{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31842912", "kind": "science-record", "revision": 7, "content_hash": "sha256:4f0154a4fbc12a8740728dd436b18f40b9441b9f2b864cfdb9b89bffac9e39ea", "created_at": "2026-11-01T15:40:53Z", "updated_at": "2026-11-01T22:01:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "BCL2 and hsa-miR-181a-5p are potential biomarkers associated with papillary thyroid cancer based on bioinformatics analysis.", "doi": "10.1186/s12957-019-1755-9", "pmid": "31842912", "authors": ["Cong Zhang", "Chunrui Bo", "Lunhua Guo", "Pingyang Yu", "Susheng Miao", "Xin Gu"], "journal": "World journal of surgical oncology", "year": 2019, "abstract": "BACKGROUND: The morbidity of thyroid carcinoma has been rising worldwide and increasing faster than any other cancer type. The most common subtype with the best prognosis is papillary thyroid cancer (PTC); however, the exact molecular pathogenesis of PTC is still not completely understood.\nMETHODS: In the current study, 3 gene expression datasets (GSE3678, GSE3467, and GSE33630) and 2 miRNA expression datasets (GSE113629 and GSE73182) of PTC were selected from the Gene Expression Omnibus (GEO) database and were further used to identify differentially expressed genes (DEGs) and deregulated miRNAs between normal thyroid tissue samples and PTC samples. Then, Gene Ontology (GO) and pathway enrichment analyses were conducted, and a protein-protein interaction (PPI) network was constructed to explore the potential mechanism of PTC carcinogenesis. The hub gene detection was performed using the CentiScaPe v2.0 plugin, and significant modules were discovered using the MCODE plugin for Cytoscape. In addition, a miRNA-gene regulatory network in PTC was constructed using common deregulated miRNAs and DEGs.\nRESULTS: A total of 263 common DEGs and 12 common deregulated miRNAs were identified. Then, 6 significant KEGG pathways (P < 0.05) and 82 significant GO terms were found to be enriched, indicating that PTC was closely related to amino acid metabolism, development, immune system, and endocrine system. In addition, by constructing a PPI network and miRNA-gene regulatory network, we found that hsa-miR-181a-5p regulated the most DEGs, while BCL2 was targeted by the most miRNAs.\nCONCLUSIONS: The results of this study suggested that hsa-miR-181a-5p and BCL2 and their regulatory networks may play important roles in the pathogenesis of PTC.", "claims": [{"id": "claim-method", "statement": "The Benjamin and Hochberg false discovery rate (FDR) method was used to correct the adjusted P value and correct the occurrence of false positive results.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31842912", "locator": "sections[4] \"Identification of DEGs and deregulated miRNA\" paragraph 2", "quote": "The Benjamin and Hochberg false discovery rate (FDR) method was used to correct the adjusted P value and correct the occurrence of false positive results."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31842912", "locator": "sections[26] \"notes\" paragraph 1", "quote": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."}], "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:31842912"], "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:GSE113629"], "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:GSE113629"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31842912", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12957-019-1755-9", "sha256": "sha256:7e12aa6a26c647cb9a63c036d0e9fdf488be5244b128d3359dab98766ae702ed", "bytes": 33383, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12957-019-1755-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6916035", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE113629", "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=GSE113629", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE113629", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3110474", "GSM3110475", "GSM3110476", "GSM3110477", "GSM3110478", "GSM3110479", "GSM3110480", "GSM3110481", "GSM3110482", "GSM3110483"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "24741", "taxon": "Homo sapiens", "title": "microRNA expression profiling of papillary thyroid carcinoma (PTC) and matched adjacent normal thyroid tissues", "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:GSE33630", "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=GSE33630", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33630", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM831749", "GSM831750", "GSM831751", "GSM831752", "GSM831753", "GSM831754", "GSM831755", "GSM831756", "GSM831757", "GSM831758", "GSM831759", "GSM831760", "GSM831761", "GSM831762", "GSM831763", "GSM831764", "GSM831765", "GSM831766", "GSM831767", "GSM831768", "GSM831769", "GSM831770", "GSM831771", "GSM831772", "GSM831773", "GSM831774", "GSM831775", "GSM831776", "GSM831777", "GSM831778", "GSM831779", "GSM831780", "GSM831781", "GSM831782", "GSM831783", "GSM831784", "GSM831785", "GSM831786", "GSM831787", "GSM831788", "GSM831789", "GSM831790", "GSM831791", "GSM831792", "GSM831793", "GSM831794", "GSM831795", "GSM831796", "GSM831797", "GSM831798", "GSM831799", "GSM831800", "GSM831801", "GSM831802", "GSM831803", "GSM831804", "GSM831805", "GSM831806", "GSM831807", "GSM831808", "GSM831809", "GSM831810", "GSM831811", "GSM831812", "GSM831813", "GSM831814", "GSM831815", "GSM831816", "GSM831817", "GSM831818", "GSM831819", "GSM831820", "GSM831821", "GSM831822", "GSM831823", "GSM831824", "GSM831825", "GSM831826", "GSM831827", "GSM831828", "GSM831829", "GSM831830", "GSM831831", "GSM831832", "GSM831833", "GSM831834", "GSM831835", "GSM831836", "GSM831837", "GSM831838", "GSM831839", "GSM831840", "GSM831841", "GSM831842", "GSM831843", "GSM831844", "GSM831845", "GSM831846", "GSM831847", "GSM831848", "GSM831849", "GSM831850", "GSM831851", "GSM831852", "GSM831853"], "sample_count": 105, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Normal thyrocytes vs papillary vs anaplastic thyroid carcinomas", "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:GSE3467", "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=GSE3467", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3467", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM77362", "GSM77363", "GSM77364", "GSM77365", "GSM77366", "GSM77367", "GSM77368", "GSM77369", "GSM77370", "GSM77371", "GSM77372", "GSM77373", "GSM77374", "GSM77375", "GSM77376", "GSM77377", "GSM77378", "GSM77379"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "The role of micro-RNA genes in papillary thyroid carcinoma", "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:GSE3678", "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=GSE3678", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3678", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM85215", "GSM85216", "GSM85217", "GSM85218", "GSM85219", "GSM85220", "GSM85221", "GSM85222", "GSM85223", "GSM85224", "GSM85225", "GSM85226", "GSM85227", "GSM85228"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "PTC versus paired normal thyroid tissue", "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:GSE73182", "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=GSE73182", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73182", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1888201", "GSM1888202", "GSM1888203", "GSM1888204", "GSM1888205", "GSM1888206", "GSM1888207", "GSM1888208", "GSM1888209", "GSM1888210", "GSM1888211", "GSM1888212", "GSM1888213", "GSM1888214", "GSM1888215", "GSM1888216", "GSM1888217", "GSM1888218", "GSM1888219", "GSM1888220", "GSM1888221", "GSM1888222", "GSM1888223", "GSM1888224"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "20194", "taxon": "Homo sapiens", "title": "miRNA expression profiling of snap-frozen primary papillary thyroid carcinomas (PTC) and normal thyroids", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31842912:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ea1662f87c0a063ec78ab0d981d0348da8485009818af5ba860e3dc05ef7e2c9", "bytes": 754, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab1", "version": null, "note": "Six significant KEGG pathways and their classification", "structure": {"pmcid": "PMC6916035", "section_index": 12, "section_title": "Pathway enrichment analysis of common DEGs", "row_count": 7, "column_count": 3}, "table": {"label": "Table 1", "caption": "Six significant KEGG pathways and their classification", "rows": [["Pathway", "P value", "Classification"], ["hsa00350:Tyrosine metabolism", "0.002602", "Metabolism; Amino acid metabolism"], ["hsa05200:Pathways in cancer", "0.005643", "Human Diseases; Cancers: Overview"], ["hsa05222:Small cell lung cancer", "0.013589", "Human Diseases; Cancers: Specific types"], ["hsa04360:Axon guidance", "0.019287", "Organismal Systems; Development"], ["hsa04610:Complement and coagulation cascades", "0.027889", "Organismal Systems; Immune system"], ["hsa04920:Adipocytokine signaling pathway", "0.029209", "Organismal Systems; Endocrine system"]], "row_count": 7, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31842912:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1cd91457c62a70b69bb3a823677367ee09c1946208567bcfcc2b629811d3934a", "bytes": 2381, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab2", "version": null, "note": "Detailed information on the 11 hub genes identified in the PPI network", "structure": {"pmcid": "PMC6916035", "section_index": 14, "section_title": "Construction of the PPI network and module analysis", "row_count": 12, "column_count": 5}, "table": {"label": "Table 2", "caption": "Detailed information on the 11 hub genes identified in the PPI network", "rows": [["Gene", "Full name", "Overview", "Expression in PTC", "Reference"], ["FN1", "Fibronectin 1", "FN1 is involved in cell adhesion and migration processes including host defense and metastasis.", "Upregulated", "[29]"], ["CCND1", "Cyclin D1", "CCND1 has been demonstrated to interact with tumor suppressor protein Rb.", "Upregulated", "[30]"], ["MET", "MET proto-oncogene, receptor tyrosine kinase", "MET plays a role in cellular survival, embryogenesis, and cellular migration and invasion.", "Downregulated", "[31]"], ["RUNX2", "RUNX family transcription factor 2", "RUNX2 is essential for osteoblastic differentiation and skeletal morphogenesis.", "Upregulated", "[32]"], ["IRS1", "Insulin receptor substrate 1", "Mutations in IRS1 are associated with type II diabetes and susceptibility to insulin resistance.", "No relevant biological experiments", "[33]"], ["SERPINA1", "Serpin family A member 1", "The protein encoded by SERPINA1 is an inhibitor whose targets include elastase, plasmin, thrombin, trypsin, chymotrypsin, and plasminogen activator.", "Upregulated", "[34]"], ["KRT19", "Keratin 19", "KRT19 is responsible for the structural integrity of epithelial cells. It is specifically expressed in the periderm.", "Upregulated", "[35]"], ["FGFR2", "Fibroblast growth factor receptor 2", "FGFR-2 is involved in regulating cell proliferation, migration and differentiation, as well as in the response to injury and tissue repair.", "Downregulated", "[36]"], ["MUC1", "Mucin 1, cell surface associated", "Overexpression, aberrant intracellular localization, and changes in the glycosylation of MUC1 have been associated with carcinomas.", "Downregulated", "[37]"], ["NCAM1", "Neural cell adhesion molecule 1, also known as CD56", "NCAM1 is involved in the development of the nervous system, the expansion of T cells and dendritic cells with a regulatory role in cell motility and migratory capacity of neoplastic cells.", "Downregulated", "[38]"], ["WFS1", "Wolframin ER transmembrane glycoprotein", "Mutations in WFS1 are associated with Wolfram syndrome, also called DIDMOAD (diabetes insipidus, diabetes mellitus, optic atrophy, and deafness), an autosomal recessive disorder.", "No related references", "[39]"]], "row_count": 12, "column_count": 5, "numeric_cells": 22, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab2"}}], "gaps": ["asset:data:geo:GSE113629 not downloaded", "asset:data:geo:GSE113629 licence not read", "asset:data:geo:GSE33630 not downloaded", "asset:data:geo:GSE33630 licence not read", "asset:data:geo:GSE3467 not downloaded", "asset:data:geo:GSE3467 licence not read", "asset:data:geo:GSE3678 not downloaded", "asset:data:geo:GSE3678 licence not read", "asset:data:geo:GSE73182 not downloaded", "asset:data:geo:GSE73182 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"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"}}, {"id": "method-3", "family": null, "specific": null, "label": "Benjamini and Hochberg false discovery rate (FDR) method", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Benjamin and Hochberg false discovery rate (FDR) method was used to correct the adjusted P value and correct the occurrence of false positive results."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE3678", "GSE3467", "GSE33630", "GSE113629", "GSE73182"], "resolved_accessions": ["GSE3678", "GSE3467", "GSE33630", "GSE113629", "GSE73182"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE3678, GSE3467, GSE33630, GSE113629, GSE73182 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:31842912", "data:geo:GSE113629", "asset:table:pmid:31842912:1", "asset:table:pmid:31842912:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE113629"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:33Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 25398, "completion_tokens": 1781, "cached_tokens": 776}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:31842912", "type": "paper", "label": "pmid:31842912"}, {"id": "source:pmid:31842912", "type": "manuscript", "label": "PMID 31842912 full text"}, {"id": "data:geo:GSE113629", "type": "dataset", "label": "GEO GSE113629"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31842912", "type": "paper", "label": "pmid:31842912"}, {"id": "source:pmid:31842912", "type": "manuscript", "label": "PMID 31842912 full text"}, {"id": "data:geo:GSE113629", "type": "dataset", "label": "GEO GSE113629"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31842912", "type": "extraction", "used": ["source:pmid:31842912"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE113629", "type": "accession_resolution", "used": ["data:geo:GSE113629"], "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:31842912", "parent_hash": "sha256:b8bf9ad8a80f0f7726e1a910bb3364e24581b7b63fc1bc537dc97cfe24f35709", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE113629 licence not read", "asset:data:geo:GSE113629 not downloaded", "asset:data:geo:GSE33630 licence not read", "asset:data:geo:GSE33630 not downloaded", "asset:data:geo:GSE3467 licence not read", "asset:data:geo:GSE3467 not downloaded", "asset:data:geo:GSE3678 licence not read", "asset:data:geo:GSE3678 not downloaded", "asset:data:geo:GSE73182 licence not read", "asset:data:geo:GSE73182 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "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":"2026-11-04T01:48:17+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}}}