{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28415559", "kind": "science-record", "revision": 7, "content_hash": "sha256:1c6b8db43549de18213012820db9a6592cdd7fc0b6e67ed31d224e4b44497e6e", "created_at": "2026-11-01T15:40:25Z", "updated_at": "2026-11-01T21:20:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptome analysis reveals differentially expressed lncRNAs between oral squamous cell carcinoma and healthy oral mucosa.", "doi": "10.18632/oncotarget.16358", "pmid": "28415559", "authors": ["Lu Feng", "John R Houck", "Pawadee Lohavanichbutr", "Chu Chen"], "journal": "Oncotarget", "year": 2017, "abstract": "Oral cavity and oropharyngeal squamous cell carcinoma (OSCC) is a major cancer type in the head and neck region. To better understand the roles long non-coding RNA (lncRNA) play in OSCC carcinogenesis, we compared the expression levels of 3,054 probe sets for lncRNAs between 167 OSCCs and 45 healthy oral mucosa using an Affymetrix HG U133 plus 2.0 array dataset. We found 658 lncRNA transcripts (790 probe sets) to be significantly differentially expressed using a criteria of FDR < 0.01, with 36 of them (39 probe sets) showing more than a 2-fold change. We further validated the top differentially expressed lncRNAs in three independent datasets from Gene Expression Omnibus (GEO) repository: GSE42743, GSE9844, and GSE6791. Fourteen lncRNAs (15 probe sets) were validated in all three datasets using the criteria FDR < 0.01: LOC441178, C5orf66-AS1, HCG22, FLG-AS1, CCL14/CCL15-CCL14, LOC100506990, TRIP10, PCBP1-AS1, LINC01315, LINC00478, COX10-AS1/LOC100506974, MLLT4-AS1, MIR31HG, and DUXAP10/LINC01296. Three lncRNAs in the validated list which showed the highest fold change (LOC441178, HCG22 and C5orf66-AS1) were verified by quantitative RT-PCR in a subset of 20 OSCCs and 10 control samples. In silico prediction of their functional role has given us directions for further investigation.", "claims": [{"id": "claim-method", "statement": "The statistical analysis of differentially expressed lncRNA (between cases and controls) was performed using linear regression, adjusting for age and sex.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28415559", "locator": "sections[9] \"Statistical analysis\" paragraph 2", "quote": "The statistical analysis of differentially expressed lncRNA (between cases and controls) was performed using linear regression, adjusting for age and sex."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28415559", "locator": "sections[8] \"Gene expression array data and identification of lncRNAs\" paragraph 2", "quote": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 658 significantly differentially expressed lncRNA transcripts between OSCC and healthy oral mucosa using linear regression adjusted for age and sex, with FDR < 0.01 and a 2-fold expression difference as selection criteria; source microarray data were obtained from the OralChip study (167 OSCCs and 45 healthy oral-mucosa samples), normalized with RMA, and accessed through GEO under accession GSE30784.", "kind": "quantitative", "target": {"value": 2.0, "unit": "fold change", "tolerance": null, "source": "We found 658 lncRNA transcripts (790 probe sets) to be significantly differentially expressed using a criteria of FDR < 0.01, with 36 of them (39 probe sets) showing more than a 2-fold change."}, "evidence": [{"asset": "source:pmid:28415559", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We found 658 lncRNA transcripts (790 probe sets) to be significantly differentially expressed using a criteria of FDR < 0.01, with 36 of them (39 probe sets) showing more than a 2-fold change."}, {"asset": "source:pmid:28415559", "locator": "sections[9] \"Statistical analysis\" paragraph 2", "quote": "The statistical analysis of differentially expressed lncRNA (between cases and controls) was performed using linear regression, adjusting for age and sex."}, {"asset": "source:pmid:28415559", "locator": "sections[9] \"Statistical analysis\" paragraph 2", "quote": "The false discovery rate (FDR) of 0.01 and a 2-fold difference in expression between the two groups were used as criteria to select the differentially expressed lncRNA."}, {"asset": "source:pmid:28415559", "locator": "sections[8] \"Gene expression array data and identification of lncRNAs\" paragraph 2", "quote": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784."}, {"asset": "source:pmid:28415559", "locator": "sections[8] \"Gene expression array data and identification of lncRNAs\" paragraph 2", "quote": "The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls."}, {"asset": "source:pmid:28415559", "locator": "sections[8] \"Gene expression array data and identification of lncRNAs\" paragraph 2", "quote": "CEL files were preprocessed and normalized using RMA algorithm in Partek Genomics Suite™ software version 6.6."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified 658 significantly differentially expressed lncRNA transcripts between OSCC and healthy oral mucosa using linear regression adjusted for age and sex, with FDR < 0.01 and a 2-fold expression difference as selection criteria; source microarray data were obtained from the OralChip study (167 OSCCs and 45 healthy oral-mucosa samples), normalized with RMA, and accessed through GEO under accession GSE30784.", "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:28415559"], "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:GSE30784"], "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:GSE30784"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28415559", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/oncotarget.16358", "sha256": "sha256:65adc3ed0d9374eb36ecd76a579a5cf5773b86aa94e3ec03f437b0dc79bd02f5", "bytes": 37316, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/oncotarget.16358", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5458226", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE30784", "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=GSE30784", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30784", "version": null, "note": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM764749", "GSM764750", "GSM764751", "GSM764752", "GSM764753", "GSM764754", "GSM764755", "GSM764756", "GSM764757", "GSM764758", "GSM764759", "GSM764760", "GSM764761", "GSM764762", "GSM764763", "GSM764764", "GSM764765", "GSM764766", "GSM764767", "GSM764768", "GSM764769", "GSM764770", "GSM764771", "GSM764772", "GSM764773", "GSM764774", "GSM764775", "GSM764776", "GSM764777", "GSM764778", "GSM764779", "GSM764780", "GSM764781", "GSM764782", "GSM764783", "GSM764784", "GSM764785", "GSM764786", "GSM764787", "GSM764788", "GSM764789", "GSM764790", "GSM764791", "GSM764792", "GSM764793", "GSM764794", "GSM764795", "GSM764796", "GSM764797", "GSM764798", "GSM764799", "GSM764800", "GSM764801", "GSM764802", "GSM764803", "GSM764804", "GSM764805", "GSM764806", "GSM764807", "GSM764808", "GSM764809", "GSM764810", "GSM764811", "GSM764812", "GSM764813", "GSM764814", "GSM764815", "GSM764816", "GSM764817", "GSM764818", "GSM764819", "GSM764820", "GSM764821", "GSM764822", "GSM764823", "GSM764824", "GSM764825", "GSM764826", "GSM764827", "GSM764828", "GSM764829", "GSM764830", "GSM764831", "GSM764832", "GSM764833", "GSM764834", "GSM764835", "GSM764836", "GSM764837", "GSM764838", "GSM764839", "GSM764840", "GSM764841", "GSM764842", "GSM764843", "GSM764844", "GSM764845", "GSM764846", "GSM764847", "GSM764848", "GSM764849", "GSM764850", "GSM764851", "GSM764852", "GSM764853", "GSM764854", "GSM764855", "GSM764856", "GSM764857", "GSM764858", "GSM764859", "GSM764860", "GSM764861", "GSM764862", "GSM764863", "GSM764864", "GSM764865", "GSM764866", "GSM764867", "GSM764868", "GSM764869", "GSM764870", "GSM764871", "GSM764872", "GSM764873", "GSM764874", "GSM764875", "GSM764876", "GSM764877", "GSM764878", "GSM764879", "GSM764880", "GSM764881", "GSM764882", "GSM764883", "GSM764884", "GSM764885", "GSM764886", "GSM764887", "GSM764888", "GSM764889", "GSM764890", "GSM764891", "GSM764892", "GSM764893", "GSM764894", "GSM764895", "GSM764896", "GSM764897", "GSM764898", "GSM764899", "GSM764900", "GSM764901", "GSM764902", "GSM764903", "GSM764904", "GSM764905", "GSM764906", "GSM764907", "GSM764908", "GSM764909", "GSM764910", "GSM764911", "GSM764912", "GSM764913", "GSM764914", "GSM764915", "GSM764916", "GSM764917", "GSM764918", "GSM764919", "GSM764920", "GSM764921", "GSM764922", "GSM764923", "GSM764924", "GSM764925", "GSM764926", "GSM764927", "GSM764928", "GSM764929", "GSM764930", "GSM764931", "GSM764932", "GSM764933", "GSM764934", "GSM764935", "GSM764936", "GSM764937", "GSM764938", "GSM764939", "GSM764940", "GSM764941", "GSM764942", "GSM764943", "GSM764944", "GSM764945", "GSM764946", "GSM764947", "GSM764948", "GSM764949", "GSM764950", "GSM764951", "GSM764952", "GSM764953", "GSM764954", "GSM764955", "GSM764956", "GSM764957", "GSM764958", "GSM764959", "GSM764960", "GSM764961", "GSM764962", "GSM764963", "GSM764964", "GSM764965", "GSM764966", "GSM764967", "GSM764968", "GSM764969", "GSM764970", "GSM764971", "GSM764972", "GSM764973", "GSM764974", "GSM764975", "GSM764976", "GSM764977"], "sample_count": 229, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of oral squamous cell carcinoma (OSCC)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE42743", "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=GSE42743", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42743", "version": null, "note": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1049079", "GSM1049080", "GSM1049081", "GSM1049082", "GSM1049083", "GSM1049084", "GSM1049085", "GSM1049086", "GSM1049087", "GSM1049088", "GSM1049089", "GSM1049090", "GSM1049091", "GSM1049092", "GSM1049093", "GSM1049094", "GSM1049095", "GSM1049096", "GSM1049097", "GSM1049098", "GSM1049099", "GSM1049100", "GSM1049101", "GSM1049102", "GSM1049103", "GSM1049104", "GSM1049105", "GSM1049106", "GSM1049107", "GSM1049108", "GSM1049109", "GSM1049110", "GSM1049111", "GSM1049112", "GSM1049113", "GSM1049114", "GSM1049115", "GSM1049116", "GSM1049117", "GSM1049118", "GSM1049119", "GSM1049120", "GSM1049121", "GSM1049122", "GSM1049123", "GSM1049124", "GSM1049125", "GSM1049126", "GSM1049127", "GSM1049128", "GSM1049129", "GSM1049130", "GSM1049131", "GSM1049132", "GSM1049133", "GSM1049134", "GSM1049135", "GSM1049136", "GSM1049137", "GSM1049138", "GSM1049139", "GSM1049140", "GSM1049141", "GSM1049142", "GSM1049143", "GSM1049144", "GSM1049145", "GSM1049146", "GSM1049147", "GSM1049148", "GSM1049149", "GSM1049150", "GSM1049151", "GSM1049152", "GSM1049153", "GSM1049154", "GSM1049155", "GSM1049156", "GSM1049157", "GSM1049158", "GSM1049159", "GSM1049160", "GSM1049161", "GSM1049162", "GSM1049163", "GSM1049164", "GSM1049165", "GSM1049166", "GSM1049167", "GSM1049168", "GSM1049169", "GSM1049170", "GSM1049171", "GSM1049172", "GSM1049173", "GSM1049174", "GSM1049175", "GSM1049176", "GSM1049177", "GSM1049178", "GSM1049179", "GSM1049180", "GSM1049181"], "sample_count": 103, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Oral Cavity Cancer Compared to Adjacent \"Normal\" Tissue [Validation Set]", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6791", "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=GSE6791", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6791", "version": null, "note": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM155645", "GSM155646", "GSM155647", "GSM155648", "GSM155649", "GSM155650", "GSM155651", "GSM155652", "GSM155653", "GSM155654", "GSM155655", "GSM155656", "GSM155657", "GSM155658", "GSM155659", "GSM155660", "GSM155661", "GSM155662", "GSM155663", "GSM155664", "GSM155665", "GSM155666", "GSM155667", "GSM155668", "GSM155669", "GSM155670", "GSM155671", "GSM155672", "GSM155673", "GSM155674", "GSM155675", "GSM155676", "GSM155677", "GSM155678", "GSM155679", "GSM155680", "GSM155681", "GSM155682", "GSM155683", "GSM155684", "GSM155685", "GSM155686", "GSM155687", "GSM155688", "GSM155689", "GSM155690", "GSM155691", "GSM155692", "GSM155693", "GSM155694", "GSM155695", "GSM155696", "GSM155697", "GSM155698", "GSM155699", "GSM155700", "GSM155701", "GSM155702", "GSM155703", "GSM155704", "GSM155705", "GSM155706", "GSM155707", "GSM155708", "GSM155709", "GSM155710", "GSM155711", "GSM155712", "GSM155713", "GSM155714", "GSM155715", "GSM155716", "GSM155717", "GSM155718", "GSM155719", "GSM155720", "GSM155721", "GSM155722", "GSM155723", "GSM155724", "GSM155725", "GSM155726", "GSM155727", "GSM155728"], "sample_count": 84, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Profiles of HPV-Positive and -Negative Head/Neck and Cervical Cancers", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE9844", "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=GSE9844", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE9844", "version": null, "note": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM248238", "GSM248650", "GSM248651", "GSM248652", "GSM248653", "GSM248655", "GSM248656", "GSM248658", "GSM248659", "GSM248660", "GSM248661", "GSM248662", "GSM248663", "GSM248664", "GSM248665", "GSM248667", "GSM248668", "GSM248669", "GSM248670", "GSM248671", "GSM248672", "GSM248673", "GSM248674", "GSM248675", "GSM248676", "GSM248677", "GSM248678", "GSM248679", "GSM248680", "GSM248681", "GSM248682", "GSM248683", "GSM248684", "GSM248685", "GSM248686", "GSM248687", "GSM248780", "GSM248781"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptomic Dissection of Tongue Squamous Cell Carcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28415559:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b1af4f6dc162b9e2c2b2542b7c8b417286015269949b8c1217c3f81f8bbfe8b9", "bytes": 680, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Characteristics of four microarray datasets used in this study", "structure": {"pmcid": "PMC5458226", "section_index": 3, "section_title": "Differentially expressed lncRNA genes between cases and controls", "row_count": 8, "column_count": 6}, "table": {"label": "Table 1", "caption": "Characteristics of four microarray datasets used in this study", "rows": [["Characteristics", "FHCRC dataset [34] (n = 212)", "GSE42743 [35] (n = 103)", "GSE9844 [36] (n = 38)", "GSE6791 [37] (n = 49)"], ["Case", "Cancer", "167 (OSCC)", "74 (oral cavity)", "26 (tongue)", "35 (OSCC)"], ["Control", "45 (healthy normal)", "29 (adjacent normal)", "12 (adjacent normal)", "14 (non-cancerous normal)"], ["Gender", "Male", "152", "79", "29", "29"], ["Female", "60", "24", "9", "20"], ["Age", "< 50", "64", "29", "11", "7"], ["50~70", "118", "51", "24", "31"], ["> 70", "30", "23", "3", "11"]], "row_count": 8, "column_count": 6, "numeric_cells": 35, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:28415559:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:39eae5944d93c1830f0ae76f14f7924637b4ba0596d8c59dcec5b33aae2a4ca9", "bytes": 4034, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#T2", "version": null, "note": "Validation of 39 differentially expressed probe sets between OSCC and control in three independent datasets", "structure": {"pmcid": "PMC5458226", "section_index": 3, "section_title": "Differentially expressed lncRNA genes between cases and controls", "row_count": 40, "column_count": 8}, "table": {"label": "Table 2", "caption": "Validation of 39 differentially expressed probe sets between OSCC and control in three independent datasets", "rows": [["Probe sets ID", "Gene Symbol", "Chromosomal Location", "Fold change in FHCRC dataset", "Q-value in FHCRC dataset", "Q-value in GSE42743", "Q-value in GSE9844", "Q-value in GSE6791"], ["1563894_at*", "LOC441178", "chr6q27", "–14.50", "8.83E-49", "1.00E-12", "1.11E-06", "6.09E-13"], ["1561685_a_at*", "LOC441178", "chr6q27", "–14.23", "8.83E-49", "5.22E-13", "1.11E-06", "2.26E-13"], ["1558920_at", "SLC8A1-AS1", "chr2p22.1", "–8.43", "5.85E-45", "6.51E-07", "0.02", "1.83E-03"], ["236444_x_at", "C5orf66-AS1", "chr5q31.1", "–6.60", "1.91E-28", "4.32E-09", "2.29E-03", "9.62E-06"], ["227725_at*", "ST6GALNAC1", "chr17q25.1", "–5.87", "1.44E-15", "1.93E-09", "0.02", "1.18E-04"], ["204919_at*", "PRH1-PRR4/PRR4", "chr12p/chr12p13", "–5.31", "4.18E-06", "5.29E-03", "0.59", "0.03"], ["1560767_at*", "HCG22", "chr6p21.33", "–3.95", "1.91E-28", "5.83E-14", "2.35E-05", "1.50E-05"], ["241014_at", "FLG-AS1", "chr1q21.3", "–3.61", "6.52E-35", "5.22E-13", "6.69E-06", "9.62E-06"], ["244620_at", "SLC8A1-AS1", "chr2p22.1", "–3.29", "1.81E-34", "4.33E-06", "0.04", "2.14E-03"], ["224997_x_at", "H19/MIR675", "chr11p15.5", "–3.23", "6.43E-04", "0.05", "0.10", "0.11"], ["205392_s_at*", "CCL14/CCL15-CCL14", "chr17q11.2/chr17q12", "–2.92", "2.08E-14", "1.29E-08", "7.54E-06", "7.39E-07"], ["227917_at", "LOC100506990", "chr8p23.1", "–2.77", "4.44E-21", "1.93E-09", "1.04E-03", "6.38E-04"], ["242546_at", "DUXAP10/LINC01296", "chr14q11.2", "2.75", "3.56E-09", "1.49E-06", "8.29E-03", "3.18E-04"], ["202734_at*", "TRIP10", "chr19p13.3", "–2.69", "4.82E-33", "3.06E-06", "7.44E-03", "6.29E-06"], ["1557389_at", "SH3PXD2A-AS1", "chr10q24.33", "–2.51", "6.31E-14", "2.99E-03", "0.46", "1.03E-03"], ["1554097_a_at", "MIR31HG", "chr9p21.3", "2.50", "1.92E-09", "1.48E-08", "5.59E-03", "8.48E-03"], ["1562921_at", "EP300-AS1", "chr22q13.2", "–2.44", "3.79E-14", "4.87E-03", "0.04", "3.30E-03"], ["228658_at", "MIAT", "chr22q12.1", "2.37", "9.59E-09", "2.31E-04", "0.59", "0.19"], ["236573_at", "MIR1-2/MIR133A1/MIR133A1HG", "chr18q11.2", "–2.34", "2.46E-08", "5.62E-07", "0.17", "0.12"], ["227969_at", "PCBP1-AS1", "chr2p14", "–2.31", "1.24E-35", "6.61E-08", "5.41E-06", "2.18E-04"], ["208908_s_at*", "CAST", "chr5q15", "–2.26", "2.93E-30", "7.59E-06", "0.02", "1.33E-03"], ["229930_at", "LINC01315", "chr22q13.2", "–2.25", "1.77E-22", "6.81E-09", "2.35E-05", "7.86E-06"], ["239999_at", "LINC00478", "chr21q21.1", "–2.25", "2.34E-11", "1.93E-09", "2.35E-05", "1.96E-06"], ["220918_at", "RUNX1-IT1", "chr21q22.12", "2.23", "4.70E-11", "3.42E-07", "0.10", "0.03"], ["202672_s_at*", "ATF3", "chr1q32.3", "2.23", "9.56E-06", "8.20E-05", "0.31", "0.03"], ["1559361_at", "LOC101927668/MACC1", "chr7p21.1", "–2.21", "1.75E-13", "7.55E-04", "0.23", "0.01"], ["230451_at", "COX10-AS1/LOC100506974", "chr17p12", "–2.20", "2.23E-37", "6.63E-09", "1.11E-06", "5.16E-08"], ["219871_at", "KLF3-AS1", "chr4p14", "–2.20", "7.82E-19", "5.00E-08", "0.06", "0.04"], ["238320_at", "MIR612/NEAT1", "chr11q13.1", "2.15", "2.35E-06", "0.02", "0.29", "0.02"], ["207467_x_at*", "CAST", "chr5q15", "–2.14", "1.22E-30", "3.68E-06", "0.01", "1.33E-03"], ["1557146_a_at", "SSTR5-AS1", "chr16p13.3", "–2.12", "7.86E-07", "0.02", "0.40", "0.19"], ["210409_at*", "MLLT4-AS1", "chr6q27", "–2.12", "1.63E-30", "6.45E-07", "1.92E-04", "2.38E-10"], ["226382_at*", "LOC283070", "chr10p13", "–2.09", "9.82E-14", "8.52E-06", "9.58E-03", "0.03"], ["228370_at", "IPW/LOC101930404/PWARSN/SNORD107/SNORD115-13/SNORD115-26/SNORD115-7/SNORD116-22/SNORD116-28/SNORD116-4", "chr15q11.2", "–2.09", "9.34E-08", "1.55E-06", "0.02", "0.04"], ["232034_at", "LINC00537", "chr9q21.11", "–2.05", "1.33E-11", "0.02", "0.10", "0.10"], ["233565_s_at*", "FKBP1A-SDCBP2/SDCBP2", "chr20p13", "–2.05", "1.23E-09", "4.78E-04", "0.17", "0.06"], ["229635_at", "LINC01094", "chr4q21.21", "2.04", "4.78E-12", "9.33E-05", "0.05", "0.01"], ["228564_at", "LINC01116", "chr2q31.1", "2.03", "3.40E-10", "4.94E-08", "0.10", "0.03"], ["227061_at", "LINC01279", "chr3q13.2", "–2.02", "1.63E-03", "5.34E-06", "2.29E-03", "0.19"]], "row_count": 40, "column_count": 8, "numeric_cells": 299, "header_rows": 1, "locator": "section[3]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:28415559:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d0f356ca5f8ca36f1bca568071f9611689d4417ef1812125fe37dec643bfd2e6", "bytes": 930, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T3", "version": null, "note": "Functional clustering of the putative predicted targets of LOC441178", "structure": {"pmcid": "PMC5458226", "section_index": 5, "section_title": "Prediction of putative targets of lncRNA LOC441178 and functional clustering", "row_count": 10, "column_count": 5}, "table": {"label": "Table 3", "caption": "Functional clustering of the putative predicted targets of LOC441178", "rows": [["Annotation Cluster 1Enrichment Score: 4.07393095028667"], ["Category", "Term", "Count", "%", "P Value"], ["GOTERM_MF_DIRECT", "GO:0016887~ATPase activity", "11", "11.22449", "1.91E-08"], ["GOTERM_MF_DIRECT", "GO:0003777~microtubule motor activity", "7", "7.142857", "2.46E-06"], ["GOTERM_CC_DIRECT", "GO:0030286~dynein complex", "5", "5.102041", "3.80E-06"], ["GOTERM_BP_DIRECT", "GO:0007018~microtubule-based movement", "6", "6.122449", "5.59E-05"], ["GOTERM_CC_DIRECT", "GO:0005874~microtubule", "8", "8.163265", "8.78E-04"], ["GOTERM_MF_DIRECT", "GO:0005524~ATP binding", "17", "17.34694", "0.002009"], ["KEGG_PATHWAY", "hsa05016:Huntington's disease", "6", "6.122449", "0.003745"], ["GOTERM_CC_DIRECT", "GO:0005929~cilium", "4", "4.081633", "0.038842"]], "row_count": 10, "column_count": 5, "numeric_cells": 33, "header_rows": 2, "locator": "section[5]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE30784 not downloaded", "asset:data:geo:GSE30784 licence not read", "asset:data:geo:GSE42743 not downloaded", "asset:data:geo:GSE42743 licence not read", "asset:data:geo:GSE6791 not downloaded", "asset:data:geo:GSE6791 licence not read", "asset:data:geo:GSE9844 not downloaded", "asset:data:geo:GSE9844 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The statistical analysis of differentially expressed lncRNA (between cases and controls) was performed using linear regression, adjusting for age and sex."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "ols_fit", "expected_value": 2.0, "unit": "fold change", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["ols_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ols."}, "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": ["GSE30784", "GSE42743", "GSE9844", "GSE6791"], "resolved_accessions": ["GSE30784", "GSE42743", "GSE9844", "GSE6791"], "statements": ["The microarray data were generated using the Affymetrix Human Genome U133 Plus 2.0 array (Affymetrix, Santa Clara, CA, USA) and were deposited in the Gene Expression Omnibus (GEO) Repository under the general accession number GSE30784. The dataset has 212 samples in total, 167 of them are OSCCs and 45 of them are oral mucosa from healthy controls."], "basis": "The paper names GSE30784, GSE42743, GSE9844, GSE6791 in Gene Expression Omnibus (GEO) Repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["ols_fit"], "assets": ["source:pmid:28415559", "data:geo:GSE30784", "asset:table:pmid:28415559:1", "asset:table:pmid:28415559:2", "asset:table:pmid:28415559:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE30784"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:51Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 86134, "completion_tokens": 4605, "cached_tokens": 2104}}, "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:28415559", "type": "paper", "label": "pmid:28415559"}, {"id": "source:pmid:28415559", "type": "manuscript", "label": "PMID 28415559 full text"}, {"id": "data:geo:GSE30784", "type": "dataset", "label": "GEO GSE30784"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28415559", "type": "paper", "label": "pmid:28415559"}, {"id": "source:pmid:28415559", "type": "manuscript", "label": "PMID 28415559 full text"}, {"id": "data:geo:GSE30784", "type": "dataset", "label": "GEO GSE30784"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28415559", "type": "extraction", "used": ["source:pmid:28415559"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE30784", "type": "accession_resolution", "used": ["data:geo:GSE30784"], "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:28415559", "parent_hash": "sha256:79a12f130a0172c46f1e041b477bc9d6a948cb54379bfcaffdc74438f9a13112", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE30784 licence not read", "asset:data:geo:GSE30784 not downloaded", "asset:data:geo:GSE42743 licence not read", "asset:data:geo:GSE42743 not downloaded", "asset:data:geo:GSE6791 licence not read", "asset:data:geo:GSE6791 not downloaded", "asset:data:geo:GSE9844 licence not read", "asset:data:geo:GSE9844 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["67 OSCCs and 45 healthy oral mucosa using an Affymetrix HG U133 plus 2.0 array dataset. We found 658"], "order_basis": "paper_text_order:403", "id": "assay:1"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["ols_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The statistical analysis of differentially expressed lncRNA (between cases and controls) was performed using linear regression, adjusting for age and sex."], "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":"2026-11-04T01:46:57+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}}}