{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33879674", "kind": "science-record", "revision": 7, "content_hash": "sha256:54e6f27c795ae366a59cd14a9b5ed26659d3aaab7c573b223ae9d70d56e7c812", "created_at": "2026-11-01T15:41:33Z", "updated_at": "2026-11-01T22:03:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes and pathways in discoid lupus skin via bioinformatics analysis.", "doi": "10.1097/MD.0000000000025433", "pmid": "33879674", "authors": ["Qian Dong", "Kang Chen", "Jinye Xie", "Hui Han", "Yanping Feng", "Jianqiang Lu", "Weijia Wang"], "journal": "Medicine", "year": 2021, "abstract": "ABSTRACT: Discoid lupus erythematosus (DLE) is the most common skin manifestation of lupus; however, the molecular mechanisms underlying DLE remain unknown. Therefore, we aimed to identify key differentially expressed genes (DEGs) in discoid lupus skin and investigate their potential pathways.To identify candidate genes involved in the occurrence and development of the disease, we downloaded the microarray datasets GSE52471 and GSE72535 from the Gene Expression Database (GEO). DEGs between discoid lupus skin and normal controls were selected using the GEO2R tool and Venn diagram software (http://bioinformatics.psb.ugent.be/webtools/Venn/). The Database for Annotation, Visualization, and Integrated Discovery (DAVID), Enrichr, and Cytoscape ClueGo were used to analyze the Kyoto Encyclopedia of Gene and Genome pathways and gene ontology. Protein-protein interactions (PPIs) of these DEGs were further assessed using the Search Tool for the Retrieval Interacting Genes version 10.0.Seventy three DEGs were co-expressed in both datasets. DEGs were predominantly upregulated in receptor signaling pathways of the immune response. In the PPI network, 69 upregulated genes were selected. Furthermore, 4 genes (CXCL10, ISG15, IFIH1, and IRF7) were found to be significantly upregulated in the RIG-I-like receptor signaling pathway, from analysis of Enrichr and Cytoscape ClueGo.The results of this study may provide new insights into the potential molecular mechanisms of DLE. However, further experimentation is required to confirm these findings.", "claims": [{"id": "claim-method", "statement": "To identify the DEGs from these 2 groups (DLE and normal controls), we conducted GEO2R web-server analysis to calculate the P-values and |logFC| values.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33879674", "locator": "sections[9] \"Identification of DEGs in DLE\" paragraph 2", "quote": "To identify the DEGs from these 2 groups (DLE and normal controls), we conducted GEO2R web-server analysis to calculate the P-values and |logFC| values."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated during and/or analyzed during the current study are publicly available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33879674", "locator": "sections[16] \"fn-group\" paragraph 1", "quote": "The datasets generated during and/or analyzed during the current study are publicly available."}], "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:33879674"], "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:GSE52471"], "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:GSE52471"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33879674", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000025433", "sha256": "sha256:bcc53e6cee0f28de4229bb1c930c3e9b2a6ad707ffb95d2282c9b5e8f25d732b", "bytes": 17992, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000025433", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8078291", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE52471", "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=GSE52471", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52471", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1267412", "GSM1267413", "GSM1267414", "GSM1267415", "GSM1267416", "GSM1267417", "GSM1267418", "GSM1267419", "GSM1267420", "GSM1267421", "GSM1267422", "GSM1267423", "GSM1267424", "GSM1267425", "GSM1267426", "GSM1267427", "GSM1267428", "GSM1267429", "GSM1267430", "GSM1267431", "GSM1267432", "GSM1267433", "GSM1267434", "GSM1267435", "GSM1267436", "GSM1267437", "GSM1267438", "GSM1267439", "GSM1267440", "GSM1267441", "GSM1267442", "GSM1267443", "GSM1267444", "GSM1267445", "GSM1267446", "GSM1267447", "GSM1267448", "GSM1267449"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Dominant Th1 and Minimal Th17 Skewing in Discoid Lupus Revealed by Transcriptomic Comparison with Psoriasis", "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:GSE72535", "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=GSE72535", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE72535", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1864221", "GSM1864223", "GSM1864224", "GSM1864226", "GSM1864228", "GSM1864230", "GSM1864231", "GSM1864233", "GSM1864235", "GSM1864236", "GSM1864238", "GSM1864239", "GSM1864240", "GSM1864241", "GSM1864242", "GSM1864243", "GSM1864244"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "CD163 macrophages display mixed polarizations in discoid lupus skin", "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:33879674:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:51d849aac4bf5c1c419d1503850cbbd7c17380bebc3f3080c2cf24ac8a30f89a", "bytes": 743, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "All 73 common differentially expressed genes (DEGs) were detected from two profile datasets in DLE lesions compared to normal skin.", "structure": {"pmcid": "PMC8078291", "section_index": 9, "section_title": "Identification of DEGs in DLE", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "All 73 common differentially expressed genes (DEGs) were detected from two profile datasets in DLE lesions compared to normal skin.", "rows": [["DEGs", "Genes Name"], ["Up-regulated", "IL7R IFI35 CXCL10 HERC5 IDO1 STAT2 CCL5 OAS3 OAS1 RSAD2 MX1 CXCL13 WARS TRIM22 LTB LGALS3BP BST2 IRF7 CFB SP110 IFI6 HERC6 CD8A XAF1 IFIH1 ADAMDEC1 GZMA CD2 AIM2 IRF8 USP18 TDO2 SAMD9 TLR7 KRT6B IFI44L IFIT1 PLAC8 LAMP3 CCL8 GBP1 OAS2 CD3D KRT16 CXCL9 FCMR GZMB ZBP1 PI3 LAG3 ISG20 OASL CXCL11 C1QB STAT1 TYMP JCHAIN RTP4 IFI44 CD48 GZMK CCR7 ISG15 MX2 IFIT3 MMP9 GNLY NKG7 IFI27"], ["Down-regulated", "PON3 FABP7 COCH HSD11B1"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33879674:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7631015818aa5536a9bb8997e455077547d2d145a7bc74a288e0f5c42725f7df", "bytes": 1693, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T2", "version": null, "note": "Gene ontology analysis of differentially expressed genes in DLE.", "structure": {"pmcid": "PMC8078291", "section_index": 10, "section_title": "DEGs gene ontology and KEGG pathway analysis in DLE", "row_count": 16, "column_count": 6}, "table": {"label": "Table 2", "caption": "Gene ontology analysis of differentially expressed genes in DLE.", "rows": [["Category", "Term", "Count", "%", "P-value", "FDR"], ["GOTERM_BP_DIRECT", "GO:0006955∼immune response", "13", "16.34", "1.11E–11", "1.48E–08"], ["GOTERM_BP_DIRECT", "GO:0070098∼chemokine-mediated signaling pathway", "6", "7.54", "1.03E–06", "0.00138"], ["GOTERM_BP_DIRECT", "GO:0006954∼inflammatory response", "9", "11.31", "2.70E–06", "0.003596"], ["GOTERM_BP_DIRECT", "GO:0045087∼innate immune response", "8", "10.05", "1.17E–05", "0.0156"], ["GOTERM_BP_DIRECT", "GO:0035455∼responseto interferon-alpha", "3", "3.77", ".00102", "1.352729"], ["GOTERM_CC_DIRECT", "GO:0009897∼external side of plasma membrane", "8", "10.05", "2.80E–06", "0.002757"], ["GOTERM_CC_DIRECT", "GO:0005737∼cytoplasm", "19", "23.88", ".011213", "10.49805"], ["GOTERM_CC_DIRECT", "GO:0005615∼extracellular space", "9", "11.31", ".022916", "20.389"], ["GOTERM_CC_DIRECT", "GO:0072562∼blood microparticle", "3", "3.77", ".042296", "34.62742"], ["GOTERM_MF_DIRECT", "GO:0008009∼chemokine activity", "6", "7.54", "8.76E–07", "9.22E–04"], ["GOTERM_MF_DIRECT", "GO:0003725∼double-stranded RNA binding", "6", "7.54", "2.17E–06", "0.002284"], ["GOTERM_MF_DIRECT", "GO:0045236∼CXCR chemokine receptor binding", "3", "3.77", ".001204", "1.259238"], ["GOTERM_MF_DIRECT", "GO:0016779∼nucleotidyltransferase activity", "3", "3.77", ".002446", "2.543669"], ["GOTERM_MF_DIRECT", "GO:0004252∼serine-type endopeptidase activity", "5", "6.28", ".002603", "2.705516"], ["GOTERM_MF_DIRECT", "GO:0000975∼regulatory region DNA binding", "2", "2.51", ".025951", "24.17125"]], "row_count": 16, "column_count": 6, "numeric_cells": 75, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:33879674:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1ede9b56c76746b2be388cd024de6e5fd14069e9ed5135565934ae68513c25cf", "bytes": 606, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#T3", "version": null, "note": "KEGG pathway analysis of differentially expressed genes in DLE.", "structure": {"pmcid": "PMC8078291", "section_index": 10, "section_title": "DEGs gene ontology and KEGG pathway analysis in DLE", "row_count": 4, "column_count": 6}, "table": {"label": "Table 3", "caption": "KEGG pathway analysis of differentially expressed genes in DLE.", "rows": [["Pathway ID", "Name", "Count", "%", "P-value", "Genes"], ["hsa04062", "Chemokine signaling pathway", "9", "12.33", "7.37E–06", "CCR7,CXCL13,CXCL9,CCL8,CXCL11,STAT1,CCL5,STAT2,CXCL10"], ["hsa04620", "Toll-like receptor signaling pathway", "7", "9.59", "2.51E–05", "IRF7,CXCL9,CXCL11,STAT1,CCL5,TLR7,CXCL10"], ["hsa04622", "RIG-I-like receptor signaling pathway", "4", "5.48", ".007097", "IFIH1,ISG15,IRF7,CXCL10"]], "row_count": 4, "column_count": 6, "numeric_cells": 15, "header_rows": 1, "locator": "section[10]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:33879674:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f34520344c80d72f087f9f59b005d6e6ad498a1373062c78a04549791ee80a97", "bytes": 399, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T4", "version": null, "note": "Reanalysis of 30 selected genes via KEGG pathway enrichment.", "structure": {"pmcid": "PMC8078291", "section_index": 12, "section_title": "Re-analysis of 30 selected genes via KEGG pathway upregulation", "row_count": 2, "column_count": 6}, "table": {"label": "Table 4", "caption": "Reanalysis of 30 selected genes via KEGG pathway enrichment.", "rows": [["Term", "P-value", "Adjusted P-value", "Odds ratio", "Combined score", "Genes"], ["RIG-I-like receptor signaling pathway", "3.52E–06", "1.66E–05", "46.39627", "582.6039", "IFIH1,ISG15,IRF7,CXCL10"]], "row_count": 2, "column_count": 6, "numeric_cells": 5, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE52471 not downloaded", "asset:data:geo:GSE52471 licence not read", "asset:data:geo:GSE72535 not downloaded", "asset:data:geo:GSE72535 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": "PPI"}}, {"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 web-server analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify the DEGs from these 2 groups (DLE and normal controls), we conducted GEO2R web-server analysis to calculate the P-values and |logFC| values."}}], "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": ["GSE52471", "GSE72535"], "resolved_accessions": ["GSE52471", "GSE72535"], "statements": ["The datasets generated during and/or analyzed during the current study are publicly available."], "basis": "The paper names GSE52471, GSE72535 in NCBI 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:33879674", "data:geo:GSE52471", "asset:table:pmid:33879674:1", "asset:table:pmid:33879674:2", "asset:table:pmid:33879674:3", "asset:table:pmid:33879674:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE52471"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 14523, "completion_tokens": 1236, "cached_tokens": 529}}, "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:33879674", "type": "paper", "label": "pmid:33879674"}, {"id": "source:pmid:33879674", "type": "manuscript", "label": "PMID 33879674 full text"}, {"id": "data:geo:GSE52471", "type": "dataset", "label": "GEO GSE52471"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33879674", "type": "paper", "label": "pmid:33879674"}, {"id": "source:pmid:33879674", "type": "manuscript", "label": "PMID 33879674 full text"}, {"id": "data:geo:GSE52471", "type": "dataset", "label": "GEO GSE52471"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33879674", "type": "extraction", "used": ["source:pmid:33879674"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE52471", "type": "accession_resolution", "used": ["data:geo:GSE52471"], "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:33879674", "parent_hash": "sha256:a3ffeca6d2ea60a9c04cf105616be388e483c313cdb0d6b75bee5a5fa31945a8", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE52471 licence not read", "asset:data:geo:GSE52471 not downloaded", "asset:data:geo:GSE72535 licence not read", "asset:data:geo:GSE72535 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": ["PPI"], "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":"2026-11-04T02:16:21+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}}}