{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:19864493", "kind": "science-record", "revision": 9, "content_hash": "sha256:bad78f3288b63efb5b562edd76cfae5d089b59b312395907722c24047dafbc6a", "created_at": "2026-11-01T15:14:33Z", "updated_at": "2026-11-01T22:41:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Sporadic ALS has compartment-specific aberrant exon splicing and altered cell-matrix adhesion biology.", "doi": "10.1093/hmg/ddp498", "pmid": "19864493", "authors": ["Stuart J Rabin", "Jae Mun Hugo Kim", "Michael Baughn", "Ryan T Libby", "Young Joo Kim", "Yuxin Fan", "Randell T Libby", "Albert La Spada", "Brad Stone", "John Ravits"], "journal": "Human molecular genetics", "year": 2010, "abstract": "Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease characterized by progressive weakness from loss of motor neurons. The fundamental pathogenic mechanisms are unknown and recent evidence is implicating a significant role for abnormal exon splicing and RNA processing. Using new comprehensive genomic technologies, we studied exon splicing directly in 12 sporadic ALS and 10 control lumbar spinal cords acquired by a rapid autopsy system that processed nervous systems specifically for genomic studies. ALS patients had rostral onset and caudally advancing disease and abundant residual motor neurons in this region. We created two RNA pools, one from motor neurons collected by laser capture microdissection and one from the surrounding anterior horns. From each, we isolated RNA, amplified mRNA, profiled whole-genome exon splicing, and applied advanced bioinformatics. We employed rigorous quality control measures at all steps and validated findings by qPCR. In the motor neuron enriched mRNA pool, we found two distinct cohorts of mRNA signals, most of which were up-regulated: 148 differentially expressed genes (P <or= 10(-3)) and 411 aberrantly spliced genes (P <or= 10(-5)). The aberrantly spliced genes were highly enriched in cell adhesion (P <or= 10(-57)), especially cell-matrix as opposed to cell-cell adhesion. Most of the enriching genes encode transmembrane or secreted as opposed to nuclear or cytoplasmic proteins. The differentially expressed genes were not biologically enriched. In the anterior horn enriched mRNA pool, we could not clearly identify mRNA signals or biological enrichment. These findings, perturbed and up-regulated cell-matrix adhesion, suggest possible mechanisms for the contiguously progressive nature of motor neuron degeneration. Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920.", "claims": [{"id": "claim-method", "statement": "To determine aberrant exon splicing, we used an ANOVA-based analysis that generates P-values indicating the probability of aberrant splicing occurring in a particular gene.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:19864493", "locator": "sections[6] \"Exon splicing is significantly aberrant in the motor neuron enriched mRNA pool and is distinct from and more pronounced than differential gene expression\" paragraph 2", "quote": "To determine aberrant exon splicing, we used an ANOVA-based analysis that generates P-values indicating the probability of aberrant splicing occurring in a particular gene."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:19864493", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In the motor neuron enriched mRNA pool, we found two distinct cohorts of mRNA signals, most of which were up-regulated: 148 differentially expressed genes (P ≤ 10−3) and 411 aberrantly spliced genes (P ≤ 10−5).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:19864493", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In the motor neuron enriched mRNA pool, we found two distinct cohorts of mRNA signals, most of which were up-regulated: 148 differentially expressed genes (P ≤ 10−3) and 411 aberrantly spliced genes (P ≤ 10−5)."}, {"asset": "source:pmid:19864493", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "In the motor neuron enriched mRNA pool, we found two distinct cohorts of mRNA signals, most of which were up-regulated: 148 differentially expressed genes (P ≤ 10−3) and 411 aberrantly spliced genes (P ≤ 10−5).", "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:19864493"], "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:GSE18920"], "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:GSE18920"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:19864493", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/hmg/ddp498", "sha256": "sha256:a8852e257762de321c95c2056c2e03b93c83e9eba21645db36d1b40c6328e354", "bytes": 69761, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/hmg/ddp498", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC2796893", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE18920", "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=GSE18920", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18920", "version": null, "note": "Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM468729", "GSM468730", "GSM468731", "GSM468732", "GSM468733", "GSM468734", "GSM468735", "GSM468736", "GSM468737", "GSM468738", "GSM468739", "GSM468740", "GSM468741", "GSM468742", "GSM468743", "GSM468744", "GSM468745", "GSM468746", "GSM468747", "GSM468748", "GSM468749", "GSM468750", "GSM468751", "GSM468752", "GSM468753", "GSM468754", "GSM468755", "GSM468756", "GSM468757", "GSM468758", "GSM468759", "GSM468760", "GSM468761", "GSM468762", "GSM468763", "GSM468764", "GSM468765", "GSM468766", "GSM468767", "GSM468768", "GSM468769", "GSM468770", "GSM468771", "GSM468772"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "5188", "taxon": "Homo sapiens", "title": "Sporadic ALS has compartment-specific aberrant exon splicing and altered cell-matrix adhesion biology", "resolution_checked_at": "2026-11-01T15:14:33Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:19864493:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:61110f5ef8f59116c7364951dd587ba0fa6d65c8717108c4c85a0dbe8d2cd67f", "bytes": 1250, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#DDP498TB1", "version": null, "note": "Demographic details", "structure": {"pmcid": "PMC2796893", "section_index": 3, "section_title": "Special processing of CNS coupled with laser capture microdissection permits collection and selective enrichment of relevant cellular compartments for genomic analysis", "row_count": 23, "column_count": 7}, "table": {"label": "Table 1.", "caption": "Demographic details", "rows": [["Primary diagnosis", "CNS ID number", "Age", "Gender", "Site of onset", "Disease course (years)", "PMI (h)"], ["SALS", "14", "73", "Female", "Bulbar", "1.5", "6"], ["SALS", "16", "61", "Male", "Arm", "2.5", "3.5"], ["SALS", "17", "55", "Male", "Arm", "2", "3"], ["SALS", "18", "80", "Female", "Bulbar", "2", "4"], ["SALS", "27", "74", "Male", "Bulbar", "3.25", "4"], ["SALS", "33", "54", "Male", "Arm", "6.5", "5"], ["SALS", "34", "81", "Female", "Bulbar", "1", "3.5"], ["SALS", "35", "74", "Female", "Bulbar", "5.75", "5"], ["SALS", "60", "58", "Female", "Bulbar", "3", "3"], ["SALS", "63", "68", "Male", "Arm", "2.5", "5"], ["SALS", "64", "47", "Male", "Arm", "3", "6.5"], ["SALS", "68", "72", "Female", "Leg", "1.5", "4"], ["Control", "10", "78", "Male", "NA", "NA", "2.5"], ["Control", "19", "80", "Female", "NA", "NA", "2.5"], ["Control", "26", "49", "Male", "NA", "NA", "4"], ["Control", "39", "77", "Male", "NA", "NA", "2"], ["Control", "42", "61", "Male", "NA", "NA", "6"], ["Control", "44", "80", "Female", "NA", "NA", "5"], ["Control", "55", "71", "Male", "NA", "NA", "13"], ["Control", "59", "73", "Male", "NA", "NA", "8"], ["Control", "65", "82", "Male", "NA", "NA", "4"], ["Control", "67", "77", "Male", "NA", "NA", "4"]], "row_count": 23, "column_count": 7, "numeric_cells": 78, "header_rows": 1, "locator": "section[3]/table-wrap[1]#DDP498TB1"}}, {"id": "asset:table:pmid:19864493:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c2ffe7e8934b7987884f2bc7cd3c4a60a52ca9836e8ccec533c286b3032f769e", "bytes": 5259, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#DDP498TB2", "version": null, "note": "Top 25 aberrantly spliced and top 25 differentially expressed genes", "structure": {"pmcid": "PMC2796893", "section_index": 5, "section_title": "Genomic analysis identifies differentially expressed gene signals in the motor neuron enriched mRNA pool", "row_count": 49, "column_count": 7}, "table": {"label": "Table 2.", "caption": "Top 25 aberrantly spliced and top 25 differentially expressed genes", "rows": [["Gene symbol", "Gene name", "RefSeq", "Alt. splice P-value", "Differential expression P-value", "Fold-change (A versus C)", "# Markers (exons)"], ["ABCA8", "ATP-binding cassette, sub-family A (ABC1), member 8", "NM_007168", "2.84E–17", "0.0147702", "2.07853", "37"], ["ACADVL", "Acyl-Coenzyme A dehydrogenase, very long chain", "NM_000018", "0.07572", "9.62E-05", "−1.36709", "20"], ["AGTRL1", "Angiotensin II receptor-like 1", "NM_005161", "0.00280309", "0.000100449", "2.80667", "6"], ["AQP4", "Aquaporin 4", "NM_001650", "1.35E-27", "1.21E−06", "3.17926", "13"], ["ASPA", "Aspartoacylase (Canavan disease)", "NM_000049", "0.199691", "0.000120487", "2.94572", "6"], ["C1orf198", "Chromosome 1 open reading frame 198", "AK096166", "2.66E−16", "0.00111187", "1.7294", "17"], ["C21orf33", "Chromosome 21 open reading frame 33", "NM_004649", "0.0218155", "0.00010392", "−1.30992", "10"], ["C3", "Complement component 3", "NM_000064", "1.89E−23", "0.00107972", "2.39112", "43"], ["C4A", "Complement component 4A (Rodgers blood group)", "NM_007293", "1.88E−31", "0.000487554", "2.3395", "48"], ["CENTD1", "Centaurin, delta 1", "NM_015230", "9.18E−08", "8.68E−05", "1.86511", "37"], ["COG5", "Component of oligomeric golgi complex 5", "NM_006348", "1.79E−05", "0.000102532", "1.63965", "28"], ["COL1A2", "Collagen, type I, alpha 2", "NM_000089", "2.02E−24", "0.0319974", "1.44001", "47"], ["COL6A3", "ollagen, type VI, Calpha 3", "NM_004369", "3.34E−20", "0.0945555", "1.36456", "45"], ["CPVL", "Carboxypeptidase, vitellogenic-like", "NM_019029", "3.89E−11", "6.99E−06", "2.06165", "17"], ["CXCL16", "Chemokine (C-X-C motif) ligand 16", "NM_022059", "0.00011424", "2.01E−05", "1.99739", "10"], ["DST", "Dystonin", "NM_183380", "9.73E−24", "0.323111", "1.0925", "125"], ["EDNRB", "Endothelin receptor type B", "NM_000115", "2.64E−19", "1.64E−05", "3.01733", "17"], ["ELAVL3", "ELAV (embryonic lethal, abnormal vision, Drosophila)-like", "NM_032281", "1.12E−05", "0.000109817", "−2.14778", "18"], ["EXOSC6", "Exosome component 6", "NM_058219", "0.804989", "0.000105887", "−1.21483", "7"], ["FAM46C", "Family with sequence similarity 46, member C", "NM_017709", "6.43E−08", "0.000117789", "2.4746", "6"], ["FLJ21963", "FLJ21963 protein", "NM_024560", "2.64E−12", "2.35E−05", "3.01776", "17"], ["FLJ44874", "FLJ44874 protein", "AK126822", "0.597731", "1.44E−07", "−1.46746", "3"], ["FLNC", "Filamin C, gamma (actin-binding protein 280)", "NM_001458", "2.80E−16", "0.289023", "1.0877", "48"], ["FN1", "Fibronectin 1", "NM_212482", "2.24E−21", "0.0133788", "2.50828", "63"], ["HIF3A", "Hypoxia inducible factor 3, alpha subunit", "NM_022462", "6.33E−16", "0.0968477", "1.24509", "27"], ["HLA-B", "Major histocompatibility complex, class I, B", "NM_005514", "0.011742", "0.000145132", "2.07808", "3"], ["HLA-DMB", "Major histocompatibility complex, class II, DM beta", "NM_002118", "0.00334092", "0.000122339", "2.64162", "3"], ["HLA-DRA", "Major histocompatibility complex, class II, DR alpha", "NM_019111", "0.0176529", "9.96E−06", "3.75813", "9"], ["INPP5D", "Inositol polyphosphate-5-phosphatase, 145 kDa", "NM_005541", "2.28E−15", "0.00485491", "1.54023", "25"], ["KIAA0644", "KIAA0644 gene product", "NM_014817", "5.30E−18", "0.0764209", "1.16279", "15"], ["KRT73", "Keratin 73", "NM_175068", "0.156092", "6.78E−05", "−1.35392", "9"], ["LRP1", "Low-density lipoprotein-related protein 1 (alpha-2-macroglo", "NM_002332", "2.68E−19", "0.0219457", "1.28675", "105"], ["MACF1", "Microtubule-actin cross-linking factor 1", "NM_012090", "7.85E−22", "0.00408213", "1.24486", "115"], ["MYBPC1", "Myosin binding protein C, slow type", "NM_002465", "1.90E−21", "0.00967833", "1.31138", "31"], ["OR2W3", "Olfactory receptor, family 2, subfamily W, member 3", "NM_001001957", "0.602669", "0.000100305", "−1.45266", "13"], ["OR5AS1", "Olfactory receptor, family 5, subfamily AS, member 1", "NM_001001921", "0.548751", "0.000141626", "−1.3982", "3"], ["PADI2", "Peptidyl arginine deiminase, type II", "NM_007365", "9.72E−14", "0.000114651", "1.6916", "18"], ["PARP9", "Poly (ADP-ribose) polymerase family, member 9", "NM_031458", "0.606104", "2.15E−05", "3.48026", "3"], ["PCDHGC5", "Protocadherin gamma subfamily C, 5", "NM_018929", "2.24E−21", "0.00182203", "1.23154", "100"], ["PYGM", "Phosphorylase, glycogen; muscle (McArdle syndrome, glycogen", "NM_005609", "7.14E−19", "0.000661684", "1.64136", "20"], ["SEMA5B", "Sema domain, seven thrombospondin Repeats (type 1 and", "NM_001031702", "6.12E−25", "0.746505", "1.02067", "31"], ["SF1", "Splicing factor 1", "NM_004630", "3.25E−18", "0.0117229", "1.26463", "32"], ["SLC1A3", "Solute carrier family 1 (glial high affinity glutamate transporter)", "NM_004172", "3.81E−05", "0.000106293", "2.50395", "15"], ["SLC35A4", "Solute carrier family 35, member A4", "NM_080670", "0.793629", "7.95E−05", "−1.49356", "8"], ["SLC4A4", "Solute carrier family 4, sodium bicarbonate co-transporter", "NM_001098484", "1.64E−16", "0.000145173", "2.17261", "31"], ["TJP2", "Tight junction protein 2 (zona occludens 2)", "NM_004817", "9.14E−16", "0.000452437", "2.01894", "31"], ["TRBV19", "T-cell receptor beta variable 19", "BC073930", "1.48E−15", "0.695085", "1.02684", "30"], ["UTRN", "Utrophin", "NM_007124", "1.56E−20", "0.00473928", "1.78074", "74"]], "row_count": 49, "column_count": 7, "numeric_cells": 285, "header_rows": 1, "locator": "section[5]/table-wrap[1]#DDP498TB2"}}, {"id": "asset:table:pmid:19864493:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:167a18825f635a6874e6b6b34d466fabacebb2c90815a8da7c3531692ab1f7f3", "bytes": 2744, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#DDP498TB3", "version": null, "note": "Biological enrichment of aberrantly spliced genes", "structure": {"pmcid": "PMC2796893", "section_index": 7, "section_title": "The aberrantly spliced genes but not the differentially expressed genes in the motor neuron enriched mRNA pool are biologically enriched", "row_count": 34, "column_count": 7}, "table": {"label": "Table 3.", "caption": "Biological enrichment of aberrantly spliced genes", "rows": [["Enrichment", "Enrichment P-value", "% genes in group that are present", "Number of genes present", "Number of genes in group", "GO ID", "GO category"], ["Biological adhesion", "10−58", "8.6758", "57", "657", "22610", "BP"], ["Cell adhesion", "10−58", "8.6758", "57", "657", "7155", "BP"], ["Basement membrane", "10−48", "28.9474", "11", "38", "5604", "CC"], ["Transmembrane receptor protein tyrosine kinase activity", "10−43", "20.5882", "14", "68", "4714", "MF"], ["Collagen", "10−43", "28.5714", "10", "35", "5581", "CC"], ["Extracellular matrix structural constituent", "10−42", "18.75", "15", "80", "5201", "MF"], ["Vascular endothelial growth factor receptor activity", "10−42", "50", "6", "12", "5021", "MF"], ["Laminin-1 complex", "10−41", "62.5", "5", "8", "5606", "CC"], ["Laminin complex", "10−41", "62.5", "5", "8", "43256", "CC"], ["Transmembrane receptor protein kinase activity", "10−41", "18.2927", "15", "82", "19199", "MF"], ["Regulation of cell migration", "10−39", "29.0323", "9", "31", "30334", "BP"], ["Cell–substrate adhesion", "10−31", "17.3913", "12", "69", "31589", "BP"], ["Cell–matrix adhesion", "10−28", "17.1875", "11", "64", "7160", "BP"], ["Extracellular region part", "10−27", "6.38003", "46", "721", "44421", "CC"], ["Protein binding", "10−27", "3.32847", "228", "6850", "5515", "MF"], ["Plasma membrane part", "10−25", "4.74517", "81", "1707", "44459", "CC"], ["Regulation of cell motility", "10−25", "14.2857", "12", "84", "51270", "BP"], ["Cell–substrate junction assembly", "10−25", "60", "3", "5", "7044", "BP"], ["Cell junction assembly", "10−25", "60", "3", "5", "34329", "BP"], ["Extracellular matrix organization and biogenesis", "10−24", "19.5122", "8", "41", "30198", "BP"], ["Collagen binding", "10−23", "29.4118", "5", "17", "5518", "MF"], ["Phosphate transport", "10−23", "13.1868", "12", "91", "6817", "BP"], ["Hemidesmosome", "10−23", "100", "2", "2", "30056", "CC"], ["Integrin-mediated signaling pathway", "10−23", "16.3636", "9", "55", "7229", "BP"], ["Proteinaceous extracellular matrix", "10−22", "9.00901", "20", "222", "5578", "CC"], ["Regulation of embryonic development", "10−22", "50", "3", "6", "45995", "BP"], ["Stereocilium", "10−22", "50", "3", "6", "32420", "CC"], ["Fibroblast growth factor receptor activity", "10−22", "50", "3", "6", "5007", "MF"], ["Extracellular matrix", "10−21", "8.77193", "20", "228", "31012", "CC"], ["Anatomical structure development", "10−21", "5.15464", "55", "1067", "48856", "BP"], ["Structural molecule activity", "10−21", "5.91716", "40", "676", "5198", "MF"], ["Integrin complex", "10−20", "21.4286", "6", "28", "8305", "CC"], ["Developmental process", "10−20", "4.04485", "101", "2497", "32502", "BP"]], "row_count": 34, "column_count": 7, "numeric_cells": 166, "header_rows": 1, "locator": "section[7]/table-wrap[1]#DDP498TB3"}}, {"id": "asset:table:pmid:19864493:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:27df59ef0bbcab5fe899ab576caf8625d52ef6a07105270e098704567bb94bcd", "bytes": 6199, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#DDP498TB4", "version": null, "note": "Aberrantly spliced cell adhesion genes", "structure": {"pmcid": "PMC2796893", "section_index": 7, "section_title": "The aberrantly spliced genes but not the differentially expressed genes in the motor neuron enriched mRNA pool are biologically enriched", "row_count": 58, "column_count": 8}, "table": {"label": "Table 4.", "caption": "Aberrantly spliced cell adhesion genes", "rows": [["Gene symbol", "Gene name", "RefSeq", "Alt. splice P-value", "Differential expression P-value", "Fold change (A versus C)", "Number of markers", "Protein location"], ["AEBP1", "AE binding protein 1", "NM_001129", "2.44E−10", "0.0186655", "1.69315", "27", "sec"], ["ANXA9", "Annexin A9", "NM_003568", "8.62E−07", "0.971328", "−1.00249", "14", "cyt"], ["CDH11", "Cadherin 11, type 2, OB-cadherin (osteoblast)", "NM_001797", "2.94E−06", "0.00458728", "1.65623", "21", "tm"], ["CDH5", "Cadherin 5, type 2, VE-cadherin (vascular epithelium)", "NM_001795", "2.36E−06", "0.102509", "1.27449", "19", "tm"], ["CDH23", "Cadherin-like 23", "NM_022124", "1.61E−07", "0.156179", "1.12818", "71", "tm"], ["CTNNA3", "Catenin (cadherin-associated protein), alpha 3", "NM_013266", "6.53E−06", "0.00648134", "1.79781", "25", "cyt"], ["CTNND2", "Catenin (cadherin-associated protein), delta 2", "NM_001332", "1.59E−06", "0.0867763", "1.1616", "32", "cyt"], ["CD44", "CD44 molecule (Indian blood group)", "NM_000610", "5.13E−12", "0.000479249", "1.89535", "21", "tm"], ["CLDN10", "Claudin 10", "NM_182848", "6.03E−06", "0.162268", "1.20723", "12", "tm"], ["CLDN11", "Claudin 11 (oligodendrocyte transmembrane protein)", "NM_005602", "1.94E−06", "0.00435624", "1.53442", "6", "tm"], ["COL3A1", "Collagen, type III, alpha 1 (Ehlers-Danlos syndrome type)", "NM_000090", "3.84E−09", "0.221719", "1.17435", "49", "sec"], ["COL6A3", "Collagen, type VI, alpha 3", "NM_004369", "3.34E−20", "0.0945555", "1.36456", "45", "sec"], ["COL11A1", "Collagen, type XI, alpha 1", "NM_001854", "2.33E−09", "0.178053", "1.20705", "46", "sec"], ["COL12A1", "Collagen, type XII, alpha 1", "NM_004370", "1.69E−10", "0.0105983", "1.79078", "69", "sec"], ["COL13A1", "Collagen, type XIII, alpha 1", "NM_005203", "6.71E−09", "0.169929", "1.15626", "25", "sec"], ["COL14A1", "Collagen, type XIV, alpha 1 (undulin)", "NM_021110", "1.06E−08", "0.00638787", "1.58704", "24", "sec"], ["COL27A1", "Collagen, type XXVII, alpha 1", "NM_032888", "1.43E−06", "0.243964", "−1.10262", "46", "sec"], ["CSF3R", "Colony stimulating factor 3 receptor (granulocyte)", "NM_156039", "2.04E−06", "0.126098", "1.10957", "24", "tm"], ["CYR61", "Cysteine-rich, angiogenic inducer, 61", "NM_001554", "1.17E−07", "0.0315499", "1.55961", "8", "sec"], ["DDR1", "Discoidin domain receptor family, member 1", "NM_013993", "4.24E−08", "0.103136", "1.15821", "31", "tm"], ["DST", "Dystonin", "NM_183380", "9.73E−24", "0.323111", "1.0925", "125", "cyt"], ["ENG", "Endoglin (Osler-Rendu-Weber syndrome 1)", "NM_000118", "5.65E−06", "0.342529", "1.19248", "20", "tm"], ["ERBB2IP", "Erbb2 interacting protein", "NM_018695", "6.83E−07", "0.000240051", "2.08535", "30", "cyt"], ["ECM2", "Extracellular matrix protein 2, female organ and adipocyte", "NM_001393", "4.60E−06", "0.0461937", "1.59777", "20", "sec"], ["FAT", "FAT // FAT tumor suppressor homolog 1 (Drosophila)", "NM_005245", "1.45E−08", "0.00159728", "1.86066", "31", "tm"], ["FN1", "Fibronectin 1", "NM_212482", "2.24E−21", "0.0133788", "2.50828", "63", "sec"], ["HMCN1", "Hemicentin 1", "NM_031935", "7.81E−07", "0.209353", "1.1854", "116", "sec"], ["HSPG2", "Heparan sulfate proteoglycan 2", "NM_005529", "2.11E−09", "0.938373", "−1.00658", "101", "sec"], ["HEPACAM", "Hepatocyte cell adhesion molecule", "NM_152722", "2.96E−06", "0.0223096", "1.54885", "13", "tm"], ["IGSF11", "Immunoglobulin superfamily, member 11", "NM_001015887", "5.57E−08", "0.0724414", "1.24835", "13", "tm"], ["ITGA6", "Integrin, alpha 6", "NM_000210", "9.56E−08", "0.0229754", "2.06743", "29", "tm"], ["ITGAX", "Integrin, alpha X (complement component 3 receptor 4 subunit)", "NM_000887", "7.10E−08", "0.305373", "1.09177", "29", "tm"], ["ITGB3", "Integrin, beta 3 (platelet glycoprotein IIIa, antigen CD61)", "NM_000212", "1.12E−06", "0.394661", "1.16482", "20", "tm"], ["ITGB4", "Integrin, beta 4", "NM_000213", "4.07E−15", "0.183707", "1.14822", "44", "tm"], ["ITGB7", "integrin, beta 7", "NM_000889", "1.28E−12", "0.345837", "−1.07065", "17", "tm"], ["ITGBL1", "ITGBL1 // integrin, beta-like 1 (with EGF-like repeat domains)", "NM_004791", "2.24E−14", "0.00392462", "1.97861", "16", "tm"], ["JAM2", "Junctional adhesion molecule 2", "NM_021219", "3.87E−08", "0.00548407", "2.02731", "13", "tm"], ["LAMB1", "Laminin, beta 1", "NM_002291", "2.61E−13", "0.0290629", "1.61794", "36", "sec"], ["LAMB2", "Laminin, beta 2 (laminin S)", "NM_002292", "3.16E−06", "0.155571", "1.21405", "40", "sec"], ["LAMC3", "Laminin, gamma 3", "NM_006059", "8.59E−06", "0.370666", "−1.06083", "35", "sec"], ["LPP", "LIM domain containing preferred translocation partner in lip", "NM_005578", "1.40E−06", "0.147014", "1.51955", "13", "cyt"], ["MYBPC1", "Myosin binding protein C, slow type", "NM_002465", "1.90E−21", "0.00967833", "1.31138", "31", "cyt"], ["NCAN", "Neurocan", "NM_004386", "4.77E−10", "0.206516", "1.13639", "25", "sec"], ["NRP2", "Neuropilin 2", "NM_003872", "5.65E−07", "0.0447044", "1.29315", "36", "tm"], ["PARVG", "Parvin, gamma", "NM_022141", "2.03E−07", "0.015984", "1.25824", "14", "cyt"], ["PDZD2", "PDZ domain containing 2", "NM_178140", "2.86E−07", "0.0529539", "1.34362", "44", "cyt"], ["PECAM1", "Platelet/endothelial cell adhesion molecule (CD31 antigen)", "NM_000442", "3.50E−06", "0.023662", "2.42764", "17", "tm"], ["PCDHGC5", "Protocadherin gamma subfamily C, 5", "NM_018929", "2.24E−21", "0.00182203", "1.23154", "100", "tm"], ["RELN", "Reelin", "NM_173054", "3.03E−06", "0.0459772", "1.59369", "73", "sec"], ["SSPN", "Sarcospan (Kras oncogene-associated gene)", "NM_005086", "1.23E−07", "0.00153469", "1.87677", "8", "tm"], ["SEMA5A", "Sema domain, seven thrombospondin Repeats", "NM_003966", "6.24E−06", "0.132723", "1.27857", "29", "tm"], ["SOX9", "SRY (sex determining region Y)-box 9 (campomelic dysplasia)", "NM_000346", "3.07E−07", "0.584737", "1.05446", "9", "nuc"], ["TNC", "Tenascin C (hexabrachion)", "NM_002160", "2.55E−08", "0.125224", "1.66206", "36", "sec"], ["TESK2", "Testis-specific kinase 2", "NM_007170", "6.75E−07", "0.0632463", "1.36536", "14", "nuc"], ["TRIP6", "Thyroid hormone receptor interactor 6", "NM_003302", "2.74E−07", "0.194651", "1.16145", "13", "cyt"], ["VCAN", "Versican", "NM_004385", "8.36E−11", "0.000148832", "2.61415", "26", "sec"], ["VWF", "von Willebrand factor", "NM_000552", "5.40E−12", "0.085195", "1.51082", "46", "sec"]], "row_count": 58, "column_count": 8, "numeric_cells": 340, "header_rows": 1, "locator": "section[7]/table-wrap[2]#DDP498TB4"}}, {"id": "asset:table:pmid:19864493:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cb39ffe1309f40377acf6f558aed4924f91f8e52c05ec36c84a5fd318e286629", "bytes": 985, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#DDP498TB5", "version": null, "note": "Summary of key findings", "structure": {"pmcid": "PMC2796893", "section_index": 12, "section_title": "DISCUSSION", "row_count": 7, "column_count": 3}, "table": {"label": "Table 5.", "caption": "Summary of key findings", "rows": [["", "Motor neuron enriched mRNA pool", "Anterior horn enriched mRNA pool"], ["Cellularity", "Homogeneous (single-cell enriched)", "Heterogeneous (glia, endothelium, small neurons, degenerating neurons)"], ["Anatomic size", "Highly discrete", "Comparatively vast"], ["Differential gene expression", "148 genes", "Not detectable above noise"], ["Biological enrichment of differentially expressed genes", "Not detectable above noise", "Not detectable above noise"], ["Aberrant exon splicing", "411 genes", "Not detectable above noise"], ["Biological enrichment of aberrantly spliced genes", "Cell–matrix adhesion and extracellular matrix biology; also transmembrane receptor protein tyrosine kinase activity, vascular endothelial growth factor receptor activity, and regulation of cell motility", "Not detectable above noise"]], "row_count": 7, "column_count": 3, "numeric_cells": 2, "header_rows": 1, "locator": "section[12]/table-wrap[1]#DDP498TB5"}}], "gaps": ["asset:data:geo:GSE18920 not downloaded", "asset:data:geo:GSE18920 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To determine aberrant exon splicing, we used an ANOVA-based analysis that generates P-values indicating the probability of aberrant splicing occurring in a particular gene."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE18920"], "resolved_accessions": ["GSE18920"], "statements": ["Data deposition: GeneChip raw data (CEL-files) have been deposited for public access in the Gene Expression Omnibus (GEO), www.ncbi.nlm.nih.gov/geo, accession number GSE18920."], "basis": "The paper names GSE18920 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:19864493", "data:geo:GSE18920", "asset:table:pmid:19864493:1", "asset:table:pmid:19864493:2", "asset:table:pmid:19864493:3", "asset:table:pmid:19864493:4", "asset:table:pmid:19864493:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE18920"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:39Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 137615, "completion_tokens": 3115, "cached_tokens": 69690}}, "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:19864493", "type": "paper", "label": "pmid:19864493"}, {"id": "source:pmid:19864493", "type": "manuscript", "label": "PMID 19864493 full text"}, {"id": "data:geo:GSE18920", "type": "dataset", "label": "GEO GSE18920"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:19864493", "type": "paper", "label": "pmid:19864493"}, {"id": "source:pmid:19864493", "type": "manuscript", "label": "PMID 19864493 full text"}, {"id": "data:geo:GSE18920", "type": "dataset", "label": "GEO GSE18920"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-19864493", "type": "extraction", "used": ["source:pmid:19864493"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE18920", "type": "accession_resolution", "used": ["data:geo:GSE18920"], "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:19864493", "parent_hash": "sha256:38558fc99bee195aa8a77849388be23730d6fca3fac2ec86a050a2fbf19e0d63", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE18920 licence not read", "asset:data:geo:GSE18920 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["sures at all steps and validated findings by qPCR. In the motor neuron enriched mRNA pool, we"], "order_basis": "paper_text_order:1036", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To determine aberrant exon splicing, we used an ANOVA-based analysis that generates P-values indicating the probability of aberrant splicing occurring in a particular gene."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T00:39:21+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}}}