "GSM846442", "GSM846443", "GSM846444", "GSM846445", "GSM846446", "GSM846447", "GSM846448", "GSM846449", "GSM846450", "GSM846451", "GSM846452", "GSM846453", "GSM846454", "GSM846455", "GSM846456", "GSM846457", "GSM846458", "GSM846459", "GSM846460", "GSM846461", "GSM846462", "GSM846463", "GSM846464", "GSM846465", "GSM846466", "GSM846467", "GSM846468", "GSM846469", "GSM846470", "GSM846471", "GSM846472", "GSM846473", "GSM846474", "GSM846475", "GSM846476", "GSM846477", "GSM846478", "GSM846479", "GSM846480", "GSM846481", "GSM846482", "GSM846483", "GSM846484", "GSM846485", "GSM846486", "GSM846487", "GSM846488", "GSM846489", "GSM846490", "GSM846491", "GSM846492", "GSM846493", "GSM846494", "GSM846495", "GSM846496", "GSM846497", "GSM846498", "GSM846499", "GSM846500", "GSM846501", "GSM846502", "GSM846503", "GSM846504", "GSM846505", "GSM846506", "GSM846507", "GSM846508", "GSM846509", "GSM846510", "GSM846511", "GSM846512", "GSM846513", "GSM846514", "GSM846515", "GSM846516", "GSM846517", "GSM846518", "GSM846519", "GSM846520", "GSM846521", "GSM846522", "GSM846523", "GSM846524", "GSM846525", "GSM846526", "GSM846527", "GSM846528", "GSM846529", "GSM846530", "GSM846531", "GSM846532", "GSM846533", "GSM846534", "GSM846535", "GSM846536", "GSM846537", "GSM846538", "GSM846539", "GSM846540", "GSM846541", "GSM846542", "GSM846543", "GSM846544", "GSM846545", "GSM846546", "GSM846547", "GSM846548", "GSM846549", "GSM846550", "GSM846551", "GSM846552", "GSM846553", "GSM846554", "GSM846555", "GSM846556", "GSM846557", "GSM846558", "GSM846559", "GSM846560", "GSM846561", "GSM846562", "GSM846563", "GSM846564", "GSM846565", "GSM846567", "GSM846568", "GSM846569", "GSM846570", "GSM846571", "GSM846572", "GSM846573", "GSM846574", "GSM846575", "GSM846576", "GSM846577", "GSM846578", "GSM846579", "GSM846580", "GSM846581", "GSM846582", "GSM846583", "GSM846584", "GSM846585", "GSM846586", "GSM846587", "GSM846588", "GSM846589", "GSM846590", "GSM846591", "GSM846592", "GSM846593", "GSM846594", "GSM846595", "GSM846596", "GSM846597", "GSM846598", "GSM846599", "GSM846600", "GSM846601", "GSM846602", "GSM846603", "GSM846604", "GSM846605", "GSM846606", "GSM846607", "GSM846608", "GSM846609", "GSM846610", "GSM846611", "GSM846612", "GSM846613", "GSM846614", "GSM846615", "GSM846616", "GSM846617", "GSM846618", "GSM846619", "GSM846620", "GSM846621", "GSM846622", "GSM846623", "GSM846624", "GSM846625", "GSM846626", "GSM846627", "GSM846628", "GSM846629", "GSM846630", "GSM846631", "GSM846632", "GSM846633", "GSM846634", "GSM846635", "GSM846636", "GSM846637", "GSM846638", "GSM846639", "GSM846640", "GSM846641", "GSM846642", "GSM846643", "GSM846644", "GSM846645", "GSM846646", "GSM846647", "GSM846648", "GSM846649", "GSM846650", "GSM846651", "GSM846652", "GSM846653", "GSM846654", "GSM846655", "GSM846656", "GSM846657", "GSM846658", "GSM846659", "GSM846660", "GSM846661", "GSM846662", "GSM846663", "GSM846664", "GSM846665", "GSM846666", "GSM846667", "GSM846668", "GSM846669", "GSM846670", "GSM846671", "GSM846672", "GSM846673", "GSM846674", "GSM846675", "GSM846676", "GSM846677", "GSM846678", "GSM846679", "GSM846680", "GSM846681", "GSM846682", "GSM846683", "GSM846684", "GSM846685", "GSM846686", "GSM846687", "GSM846688", "GSM846689", "GSM846690", "GSM846691", "GSM846692", "GSM846693", "GSM846694", "GSM846695", "GSM846696", "GSM846697", "GSM846698", "GSM846699", "GSM846700", "GSM846701", "GSM846702", "GSM846703", "GSM846704", "GSM846705", "GSM846706", "GSM846707", "GSM846708", "GSM846709", "GSM846710", "GSM846711", "GSM846712", "GSM846713", "GSM846714", "GSM846715", "GSM846716", "GSM846717", "GSM846718", "GSM846719", "GSM846720", "GSM846721", "GSM846722", "GSM846723", "GSM846724", "GSM846725", "GSM846726", "GSM846727", "GSM846728", "GSM846729", "GSM846730", "GSM846731", "GSM846732", "GSM846733", "GSM846734", "GSM846735", "GSM846736", "GSM846737", "GSM846738", "GSM846739", "GSM846740", "GSM846741", "GSM846742", "GSM846743", "GSM846744", "GSM846745", "GSM846746", "GSM846747", "GSM846748", "GSM846749", "GSM846750", "GSM846751", "GSM846752", "GSM846753", "GSM846754", "GSM846755", "GSM846756", "GSM846757", "GSM846758", "GSM846759", "GSM846760", "GSM846761", "GSM846762", "GSM846763", "GSM846764", "GSM846765", "GSM846766", "GSM846767", "GSM846768", "GSM846769", "GSM846770", "GSM846771", "GSM846772", "GSM846773", "GSM846774", "GSM846775", "GSM846776", "GSM846777"], "sample_count": 367, "group_sizes": null, "group_sizes_basis": null, "platform": "5175;14961", "taxon": "Homo sapiens", "title": "Preoperative Diagnosis of Benign Thyroid Nodules with Indeterminate Cytology", "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:31138213:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:88a434947eaf9b0620f94479be89b903b652e3afa0347bf8d35629f643763ee9", "bytes": 2724, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab1", "version": null, "note": "KEGG pathway enrichment analysis for differentially expressed genes", "structure": {"pmcid": "PMC6537382", "section_index": 13, "section_title": "Variant pathway analysis and establishment of ANN model for risk assessment", "row_count": 22, "column_count": 5}, "table": {"label": "Table 1", "caption": "KEGG pathway enrichment analysis for differentially expressed genes", "rows": [["Term", "Enrichment score", "Count", "P value", "Genes"], ["Graft-versus-host disease", "23.93073593", "8", "2.52E-08", "CD86, CD80, HLA-DRB5, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Allograft rejection", "21.34362934", "8", "5.89E-08", "CD86, CD80, HLA-DRB5, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Type I diabetes mellitus", "18.80272109", "8", "1.48E-07", "CD86, CD80, HLA-DRB5, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Autoimmune thyroid disease", "15.18681319", "8", "6.80E-07", "CD86, CD80, HLA-DRB5, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Viral myocarditis", "13.85463659", "8", "1.29E-06", "CD86, CD80, CASP8, HLA-DRB5, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Herpes simplex infection", "6.473067916", "12", "1.59E-06", "DDX58, HMGN1, IFIH1, GTF2IRD1, CASP8, HLA-DRB5, JAK2, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Tuberculosis", "5.577078289", "10", "5.85E-05", "FCGR1A, CASP8, HLA-DRB5, FCER1G, ATP6V1H, JAK2, CLEC7A, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Cell adhesion molecules (CAMs)", "6.256539235", "9", "7.58E-05", "CLDN16, CD86, CD80, HLA-DRB5, L1CAM, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Intestinal immune network for IgA production", "12.60182371", "6", "9.50E-05", "CD86, CD80, HLA-DRB5, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Phagosome", "5.806722689", "9", "1.28E-04", "FCGR1A, HLA-DRB5, ITGB5, ATP6V1H, CLEC7A, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Asthma", "16.45238095", "5", "2.05E-04", "HLA-DRB5, FCER1G, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Rheumatoid arthritis", "7.852272727", "7", "2.26E-04", "CD86, CD80, HLA-DRB5, ATP6V1H, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Influenza A", "5.10591133", "9", "3.11E-04", "DDX58, IFIH1, HLA-DRB5, JAK2, CPSF4, FAS, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Systemic lupus erythematosus", "5.893390192", "8", "3.50E-04", "HIST1H2AC, CD86, CD80, FCGR1A, HLA-DRB5, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Leishmaniasis", "8.342052314", "6", "6.70E-04", "FCGR1A, HLA-DRB5, JAK2, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Antigen processing and presentation", "7.793233083", "6", "9.15E-04", "KLRC4, HLA-DRB5, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Toxoplasmosis", "5.855932203", "7", "0.001089", "CASP8, HLA-DRB5, JAK2, BIRC3, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Staphylococcus aureus infection", "9.14021164", "5", "0.001978", "FCGR1A, HLA-DRB5, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Inflammatory bowel disease (IBD)", "7.712053571", "5", "0.003688", "IL18RAP, HLA-DRB5, HLA-DMA, HLA-DQA1, HLA-DRA"], ["HTLV-I infection", "2.69921875", "7", "0.04181", "IL2RB, HLA-DRB5, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA, APC"], ["Measles", "3.711063373", "5", "0.043409", "DDX58, IL2RB, IFIH1, JAK2, FAS"]], "row_count": 22, "column_count": 5, "numeric_cells": 76, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31138213:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c496cecb91ad4db5247d9118cd499c8f56b53b9e494a6063cf941e388d084a1e", "bytes": 1230, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#Tab2", "version": null, "note": "Selection of risk-related pathways", "structure": {"pmcid": "PMC6537382", "section_index": 13, "section_title": "Variant pathway analysis and establishment of ANN model for risk assessment", "row_count": 11, "column_count": 3}, "table": {"label": "Table 2", "caption": "Selection of risk-related pathways", "rows": [["Pathway", "P value_", "Genes"], ["Measles", "2.03E-29", "DDX58, IL2RB, IFIH1, JAK2, FAS"], ["Antigen processing and presentation", "7.42E-19", "KLRC4, HLA-DRB5, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Rheumatoid arthritis", "1.70E-13", "CD86, CD80, HLA-DRB5, ATP6V1H, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Phagosome", "5.84E-12", "FCGR1A, HLA-DRB5, ITGB5, ATP6V1H, CLEC7A, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Systemic lupus erythematosus", "1.31E-11", "HIST1H2AC, CD86, CD80, FCGR1A, HLA-DRB5, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Herpes simplex infection", "1.18E-06", "DDX58, HMGN1, IFIH1, GTF2IRD1, CASP8, HLA-DRB5, JAK2, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Inflammatory bowel disease (IBD)", "1.14E-05", "IL18RAP, HLA-DRB5, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Tuberculosis", "0.000357276", "FCGR1A, CASP8, HLA-DRB5, FCER1G, ATP6V1H, JAK2, CLEC7A, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Type I diabetes mellitus", "0.001284502", "CD86, CD80, HLA-DRB5, FAS, HLA-E, HLA-DMA, HLA-DQA1, HLA-DRA"], ["Toxoplasmosis", "0.001643", "CASP8, HLA-DRB5, JAK2, BIRC3, HLA-DMA, HLA-DQA1, HLA-DRA"]], "row_count": 11, "column_count": 3, "numeric_cells": 16, "header_rows": 1, "locator": "section[13]/table-wrap[2]#Tab2"}}], "gaps": ["asset:data:geo:GSE34289 not downloaded", "asset:data:geo:GSE34289 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "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": 1.0, "band": "verbatim", "quote": "The DEGs between high-risk samples and low-risk samples were then identified using the limma package (version 3.10.3, http://www.bioconductor.org/packages/2.9/bioc/html/limma.html) [21]."}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE34289"], "resolved_accessions": ["GSE34289"], "statements": ["The microarray data GSE34289 was downloaded from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi)."], "basis": "The paper names GSE34289 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31138213", "data:geo:GSE34289", "asset:table:pmid:31138213:1", "asset:table:pmid:31138213:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE34289"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:48Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 20371, "completion_tokens": 1811, "cached_tokens": 784}}, "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:31138213", "type": "paper", "label": "pmid:31138213"}, {"id": "source:pmid:31138213", "type": "manuscript", "label": "PMID 31138213 full text"}, {"id": "data:geo:GSE34289", "type": "dataset", "label": "GEO GSE34289"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31138213", "type": "paper", "label": "pmid:31138213"}, {"id": "source:pmid:31138213", "type": "manuscript", "label": "PMID 31138213 full text"}, {"id": "data:geo:GSE34289", "type": "dataset", "label": "GEO GSE34289"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31138213", "type": "extraction", "used": ["source:pmid:31138213"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE34289", "type": "accession_resolution", "used": ["data:geo:GSE34289"], "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:31138213", "parent_hash": "sha256:e687381160fe17602c9fc318a81d308372e6454fa015198bea1b6dec3a919614", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE34289 licence not read", "asset:data:geo:GSE34289 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ict the risk of thyroid cancer. METHODS: The RNASeq data of 482 thyroid cancer samples were down"], "order_basis": "paper_text_order:236", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ival analysis and analysis of an independent microarray dataset (GSE34289) for thyroid cancer. RESUL", "he samples with different risks. Analysis of microarray dataset GSE34289 showed that the accuracy of"], "order_basis": "paper_text_order:781", "id": "assay:2"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The DEGs between high-risk samples and low-risk samples were then identified using the limma package (version 3.10.3, http://www.bioconductor.org/packages/2.9/bioc/html/limma.html) [21]."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:47:04+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}}}