{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33869630", "kind": "science-record", "revision": 8, "content_hash": "sha256:3d54383d18d4f50e88e30481b18657025c79b56fe452213832a735c915f3590c", "created_at": "2026-11-01T15:41:32Z", "updated_at": "2026-11-01T22:46:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Shared Molecular Mechanisms between Alzheimer's Disease and Periodontitis Revealed by Transcriptomic Analysis.", "doi": "10.1155/2021/6633563", "pmid": "33869630", "authors": ["Jieqi Jin", "Mengkai Guang", "Anthony Chukwunonso Ogbuehi", "Simin Li", "Kai Zhang", "Yihong Ma", "Aneesha Acharya", "Bihan Guo", "Zongwu Peng", "Xiangqiong Liu", "Yupei Deng", "Zhaobi Fang", "Xiongjie Zhu", "Shiting Hua", "Cong Li", "Rainer Haak", "Dirk Ziebolz", "Gerhard Schmalz", "Lei Liu", "Baohua Xu", "Xiaofeng Huang"], "journal": "BioMed research international", "year": 2021, "abstract": "OBJECTIVE: To investigate the genetic crosstalk mechanisms that link periodontitis and Alzheimer's disease (AD).\nBACKGROUND: Periodontitis, a common oral infectious disease, is associated with Alzheimer's disease (AD) and considered a putative contributory factor to its progression. However, a comprehensive investigation of potential shared genetic mechanisms between these diseases has not yet been reported.\nMETHODS: Gene expression datasets related to periodontitis were downloaded from the Gene Expression Omnibus (GEO) database, and differential expression analysis was performed to identify differentially expressed genes (DEGs). Genes associated with AD were downloaded from the DisGeNET database. Overlapping genes among the DEGs in periodontitis and the AD-related genes were defined as crosstalk genes between periodontitis and AD. The Boruta algorithm was applied to perform feature selection from these crosstalk genes, and representative crosstalk genes were thus obtained. In addition, a support vector machine (SVM) model was constructed by using the scikit-learn algorithm in Python. Next, the crosstalk gene-TF network and crosstalk gene-DEP (differentially expressed pathway) network were each constructed. As a final step, shared genes among the crosstalk genes and periodontitis-related genes in DisGeNET were identified and denoted as the core crosstalk genes.\nRESULTS: Four datasets (GSE23586, GSE16134, GSE10334, and GSE79705) pertaining to periodontitis were included in the analysis. A total of 48 representative crosstalk genes were identified by using the Boruta algorithm. Three TFs (FOS, MEF2C, and USF2) and several pathways (i.e., JAK-STAT, MAPK, NF-kappa B, and natural killer cell-mediated cytotoxicity) were identified as regulators of these crosstalk genes. Among these 48 crosstalk genes and the chronic periodontitis-related genes in DisGeNET, C4A, C4B, CXCL12, FCGR3A, IL1B, and MMP3 were shared and identified as the most pivotal candidate links between periodontitis and AD.\nCONCLUSIONS: Exploration of available transcriptomic datasets revealed C4A, C4B, CXCL12, FCGR3A, IL1B, and MMP3 as the top candidate molecular linkage genes between periodontitis and AD.", "claims": [{"id": "claim-method", "statement": "Differential gene expression analysis of periodontitis-related datasets was carried out using the Linear Models for Microarray (limma) package [12] in the R project (version 3.0.1, http://www.r-project.org/) [13].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33869630", "locator": "sections[5] \"2.3. Differential Gene Expression Analysis\" paragraph 2", "quote": "Differential gene expression analysis of periodontitis-related datasets was carried out using the Linear Models for Microarray (limma) package [12] in the R project (version 3.0.1, http://www.r-project.org/) [13]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33869630", "locator": "sections[27] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are available from the corresponding author upon request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:33869630"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33869630", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/6633563", "sha256": "sha256:32f3d96d095d16c687890ec073b57e97cfa5c022bfc6da9b63d99963bb0f9ee7", "bytes": 52512, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/6633563", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8032519", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33869630:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7ff6bd27d0a24a54442c534b130a2e4ea2584737d9a7147e407e290031715016", "bytes": 891, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#tab1", "version": null, "note": "Details of the included periodontitis-related GEO datasets.", "structure": {"pmcid": "PMC8032519", "section_index": 15, "section_title": "3.1. Included Periodontitis-Related Datasets", "row_count": 5, "column_count": 7}, "table": {"label": "Table 1", "caption": "Details of the included periodontitis-related GEO datasets.", "rows": [["Included four datasets", "Type of periodontitis", "Experimental platform", "Number of examined genes", "Number of inflamed gingival tissue samples", "Number of healthy control samples", "Number of total samples"], ["GSE23586", "3 patients with severe chronic periodontitis", "GPL570", "23,518", "3", "3", "6"], ["GSE16134", "120 patients (65 with chronic periodontitis and 55 with aggressive periodontitis)", "GPL570", "24,441", "241", "69", "310"], ["GSE10334", "63 with chronic periodontitis and 27 with aggressive periodontitis", "GPL570", "24,441", "183", "64", "247"], ["GSE79705", "Generalized aggressive periodontitis (GAgP): n = 4; chronic periodontitis (CP): n = 4", "GPL18734", "19,305", "8", "4", "12"]], "row_count": 5, "column_count": 7, "numeric_cells": 28, "header_rows": 1, "locator": "section[15]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:33869630:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:66cff32966325f77aa78b70a74a71a6615044a7d8d2860189fdc4d62f722999e", "bytes": 698, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#tab2", "version": null, "note": "The number of up/downregulated DEGs identified in the four periodontitis-related datasets GSE23586, GSE16134, GSE10334, and GSE79705 at thresholds set for defining DEGs.", "structure": {"pmcid": "PMC8032519", "section_index": 16, "section_title": "3.2. Identification of Periodontitis-Related DEGs and Their Functions", "row_count": 5, "column_count": 7}, "table": {"label": "Table 2", "caption": "The number of up/downregulated DEGs identified in the four periodontitis-related datasets GSE23586, GSE16134, GSE10334, and GSE79705 at thresholds set for defining DEGs.", "rows": [["Data", "Number of upregulated DEGs", "Number of downregulated DEGs", "Number of total DEGs", "∣log2 FC∣", "p value", "Expression scale (if the data normalization was performed)"], ["GSE23586", "7", "69", "76", ">1", "<0.05", "True"], ["GSE16134", "188", "48", "236", ">1", "<0.05", "False"], ["GSE10334", "152", "42", "194", ">1", "<0.05", "False"], ["GSE79705", "219", "291", "510", ">0", "<0.05", "True"]], "row_count": 5, "column_count": 7, "numeric_cells": 24, "header_rows": 1, "locator": "section[16]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:33869630:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b9e4f0fbb2e2599ebb446288d05388f7ef411fe20feb546f479bb72506456492", "bytes": 2841, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#tab3", "version": null, "note": "Topological characteristics of the top 30 nodes in the periodontitis-related PPI network, ranked in descending order of degree.", "structure": {"pmcid": "PMC8032519", "section_index": 17, "section_title": "3.3. The Hub Genes Identified by the Periodontitis-Related PPI Network", "row_count": 31, "column_count": 8}, "table": {"label": "Table 3", "caption": "Topological characteristics of the top 30 nodes in the periodontitis-related PPI network, ranked in descending order of degree.", "rows": [["Node", "Label", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient"], ["MYC", "DEG_down", "1027", "2.432727", "0.177217", "0.411061", "0.001896", "0.002805"], ["HSPB1", "DEG_down", "433", "2.638061", "0.059908", "0.379066", "0.00278", "0.005213"], ["SMAD3", "DEG_up", "396", "2.667636", "0.052167", "0.374864", "0.004283", "0.005425"], ["UBC", "", "395", "2.112", "0.241673", "0.473485", "0.004524", "0.007004"], ["TRIM27", "DEG_up", "334", "2.864727", "0.046792", "0.349073", "0.000791", "0.006306"], ["VIM", "DEG_up", "320", "2.705212", "0.037607", "0.369657", "0.005251", "0.007619"], ["YWHAH", "DEG_up", "282", "2.838788", "0.034115", "0.352263", "0.001868", "0.00865"], ["DDB1", "DEG_down", "276", "2.76497", "0.029677", "0.361668", "0.003531", "0.008012"], ["RPS3", "DEG_down", "275", "2.844848", "0.015036", "0.351513", "0.019323", "0.014779"], ["KAT5", "DEG_down", "245", "2.717697", "0.028224", "0.367959", "0.00716", "0.007732"], ["SMARCA4", "DEG_down", "242", "2.715758", "0.021646", "0.368221", "0.010116", "0.008636"], ["RPL13", "DEG_down", "234", "2.755152", "0.015773", "0.362956", "0.024541", "0.011238"], ["PLCG1", "DEG_down", "227", "2.885091", "0.030011", "0.34661", "0.002144", "0.009614"], ["FOS", "DEG_up", "226", "2.880727", "0.024538", "0.347135", "0.003265", "0.009974"], ["AP2M1", "DEG_down", "214", "2.850182", "0.025582", "0.350855", "0.007635", "0.010848"], ["SF3B3", "DEG_down", "203", "2.765576", "0.015188", "0.361588", "0.014583", "0.010661"], ["TP53RK", "DEG_up", "200", "2.871394", "0.013972", "0.348263", "0.01608", "0.012798"], ["MMS19", "DEG_down", "195", "2.806909", "0.022335", "0.356264", "0.004705", "0.008763"], ["RPS7", "DEG_down", "193", "2.88303", "0.008126", "0.346857", "0.028335", "0.016367"], ["MEPCE", "DEG_down", "189", "2.905212", "0.0145", "0.344209", "0.005066", "0.012337"], ["TUBB4B", "DEG_down", "173", "2.880364", "0.008167", "0.347178", "0.007595", "0.019412"], ["CDH1", "DEG_down", "171", "2.888485", "0.016186", "0.346202", "0.005848", "0.011775"], ["EZR", "DEG_down", "170", "2.906667", "0.016295", "0.344037", "0.004107", "0.01554"], ["DDX41", "DEG_down", "168", "2.950061", "0.009545", "0.338976", "0.007057", "0.017509"], ["NUDC", "DEG_up", "160", "2.943758", "0.016886", "0.339702", "0.00283", "0.013954"], ["SF3A2", "DEG_down", "156", "2.949818", "0.009075", "0.339004", "0.009926", "0.01593"], ["RPL27", "DEG_down", "147", "2.912727", "0.003949", "0.343321", "0.043985", "0.020057"], ["NIFK", "DEG_up", "145", "3.107879", "0.011111", "0.321763", "0.010345", "0.016053"], ["SRPRB", "DEG_up", "143", "2.945333", "0.017545", "0.33952", "0.001674", "0.015983"], ["ATP1A1", "DEG_up", "140", "2.816606", "0.011269", "0.355037", "0.009147", "0.013032"]], "row_count": 31, "column_count": 8, "numeric_cells": 186, "header_rows": 1, "locator": "section[17]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:33869630:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:17c8ac080cae5dbddf379b733d7f88ff625c92d67f6188271c5769b68cb82d3c", "bytes": 5152, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#tab4", "version": null, "note": "The 51 crosstalk genes that were upregulated and 41 crosstalk genes which were downregulated in periodontitis.", "structure": {"pmcid": "PMC8032519", "section_index": 18, "section_title": "3.4. Crosstalk Genes Bridging Alzheimer's Disease and Periodontitis", "row_count": 4, "column_count": 2}, "table": {"label": "Table 4", "caption": "The 51 crosstalk genes that were upregulated and 41 crosstalk genes which were downregulated in periodontitis.", "rows": [["Regulation pattern in periodontitis", "Crosstalk genes linking periodontitis and Alzheimer's disease"], ["Upregulated", "AMIGO1 (adhesion molecule with Ig-like domain 1; gene ID: 57463)ARG2 (arginase 2; gene ID: 384)BDKRB2 (bradykinin receptor B2; gene ID: 624)BRI3 (brain protein I3; gene ID: 25798)C1D (C1D nuclear receptor corepressor; gene ID: 10438)C3 (complement C3; gene ID: 718)C4A (complement C4A (Rodgers blood group); gene ID: 720)C4B (complement C4B; gene ID: 721)C4B_2 (complement component 4B (Chido blood group), copy 2; gene ID: 100293534)CASP7 (caspase 7; gene ID: 840)CD177 (CD177 molecule; gene ID: 57126)CD38 (CD38 molecule; gene ID: 952)CHCHD10 (coiled-coil-helix-coiled-coil-helix domain containing 10; gene ID: 400916)COX8A (cytochrome c oxidase subunit 8A; gene ID: 1351)CSF3 (colony-stimulating factor 3; gene ID: 1440)CTGF (cellular communication network factor 2; gene ID: 1490)CTSS (cathepsin S; gene ID: 1520)CXCL1 (C-X-C motif chemokine ligand 1; gene ID: 2919)CXCL12 (C-X-C motif chemokine ligand 12; gene ID: 6387)CXCL8 (C-X-C motif chemokine ligand 8; gene ID: 3576)CXCR4 (C-X-C motif chemokine receptor 4; gene ID: 7842)ENPP2 (ectonucleotide pyrophosphatase/phosphodiesterase 2; gene ID: 5168)FCGR3A (Fc fragment of IgG receptor IIIa; gene ID: 2214)FCGR3B (Fc fragment of IgG receptor IIIb; gene ID: 2215)FHL2 (four and a half LIM domains 2; gene ID: 2274)FOS (Fos proto-oncogene, AP-1 transcription factor subunit; gene ID: 2353)FOXO1 (forkhead box O1; gene ID: 2308)GSTK1 (glutathione S-transferase kappa 1; gene ID: 373156)GSTO1 (glutathione S-transferase omega 1; gene ID: 9446)HCLS1 (hematopoietic cell-specific Lyn substrate 1; gene ID: 3059)IGFBP7 (insulin-like growth factor binding protein 7; gene ID: 3490)IL1B (interleukin-1 beta; gene ID: 3553)LYZ (lysozyme; gene ID: 4069)MAK16 (MAK16 homolog; gene ID: 84549)MEF2C (myocyte-specific enhancer factor 2C; gene ID: 4208)MME (membrane metalloendopeptidase; gene ID: 4311)MMP1 (matrix metallopeptidase 1; gene ID: 4312)MMP3 (matrix metallopeptidase 3; gene ID: 4314)MS4A1 (membrane-spanning 4-domains A1; gene ID: 931)MSRA (methionine sulfoxide reductase A; gene ID: 4482)MZB1 (marginal zone B and B1 cell-specific protein; gene ID: 51237)NDUFB8 (NADH:ubiquinone oxidoreductase subunit B8; gene ID: 4714)PECAM1 (platelet endothelial cell adhesion molecule 1; gene ID: 5175)PLAT (plasminogen activator, tissue type; gene ID: 5327)PSENEN (presenilin enhancer, gamma-secretase subunit; gene ID: 55851)SEL1L (SEL1L adaptor subunit of ERAD E3 ubiquitin ligase; gene ID: 6400)SERPINI1 (serpin family I member 1; gene ID: 5274)ST6GAL1 (ST6 beta-galactoside alpha-2,6-sialyltransferase 1; gene ID: 6480)VCAN (versican; gene ID: 1462)VIM (vimentin; gene ID: 7431)WARS2 (tryptophanyl tRNA synthetase 2, mitochondrial; gene ID: 10352)"], [""], ["Downregulated", "ABCA12 (ATP binding cassette subfamily A member 12; gene ID: 26154)ACE (angiotensin I converting enzyme; gene ID: 1636)ADRB1 (adrenoceptor beta 1; gene ID: 153)BCL2L2 (BCL2-like 2; gene ID: 599)BRSK1 (BR serine/threonine kinase 1; gene ID: 84446)CALML5 (calmodulin-like 5; gene ID: 51806)CALR (calreticulin; gene ID: 811)CD36 (CD36 molecule; gene ID: 948)CDH1 (cadherin 1; gene ID: 999)CDK5R1 (cyclin-dependent kinase 5 regulatory subunit 1; gene ID: 8851)CTDSP2 (CTD small phosphatase 2; gene ID: 10106)DNM1 (dynamin 1; gene ID: 1759)DSG1 (desmoglein 1; gene ID: 1828)FLG (filaggrin; gene ID: 2312)GJA1 (gap junction protein alpha 1; gene ID: 2697)GRHL3 (grainyhead-like transcription factor 3; gene ID: 57822)GRIN3B (glutamate ionotropic receptor NMDA type subunit 3B; gene ID: 116444)HM13 (histocompatibility minor 13; gene ID: 81502)HMGCR (3-hydroxy-3-methylglutaryl-CoA reductase; gene ID: 3156)HSPB1 (heat shock protein family B (small) member 1; gene ID: 3315)KAT5 (lysine acetyltransferase 5; gene ID: 10524)MAP3K12 (mitogen-activated protein kinase kinase kinase 12; gene ID: 7786)MED12 (mediator complex subunit 12; gene ID: 9968)MFN2 (mitofusin 2; gene ID: 9927)MYC (MYC proto-oncogene, bHLH transcription factor; gene ID: 4609)NEFL (neurofilament light; gene ID: 4747)NES (exportin 1; gene ID: 7514)NGF (nerve growth factor; gene ID: 4803)NOS3 (nitric oxide synthase 3; gene ID: 4846)NPTXR (neuronal pentraxin receptor; gene ID: 23467)PLXNA3 (plexin A3; gene ID: 55558)PPIL2 (peptidylprolyl isomerase-like 2; gene ID: 23759)PTGS1 (prostaglandin-endoperoxide synthase 1; gene ID: 5742)RPL13 (ribosomal protein L13; gene ID: 6137)SCIMP (SLP adaptor and CSK interacting membrane protein; gene ID: 388325)SPPL2B (signal peptide peptidase-like 2B; gene ID: 56928)TIAF1 (TGFB1-induced antiapoptotic factor 1; gene ID: 9220)TP73 (tumor protein P73; gene ID: 7161)TYRP1 (tyrosinase-related protein 1; gene ID: 7306)USF2 (upstream transcription factor 2, C-Fos interacting; gene ID: 7392)VEGFA (vascular endothelial growth factor A; gene ID: 7422)"]], "row_count": 4, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[18]/table-wrap[1]#tab4"}}, {"id": "asset:table:pmid:33869630:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:699dcaca7aea84f98b3863785d4eb056eebf920dbc3103f234b87a17a6b695c4", "bytes": 2844, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[2]#tab5", "version": null, "note": "Topological characteristics of the top 30 nodes in the crosstalk gene-related PPI network, ranked in descending order of degree.", "structure": {"pmcid": "PMC8032519", "section_index": 18, "section_title": "3.4. Crosstalk Genes Bridging Alzheimer's Disease and Periodontitis", "row_count": 31, "column_count": 8}, "table": {"label": "Table 5", "caption": "Topological characteristics of the top 30 nodes in the crosstalk gene-related PPI network, ranked in descending order of degree.", "rows": [["Node", "Label", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient"], ["MYC", "DEG_AD_down", "1027", "2.127525", "0.466698", "0.47003", "5.03E − 04", "0.001842"], ["HSPB1", "DEG_AD_down", "433", "2.36959", "0.184598", "0.422014", "0.001636", "0.003351"], ["VIM", "DEG_AD_up", "320", "2.663301", "0.116611", "0.375474", "0.001763", "0.005783"], ["KAT5", "DEG_AD_down", "245", "2.566359", "0.089476", "0.389657", "0.003011", "0.005621"], ["RPL13", "DEG_AD_down", "234", "2.589729", "0.089708", "0.386141", "0.001394", "0.005672"], ["FOS", "DEG_AD_up", "226", "2.883151", "0.083642", "0.346843", "1.97E − 04", "0.017606"], ["CDH1", "DEG_AD_down", "171", "2.93191", "0.058428", "0.341075", "0", "0.025911"], ["TP73", "DEG_AD_down", "137", "2.61483", "0.046781", "0.382434", "0.006333", "0.009173"], ["FHL2", "DEG_AD_up", "136", "2.641085", "0.057192", "0.378632", "0.004031", "0.00889"], ["CALR", "DEG_AD_down", "135", "2.812464", "0.046142", "0.35556", "0.002764", "0.010949"], ["GSTK1", "DEG_AD_up", "111", "2.988459", "0.035152", "0.334621", "0", "0.026289"], ["MME", "DEG_AD_up", "104", "2.836988", "0.040386", "0.352487", "0.001307", "0.011694"], ["MED12", "DEG_AD_down", "91", "2.695615", "0.030682", "0.370973", "0.006105", "0.012517"], ["CASP7", "DEG_AD_up", "90", "2.901039", "0.027131", "0.344704", "0.005243", "0.015603"], ["DNM1", "DEG_AD_down", "84", "2.960185", "0.029086", "0.337817", "0.001147", "0.023716"], ["FOXO1", "DEG_AD_up", "67", "2.977784", "0.017403", "0.33582", "0.004071", "0.026586"], ["CXCR4", "DEG_AD_up", "65", "2.998557", "0.020851", "0.333494", "0.003846", "0.028808"], ["NOS3", "DEG_AD_down", "62", "2.963647", "0.018786", "0.337422", "0.002644", "0.027957"], ["NDUFB8", "DEG_AD_up", "56", "3.042412", "0.02136", "0.328687", "0", "0.027447"], ["UBC", "Other gene", "53", "2.084824", "0.149265", "0.479657", "0.015965", "0.027336"], ["NES", "DEG_AD_down", "53", "2.920946", "0.017012", "0.342355", "0.007983", "0.022954"], ["CDK5R1", "DEG_AD_down", "50", "3.0176", "0.0133", "0.331389", "0.002449", "0.037222"], ["NEFL", "DEG_AD_down", "49", "2.913445", "0.014886", "0.343236", "0.008503", "0.024673"], ["C3", "DEG_AD_up", "43", "3.043278", "0.01705", "0.328593", "0", "0.042101"], ["SEL1L", "DEG_AD_up", "42", "3.036065", "0.013066", "0.329374", "0", "0.045635"], ["DSG1", "DEG_AD_down", "41", "3.046163", "0.00857", "0.328282", "0", "0.068464"], ["GJA1", "DEG_AD_down", "41", "3.035199", "0.015703", "0.329468", "0", "0.04037"], ["MEF2C", "DEG_AD_up", "41", "3.039238", "0.008676", "0.32903", "0", "0.068892"], ["LYZ", "DEG_AD_up", "40", "3.042123", "0.008578", "0.328718", "0", "0.065086"], ["GSTO1", "DEG_AD_up", "38", "2.820254", "0.010905", "0.354578", "0.019915", "0.030356"]], "row_count": 31, "column_count": 8, "numeric_cells": 183, "header_rows": 1, "locator": "section[18]/table-wrap[2]#tab5"}}, {"id": "asset:table:pmid:33869630:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e5016c42dafee984b459ade3ec4011b61633300aa9be2d437be4c041eb70b170", "bytes": 810, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#tab6", "version": null, "note": "Classification performance of the 48 feature selection-obtained crosstalk genes in the four periodontitis-related datasets.", "structure": {"pmcid": "PMC8032519", "section_index": 20, "section_title": "3.6. Classification Accuracy Using the Feature Selection-Obtained Crosstalk Genes", "row_count": 5, "column_count": 13}, "table": {"label": "Table 6", "caption": "Classification performance of the 48 feature selection-obtained crosstalk genes in the four periodontitis-related datasets.", "rows": [["", "GSE16134", "GSE10334", "GSE23586", "GSE79705"], ["Samples: test set", "Samples: SVM model predicts accurately", "Accuracy", "Samples: validation set", "Samples: SVM model predicts accurately", "Accuracy", "Samples: validation set", "Samples: SVM model predicts accurately", "Accuracy", "Samples: validation set", "Samples: SVM model predicts accurately", "Accuracy"], ["Case", "93", "92", "91.94%", "183", "177", "88.26%", "3", "3", "50%", "8", "8", "66.66%"], ["Control", "31", "22", "64", "41", "3", "0", "4", "0"], ["Total", "124", "114", "247", "218", "6", "3", "12", "8"]], "row_count": 5, "column_count": 13, "numeric_cells": 32, "header_rows": 2, "locator": "section[20]/table-wrap[1]#tab6"}}, {"id": "asset:table:pmid:33869630:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6b26688de2b9f9f5c8a5c9f539bf15b911079933e6317bd93caf7b149dad922f", "bytes": 2817, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#tab7", "version": null, "note": "Topological characteristics of the top 30 nodes in the TF-crosstalk gene target network, ranking in descending order.", "structure": {"pmcid": "PMC8032519", "section_index": 22, "section_title": "3.8. The Identification of Transcription Factors Regulating the Crosstalk Genes", "row_count": 33, "column_count": 8}, "table": {"label": "Table 7", "caption": "Topological characteristics of the top 30 nodes in the TF-crosstalk gene target network, ranking in descending order.", "rows": [["Node", "Label", "Degree", "Average shortest path length", "Betweenness centrality", "Closeness centrality", "Clustering coefficient", "Topological coefficient"], ["FOS", "DEG_up&TF", "89", "2.178295", "0.206101", "0.459075", "0.020429", "0.03825"], ["VEGFA", "DEG_down", "77", "2.211886", "0.197219", "0.452103", "0.010936", "0.038456"], ["MEF2C", "DEG_up&TF", "76", "2.328165", "0.159945", "0.429523", "0.004211", "0.044258"], ["CDH1", "DEG_down", "69", "2.540052", "0.159392", "0.393693", "0", "0.086634"], ["CXCR4", "DEG_up", "47", "2.596899", "0.075105", "0.385075", "9.25E − 04", "0.083836"], ["MME", "DEG_up", "44", "2.664083", "0.04365", "0.375364", "0", "0.131313"], ["C4A", "DEG_up", "38", "2.661499", "0.029742", "0.375728", "0.01138", "0.118617"], ["VIM", "DEG_up", "38", "2.521964", "0.060293", "0.396516", "0.012802", "0.065789"], ["CSF3", "DEG_up", "36", "2.550388", "0.031734", "0.392097", "0.019048", "0.075137"], ["C4B", "DEG_up", "34", "2.679587", "0.018887", "0.373192", "0.012478", "0.122037"], ["VCAN", "DEG_up", "34", "2.726098", "0.030567", "0.366825", "0", "0.143717"], ["IL1B", "DEG_up", "33", "2.741602", "0.05746", "0.36475", "0", "0.134602"], ["BRSK1", "DEG_down", "30", "2.741602", "0.030404", "0.36475", "0", "0.153788"], ["SERPINI1", "DEG_up", "29", "2.793282", "0.019014", "0.358002", "0", "0.127586"], ["USF2", "DEG_down&TF", "27", "2.591731", "0.027575", "0.385842", "0.045584", "0.081607"], ["GRHL3", "DEG_down", "27", "2.775194", "0.027067", "0.360335", "0", "0.150732"], ["HSPB1", "DEG_down", "26", "2.780362", "0.017981", "0.359665", "0", "0.155678"], ["MMP3", "DEG_up", "26", "2.607235", "0.024377", "0.383548", "0.036923", "0.074984"], ["CTGF", "DEG_up", "25", "2.788114", "0.020669", "0.358665", "0", "0.161905"], ["HMGCR", "DEG_down", "25", "2.767442", "0.041119", "0.361345", "0", "0.16"], ["GATA2", "TF", "24", "2.095607", "0.052687", "0.477189", "0.018116", "0.104678"], ["PLAT", "DEG_up", "24", "2.762274", "0.028075", "0.362021", "0", "0.173148"], ["ETS1", "TF", "22", "2.273902", "0.03767", "0.439773", "0.012987", "0.092022"], ["NPTXR", "DEG_down", "22", "2.826873", "0.020478", "0.353748", "0", "0.154545"], ["AR", "TF", "21", "2.24031", "0.040698", "0.446367", "0.02381", "0.105465"], ["YBX1", "TF", "21", "2.315245", "0.037801", "0.43192", "0.004762", "0.098928"], ["BCL2L2", "DEG_down", "21", "2.813953", "0.018179", "0.355372", "0", "0.144048"], ["FCGR3A", "DEG_up", "21", "2.81137", "0.020521", "0.355699", "0", "0.192799"], ["ABCA12", "DEG_down", "20", "2.79845", "0.010961", "0.357341", "0", "0.2"], ["SP1", "TF", "20", "2.191214", "0.037362", "0.456368", "0.026316", "0.109167"], ["CDK5R1", "DEG_down", "20", "2.824289", "0.017878", "0.354071", "0", "0.156098"], ["FLG", "DEG_down", "20", "2.653747", "0.012281", "0.376826", "0.042105", "0.093043"]], "row_count": 33, "column_count": 8, "numeric_cells": 193, "header_rows": 1, "locator": "section[22]/table-wrap[1]#tab7"}}, {"id": "asset:table:pmid:33869630:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5ba33ebc1750e52ebc7e3c3df317805e28dad3ece3be060b12f09b3348fd83ec", "bytes": 501, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[23]/table-wrap[1]#tab8", "version": null, "note": "The number of crosstalk gene-related DEPs within the four periodontitis-related datasets.", "structure": {"pmcid": "PMC8032519", "section_index": 23, "section_title": "3.9. Signaling Pathways Enriched in the Crosstalk Genes", "row_count": 6, "column_count": 7}, "table": {"label": "Table 8", "caption": "The number of crosstalk gene-related DEPs within the four periodontitis-related datasets.", "rows": [["Data", "Sample", "DEP", "DEP", "DEP", "Log FC", "p value"], ["Up", "Down", "Total", "Abs"], ["GSE23586", "6", "1", "12", "13", ">1", "<0.05"], ["GSE16134", "310", "84", "2", "86", ">1", "<0.05"], ["GSE10334", "247", "77", "2", "79", ">1", "<0.05"], ["GSE79705", "12", "4", "4", "8", ">0", "<0.05"]], "row_count": 6, "column_count": 7, "numeric_cells": 28, "header_rows": 2, "locator": "section[23]/table-wrap[1]#tab8"}}, {"id": "asset:table:pmid:33869630:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:22ade746a93267f18ff982a361f8a4fff5b5ffd43fbd637c0158d7e77e6ccc44", "bytes": 1916, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#tab9", "version": null, "note": "The 12 overlapping genes between 48 feature selection-obtained crosstalk genes and periodontitis-related genes in the DisGeNET database. Among the 12 genes, 6 genes, C4A, C4B, CXCL12, FCGR3A, IL1B, and MMP3, were associated with chronic periodontitis.", "structure": {"pmcid": "PMC8032519", "section_index": 24, "section_title": "3.10. The Identification of Core Crosstalk Genes", "row_count": 29, "column_count": 4}, "table": {"label": "Table 9", "caption": "The 12 overlapping genes between 48 feature selection-obtained crosstalk genes and periodontitis-related genes in the DisGeNET database. Among the 12 genes, 6 genes, C4A, C4B, CXCL12, FCGR3A, IL1B, and MMP3, were associated with chronic periodontitis.", "rows": [["Gene symbol", "Gene ID", "Disease ID", "Disease name"], ["C3", "718", "C0031099", "Periodontitis"], ["C4A", "720", "C0266929", "Chronic periodontitis"], ["C4B", "721", "C0266929", "Chronic periodontitis"], ["CXCL12", "6387", "C0266929", "Chronic periodontitis"], ["FCGR3A", "2214", "C0266929", "Chronic periodontitis"], ["FCGR3A", "2214", "C0031099", "Periodontitis"], ["FCGR3A", "2214", "C0031106", "Periodontitis, juvenile"], ["FCGR3A", "2214", "C0399447", "Early-onset periodontitis"], ["FCGR3A", "2214", "C0031030", "Periapical periodontitis"], ["FCGR3B", "2215", "C0399447", "Early-onset periodontitis"], ["FCGR3B", "2215", "C0031106", "Periodontitis, juvenile"], ["HSPB1", "3315", "C0031030", "Periapical periodontitis"], ["IL1B", "3553", "C1719494", "Periodontitis, localized aggressive"], ["IL1B", "3553", "C1719495", "Aggressive periodontitis, generalized"], ["IL1B", "3553", "C0399447", "Early-onset periodontitis"], ["IL1B", "3553", "C0001342", "Acute periodontitis"], ["IL1B", "3553", "C0031106", "Periodontitis, juvenile"], ["IL1B", "3553", "C0031030", "Periapical periodontitis"], ["IL1B", "3553", "C4025886", "Severe periodontitis"], ["IL1B", "3553", "C0031099", "Periodontitis"], ["IL1B", "3553", "C0266929", "Chronic periodontitis"], ["MME", "4311", "C0031099", "Periodontitis"], ["MMP3", "4314", "C0031106", "Periodontitis, juvenile"], ["MMP3", "4314", "C0001342", "Acute periodontitis"], ["MMP3", "4314", "C0266929", "Chronic periodontitis"], ["MMP3", "4314", "C0031099", "Periodontitis"], ["PLAT", "5327", "C1719495", "Aggressive periodontitis, generalized"], ["VEGFA", "7422", "C0031099", "Periodontitis"]], "row_count": 29, "column_count": 4, "numeric_cells": 57, "header_rows": 1, "locator": "section[24]/table-wrap[1]#tab9"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differential gene expression analysis of periodontitis-related datasets was carried out using the Linear Models for Microarray (limma) package [12] in the R project (version 3.0.1, http://www.r-project.org/) [13]."}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33869630", "asset:table:pmid:33869630:1", "asset:table:pmid:33869630:2", "asset:table:pmid:33869630:3", "asset:table:pmid:33869630:4", "asset:table:pmid:33869630:5", "asset:table:pmid:33869630:6", "asset:table:pmid:33869630:7", "asset:table:pmid:33869630:8", "asset:table:pmid:33869630:9"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:31:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 43112, "completion_tokens": 1552, "cached_tokens": 785}}, "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:33869630", "type": "paper", "label": "pmid:33869630"}, {"id": "source:pmid:33869630", "type": "manuscript", "label": "PMID 33869630 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33869630", "type": "paper", "label": "pmid:33869630"}, {"id": "source:pmid:33869630", "type": "manuscript", "label": "PMID 33869630 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33869630", "type": "extraction", "used": ["source:pmid:33869630"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33869630", "parent_hash": "sha256:f4c8083e24dece79b0f18fcb13820d366b12ee26e272bc2227ce37b9beec45b8", "fork_of": null, "generation": 7}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differential gene expression analysis of periodontitis-related datasets was carried out using the Linear Models for Microarray (limma) package [12] in the R project (version 3.0.1, http://www.r-project.org/) [13]."], "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":"2026-11-04T02:14:33+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}}}