{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34555062", "kind": "science-record", "revision": 7, "content_hash": "sha256:7dc05b99be940e0772e223668cf9b174278c86a768f5402130459e0ef1b75239", "created_at": "2026-11-01T15:41:53Z", "updated_at": "2026-11-01T22:04:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatic analysis identifies potential key genes of epilepsy.", "doi": "10.1371/journal.pone.0254326", "pmid": "34555062", "authors": ["Yike Zhu", "Dan Huang", "Zhongyan Zhao", "Chuansen Lu"], "journal": "PloS one", "year": 2021, "abstract": "BACKGROUND: Epilepsy is one of the most common brain disorders worldwide. It is usually hard to be identified properly, and a third of patients are drug-resistant. Genes related to the progression and prognosis of epilepsy are particularly needed to be identified.\nMETHODS: In our study, we downloaded the Gene Expression Omnibus (GEO) microarray expression profiling dataset GSE143272. Differentially expressed genes (DEGs) with a fold change (FC) >1.2 and a P-value <0.05 were identified by GEO2R and grouped in male, female and overlapping DEGs. Functional enrichment analysis and Protein-Protein Interaction (PPI) network analysis were performed.\nRESULTS: In total, 183 DEGs overlapped (77 ups and 106 downs), 302 DEGs (185 ups and 117 downs) in the male dataset, and 750 DEGs (464 ups and 286 downs) in the female dataset were obtained from the GSE143272 dataset. These DEGs were markedly enriched under various Gene Ontology (GO) terms and Kyoto Encyclopedia of Genes and Genomes (KEGG) terms. 16 following hub genes were identified based on PPI network analysis: ADCY7, C3AR1, DEGS1, CXCL1 in male-specific DEGs, TOLLIP, ORM1, ELANE, QPCT in female-specific DEGs and FCAR, CD3G, CLEC12A, MOSPD2, CD3D, ALDH3B1, GPR97, PLAUR in overlapping DEGs.\nCONCLUSION: This discovery-driven study may be useful to provide a novel insight into the diagnosis and treatment of epilepsy. However, more experiments are needed in the future to study the functional roles of these genes in epilepsy.", "claims": [{"id": "claim-method", "statement": "The online analysis tool GEO2R was using to identify the DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34555062", "locator": "sections[4] \"2.2 Identification of DEGs\" paragraph 2", "quote": "The online analysis tool GEO2R was using to identify the DEGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All relevant data are within the manuscript.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34555062", "locator": "sections[14] \"Data Availability\" paragraph 2", "quote": "All relevant data are within the manuscript."}], "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:34555062"], "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:GSE143272"], "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:GSE143272"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34555062", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0254326", "sha256": "sha256:16c2fd90944e08866eb54bcd87bfd994d997f9456884488b1a0745fdd44d92b6", "bytes": 63352, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0254326", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8459949", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE143272", "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=GSE143272", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE143272", "version": null, "note": "All relevant data are within the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4255766", "GSM4255767", "GSM4255768", "GSM4255769", "GSM4255770", "GSM4255771", "GSM4255772", "GSM4255773", "GSM4255774", "GSM4255775", "GSM4255776", "GSM4255777", "GSM4255778", "GSM4255779", "GSM4255780", "GSM4255781", "GSM4255782", "GSM4255783", "GSM4255784", "GSM4255785", "GSM4255786", "GSM4255787", "GSM4255788", "GSM4255789", "GSM4255790", "GSM4255791", "GSM4255792", "GSM4255793", "GSM4255794", "GSM4255795", "GSM4255796", "GSM4255797", "GSM4255798", "GSM4255799", "GSM4255800", "GSM4255801", "GSM4255802", "GSM4255803", "GSM4255804", "GSM4255805", "GSM4255806", "GSM4255807", "GSM4255808", "GSM4255809", "GSM4255810", "GSM4255811", "GSM4255812", "GSM4255813", "GSM4255814", "GSM4255815", "GSM4255816", "GSM4255817", "GSM4255818", "GSM4255819", "GSM4255820", "GSM4255821", "GSM4255822", "GSM4255823", "GSM4255824", "GSM4255825", "GSM4255826", "GSM4255827", "GSM4255828", "GSM4255829", "GSM4255830", "GSM4255831", "GSM4255832", "GSM4255833", "GSM4255834", "GSM4255835", "GSM4255836", "GSM4255837", "GSM4255838", "GSM4255839", "GSM4255840", "GSM4255841", "GSM4255842", "GSM4255843", "GSM4255844", "GSM4255845", "GSM4255846", "GSM4255847", "GSM4255848", "GSM4255849", "GSM4255850", "GSM4255851", "GSM4255852", "GSM4255853", "GSM4255854", "GSM4255855", "GSM4255856", "GSM4255857", "GSM4255858", "GSM4255859", "GSM4255860", "GSM4255861", "GSM4255862", "GSM4255863", "GSM4255864", "GSM4255865", "GSM4255866", "GSM4255867", "GSM4255868", "GSM4255869", "GSM4255870", "GSM4255871", "GSM4255872", "GSM4255873", "GSM4255874", "GSM4255875", "GSM4255876", "GSM4255877", "GSM4255878", "GSM4255879", "GSM4255880", "GSM4255881", "GSM4255882", "GSM4255883", "GSM4255884", "GSM4255885", "GSM4255886", "GSM4255887", "GSM4255888", "GSM4255889", "GSM4255890", "GSM4255891", "GSM4255892", "GSM4255893", "GSM4255894", "GSM4255895", "GSM4255896", "GSM4255897", "GSM4255898", "GSM4255899", "GSM4255900", "GSM4255901", "GSM4255902", "GSM4255903", "GSM4255904", "GSM4255905", "GSM4255906", "GSM4255907"], "sample_count": 142, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Peripheral blood expression profiles of patients with epilepsy receiving and not receiving antiepileptic drug monotherapy and their differential response to the treatment.", "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:34555062:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c7120c690077498e530106807a167894166a04fd1d235abc88116f016c9d254a", "bytes": 2023, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#pone.0254326.t001", "version": null, "note": "KEGG pathway enrichment analyses for DEGs.", "structure": {"pmcid": "PMC8459949", "section_index": 9, "section_title": "3.2 Functional enrichment analysis of DEGs", "row_count": 34, "column_count": 5}, "table": {"label": "Table 1", "caption": "KEGG pathway enrichment analyses for DEGs.", "rows": [["Gender", "Pathway description", "P-Value", "Count"], ["Male", "Upregulated", "Sphingolipid signaling pathway", "0.000462", "7"], ["Biosynthesis of amino acids", "0.001856", "5"], ["Hepatocellular carcinoma", "0.003485", "7"], ["Autophagy", "0.003942", "6"], ["NOD-like receptor signaling pathway", "0.014277", "6"], ["Downregulated", "Rheumatoid arthritis", "0.000121", "5"], ["Chemokine signaling pathway", "0.003538", "5"], ["Human cytomegalovirus infection", "0.007385", "5"], ["Cytokine-cytokine receptor interaction", "0.021566", "5"], ["Female", "Upregulated", "Leishmaniasis", "0.000008", "11"], ["Osteoclast differentiation", "0.000076", "13"], ["Chemokine signaling pathway", "0.000105", "16"], ["Renal cell carcinoma", "0.000148", "9"], ["Hepatitis B", "0.000252", "13"], ["Systemic lupus erythematosus", "0.000437", "12"], ["Kaposi sarcoma-associated herpesvirus infection", "0.000937", "14"], ["Autophagy", "0.001133", "11"], ["Human immunodeficiency virus 1 infection", "0.001169", "15"], ["Phagosome", "0.001433", "12"], ["Downregulated", "Natural killer cell mediated cytotoxicity", "3.85E-07", "13"], ["Antigen processing and presentation", "0.000366", "7"], ["Graft-versus-host disease", "0.000680", "5"], ["Th1 and Th2 cell differentiation", "0.001076", "7"], ["NF-kappa B signaling pathway", "0.001300", "7"], ["T cell receptor signaling pathway", "0.001856", "7"], ["Sphingolipid signaling pathway", "0.004458", "7"], ["Hematopoietic cell lineage", "0.006826", "6"], ["HIF-1 signaling pathway", "0.007894", "6"], ["Overlap", "Upregulated", "Platelet activation", "0.000410", "5"], ["Downregulated", "Structural constituent of ribosome", "0.000097", "6"], ["DNA-binding transcription activator activity, RNA polymerase II-specific", "0.001188", "8"], ["RNA polymerase II proximal promoter sequence-specific DNA binding", "0.002694", "8"], ["proximal promoter sequence-specific DNA binding", "0.003296", "8"]], "row_count": 34, "column_count": 5, "numeric_cells": 68, "header_rows": 1, "locator": "section[9]/table-wrap[1]#pone.0254326.t001"}}, {"id": "asset:table:pmid:34555062:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7b532affaa297528397094e756c537056dd18ecff1f9aaf5bded2f56378435d3", "bytes": 1135, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#pone.0254326.t002", "version": null, "note": "Hub genes for highly differentiated expressed genes ranked in Cytohubba plugin of Cytoscape.", "structure": {"pmcid": "PMC8459949", "section_index": 10, "section_title": "3.3 PPI network analysis of DEGs", "row_count": 32, "column_count": 4}, "table": {"label": "Table 2", "caption": "Hub genes for highly differentiated expressed genes ranked in Cytohubba plugin of Cytoscape.", "rows": [["Gender", "Rank methods in CytoHubba"], ["Male", "MCC", "MNC", "Degree"], ["ADCY7", "ADCY7", "ADCY7"], ["ADORA3", "ADORA3", "C3AR1"], ["P2RY14", "P2RY14", "LYZ"], ["C3AR1", "C3AR1", "POLR2J"], ["STOM", "LYZ", "DEGS1"], ["CLEC4D", "STOM", "RAB27A"], ["SNAP23", "CLEC4D", "ALDOA"], ["DEGS1", "DEGS1", "CXCL1"], ["CXCL1", "CXCL1", "CTSD"], ["CXCL8", "CTSD", "CXCL8"], ["Female", "TOLLIP", "TOLLIP", "TOLLIP"], ["PGLYRP1", "ARG1", "ARG1"], ["ORM1", "CREBBP", "CREBBP"], ["TCN1", "ORM1", "ORM1"], ["CAMP", "BPI", "BPI"], ["TIMP2", "H2AFJ", "H2AFJ"], ["FOLR3", "HIST1H2BK", "HIST1H2BK"], ["HP", "HIST2H2AC", "HIST2H2AC"], ["ELANE", "ELANE", "ELANE"], ["QPCT", "QPCT", "QPCT"], ["Overlap", "FCAR", "FCAR", "FCAR"], ["CD3G", "CD3G", "CD3G"], ["CLEC12A", "CLEC12A", "CLEC12A"], ["MOSPD2", "MOSPD2", "GNAQ"], ["MAPK14", "CD3D", "MOSPD2"], ["CD3D", "ALDH3B1", "MAPK14"], ["ALDH3B1", "GPR97", "CD3D"], ["GPR97", "HBA1", "ALDH3B1"], ["HBA1", "PLAUR", "GPR97"], ["PLAUR", "HBA2", "PLAUR"]], "row_count": 32, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[10]/table-wrap[1]#pone.0254326.t002"}}, {"id": "asset:table:pmid:34555062:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f43adfd4c1c8bb702a02160c14fd64cbaef133c2aedd084dfc7871b5ce965821", "bytes": 1646, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#pone.0254326.t003", "version": null, "note": "Summary of functions of hub genes.", "structure": {"pmcid": "PMC8459949", "section_index": 11, "section_title": "4 Discussion", "row_count": 16, "column_count": 2}, "table": {"label": "Table 3", "caption": "Summary of functions of hub genes.", "rows": [["Hub genes", "Functions"], ["ADCY7", "Modulate the release of presynaptic GABA"], ["C3AR1", "Critical regulator in neuronal tau pathogenesis and mediating CNS immune network"], ["DEGS1", "Play an important role in sphingolipid signaling pathway and sphingolipid metabolism"], ["CXCL1", "Recruit and activate neutrophils in inflammation"], ["TOLLIP", "Inhibitory modulator in inflammatory signaling"], ["ORM1", "Regulate the inflammation and enhance the functional integrity of BBB"], ["ELANE", "Regulatory factor in degenerative and inflammatory diseases"], ["QPCT", "Catalyze the posttranslational modification of N-terminal glutamate of proteins to pyroglutamate in many neuroendocrine peptides"], ["FCAR", "Bifunctional inhibitory/activating receptor for the Fc region of IgA"], ["CD3G and CD3D", "Crucial for the development, activation, and differentiation of T cells"], ["CLEC12A", "Deliver immature DCs to the CNS across the BBB"], ["MOSPD2", "Critical in regulating the inflammatory monocyte and neutrophil migration without activating ligands"], ["ALDH3B1", "Play a critical role in the cellular defense against oxidative stress processes and aldehyde toxicity"], ["GPR97", "Contribute to macrophage-associated inflammation; regulate the development of B-cell and NF-κB activity involving in encephalitogenic T cell activation"], ["PLAUR", "Key regulator involving in not only cell signaling, proliferation, differentiation, and migration, but also tissue remodeling"]], "row_count": 16, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[11]/table-wrap[1]#pone.0254326.t003"}}], "gaps": ["asset:data:geo:GSE143272 not downloaded", "asset:data:geo:GSE143272 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": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The online analysis tool GEO2R was using to identify the DEGs."}}], "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": ["GSE143272"], "resolved_accessions": ["GSE143272"], "statements": ["All relevant data are within the manuscript."], "basis": "The paper names GSE143272 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:34555062", "data:geo:GSE143272", "asset:table:pmid:34555062:1", "asset:table:pmid:34555062:2", "asset:table:pmid:34555062:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE143272"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:35:09Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 56819, "completion_tokens": 841, "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:34555062", "type": "paper", "label": "pmid:34555062"}, {"id": "source:pmid:34555062", "type": "manuscript", "label": "PMID 34555062 full text"}, {"id": "data:geo:GSE143272", "type": "dataset", "label": "GEO GSE143272"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34555062", "type": "paper", "label": "pmid:34555062"}, {"id": "source:pmid:34555062", "type": "manuscript", "label": "PMID 34555062 full text"}, {"id": "data:geo:GSE143272", "type": "dataset", "label": "GEO GSE143272"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34555062", "type": "extraction", "used": ["source:pmid:34555062"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE143272", "type": "accession_resolution", "used": ["data:geo:GSE143272"], "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:34555062", "parent_hash": "sha256:cf3759ec97fdc7867763ae06d251668995207bf45ed09cd801418dbaec539fe3", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE143272 licence not read", "asset:data:geo:GSE143272 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":"2026-11-04T03:12:36+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}}}