{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30555656", "kind": "science-record", "revision": 4, "content_hash": "sha256:263f0fa3123a59ff68bb7916cfaf4bcb8818f4739f0091ac9953ec8774729f84", "created_at": "2026-11-01T15:40:39Z", "updated_at": "2026-11-01T21:21:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Exploring Potential Biomarkers Underlying Pathogenesis of Alzheimer's Disease by Differential Co-expression Analysis.", "doi": null, "pmid": "30555656", "authors": ["Fereshteh Izadi", "Mohammad Hasan Soheilifar"], "journal": "Avicenna journal of medical biotechnology", "year": 2018, "abstract": "BACKGROUND: Alzheimer's Disease (AD) is the most common form of dementia in the elderly. Due to the facts that biological causes of AD are complex in addition to increasing rates of AD worldwide, a deeper understanding of AD etiology is required for AD treatment and diagnosis.\nMETHODS: To identify molecular pathological alterations in AD brains, GSE36980 series containing microarray data samples from temporal cortex, frontal cortex and hippocampus were downloaded from Gene Expression Omnibus (GEO) database and valid gene symbols were subjected to building a gene co-expression network by a bioinformatics tool known as differential regulation from differential co-expression (DCGL) software package. Then, a network-driven integrative analysis was performed to find significant genes and underlying biological terms.\nRESULTS: A total of 17088 unique genes were parsed into three independent differential co-expression networks. As a result, a small number of differentially co-regulated genes mostly in frontal and hippocampus lobs were detected as potential biomarkers related to AD brains. Ultimately differentially co-regulated genes were enriched in biological terms including response to lipid and fatty acid and pathways mainly signaling pathway such as G-protein signaling pathway and glutamate receptor groups II and III. By conducting co-expression analysis, our study identified multiple genes that may play an important role in the pathogenesis of AD.\nCONCLUSION: The study aimed to provide a systematic understanding of the potential relationships among these genes and it is hoped that it could aid in AD biomarker discovery.", "claims": [{"id": "claim-method", "statement": "To find the significantly over-represented biological GO terms and functions of gene products within a co-expression network of DRGs and DRLs, functional classification was performed using BINGO Cytoscape plugin 16 running hypergeometric test and Benjamini & Hochberg FDR correction at significant level 0.01.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30555656", "locator": "sections[5] \"Gene ontology, pathway analysis and visualization\" paragraph 2", "quote": "To find the significantly over-represented biological GO terms and functions of gene products within a co-expression network of DRGs and DRLs, functional classification was performed using BINGO Cytoscape plugin 16 running hypergeometric test and Benjamini & Hochberg FDR correction at significant level 0.01."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The CEL files for GSE36980 series were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo/) database and normalized with RMA method by using the Linear Models for Microarray Data (limma) R package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30555656", "locator": "sections[3] \"Data acquisition and pre-processing\" paragraph 2", "quote": "The CEL files for GSE36980 series were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo/) database and normalized with RMA method by using the Linear Models for Microarray Data (limma) R package."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:30555656"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30555656", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:b952a830bf698e1a6d2fbf0b01ba77cb504626f4d0dd459dfaa0b38e6460fa13", "bytes": 33826, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "30555656", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6252023", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:30555656:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:36d80493d2cbb3bb809ef4983f9016fa61756968b7518c0d43aa3f1e53df27bb", "bytes": 300, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Sample characteristics", "structure": {"pmcid": "PMC6252023", "section_index": 3, "section_title": "Data acquisition and pre-processing", "row_count": 4, "column_count": 3}, "table": {"label": "Table 1.", "caption": "Sample characteristics", "rows": [["Biological samples", "Control", "AD patients"], ["Temporal cortex", "19", "10"], ["Frontal cortex", "18", "15"], ["Hippocampus", "10", "7"]], "row_count": 4, "column_count": 3, "numeric_cells": 6, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30555656:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0608f54dfb63a7f0a6d69594ddf3fd85f7317ebdf431eb8843f528954dfd8ae0", "bytes": 3565, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T2", "version": null, "note": "List of differential regulated genes (DRGs) and corresponding p-value<0.05 of differential co-expression enrichment (DCe) in temporal cortex, frontal cortex and hippocampus datasets", "structure": {"pmcid": "PMC6252023", "section_index": 7, "section_title": "Co-expression analysis", "row_count": 42, "column_count": 4}, "table": {"label": "Table 2.", "caption": "List of differential regulated genes (DRGs) and corresponding p-value<0.05 of differential co-expression enrichment (DCe) in temporal cortex, frontal cortex and hippocampus datasets", "rows": [["", "Gene name", "DCe p-value", "Description"], ["Temporal cortex", "ARID1A", "0.00069", "ARID1A was among down-regulated genes in AD model mice (17)"], ["Cdc42", "0.01224", "Cdc42 activity was increased in hippocampus neurons treated with fibrillary β-amyloid (18)"], ["LPPR4", "0.01395", "LPPR4 was up-regulated in incipient AD patients (19)"], ["PITHD1", "0.01863", "//"], ["SGIP1", "0.02064", "//"], ["SZT2", "0.01936", "//"], ["ZMPSTE24", "0.01936", "//"], [""], ["Frontal cortex", "CHD5", "5.19E-14", "The depletion of CHD5 was shown to be linked with AD associated gene sets (20)"], ["EFHD2", "3.00E-07", "EFhd2 has been found to be associated with aggregated tau in the brain in AD and in a mouse model of frontotemporal dementia (21,22)"], ["Prxs", "7.82E-07", "Peroxiredoxins (Prxs) may be associated with AD by reducing ROS elicited by amyloid β (Aβ) accumulation that could be a causative factor in the pathogenesis of AD (23)"], ["MAGIE3", "1.68E-06", "//"], ["EXTL1", "4.14E-06", "//"], ["HPCAL4", "2.09E-05", "HPCAL4 could be used as a prognostic marker for cognitive decline in AD (24)"], ["LPHN2", "2.59E-05", "LPHN2 is likely to be participated in AD as an altered protein in Lipid Raft (25)"], ["NIPAL3", "8.35E-05", "NIPAL3 was shown as a biomarker in Late-Onset Major Depressive Disorder (26)"], ["CACNA1E", "0.00017", "CACNA1E was down-regulated in cerebral Cockayne syndrome (27)"], ["IFI16", "0.00033", "IFI16 was participated in delaying onset of AD (28)"], ["HHLA3", "0.00122", "//"], ["KCNK1", "0.00202", "KCNK1 exhibited alternative splicing in patients with mesial temporal lobe epilepsy (29)"], ["rnpc3", "0.00384", "//"], ["DCAF6", "0.00542", "//"], ["IPO13", "0.00581", "IPO13 mutants involved in chronic inflammatory diseases (30)"], ["RPL11", "0.00585", "RPL11 revealed significant altered expression profiles in the neuron model of AD treated with rhTFAM (31)"], ["S100A1", "0.00716", "S100A1 modulates inflammation in AD (32)"], ["CNTN2", "0.02606", "CNTN2 associated with AD via BACE1 activity (33)"], ["GRIK3", "0.03774", "GRIK3 was highly expressed in major depression (34)"], [""], ["Hippocampus", "KCNK1", "1.55E-09", "//"], ["CHRNB2", "2.37E-09", "CHRNB2 was found to interfere with the immune system in neurologic disorders (35)"], ["HAPLN2", "3.43E-05", "Hapln2 has been recently shown to be accumulated in the neurofibrillary tangle of Alzheimer’s brain (36)"], ["Slc2a1", "0.00207", "Slc2a1 down-regulation exacerbated AD (37)"], ["FABP3", "0.00298", "serum levels of brain-type FABP are elevated in a significant proportion of patients with various neurodegenerative diseases including AD (38)"], ["DEGS1", "0.00327", "DEGS1 is likely to be involved in AD as an altered protein in Lipid Raft (25)"], ["NKAIN1", "0.00435", "//"], ["S100A1", "0.00434", "S100A1 modulates inflammation in AD (32)"], ["CNTN2", "0.00511", "CNTN2 associated with AD via b-Secretase (BACE1) activity (33)"], ["SFPQ", "0.00816", "SFPQ was shown as a transcription factor with an altered nucleo-cytoplasmic distribution under neurodegenerative conditions (39)"], ["GPSM2", "0.01073", "//"], ["GSTM1", "0.01591", "GSTM1 null genotype was found as risk factor for late-onset Alzheimer’s disease in Italian patients (40)"], ["CACHD1", "0.02830", "CACHD1 is a substrate of BACE1 responsible for generating the amyloid-b protein (41)"]], "row_count": 42, "column_count": 4, "numeric_cells": 73, "header_rows": 1, "locator": "section[7]/table-wrap[1]#T2"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Hypergeometric test with Benjamini-Hochberg false discovery rate correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To find the significantly over-represented biological GO terms and functions of gene products within a co-expression network of DRGs and DRLs, functional classification was performed using BINGO Cytoscape plugin 16 running hypergeometric test and Benjamini & Hochberg FDR correction at significant level 0.01."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Hypergeometric test with Benjamini-Hochberg false discovery rate correction), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": ["GSE36980 series"], "resolved_accessions": [], "statements": ["The CEL files for GSE36980 series were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo/) database and normalized with RMA method by using the Linear Models for Microarray Data (limma) R package."], "basis": "The paper names GSE36980 series, but the accession does not resolve in the repository (no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30555656", "asset:table:pmid:30555656:1", "asset:table:pmid:30555656:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 25573, "completion_tokens": 869, "cached_tokens": 784}}, "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:30555656", "type": "paper", "label": "pmid:30555656"}, {"id": "source:pmid:30555656", "type": "manuscript", "label": "PMID 30555656 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30555656", "type": "paper", "label": "pmid:30555656"}, {"id": "source:pmid:30555656", "type": "manuscript", "label": "PMID 30555656 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30555656", "type": "extraction", "used": ["source:pmid:30555656"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:30555656", "parent_hash": "sha256:657c68b9f21309798fcd9a5b19f4bb9fd055cb6a258a8085651c91a2fbfd188b", "fork_of": null, "generation": 3}, "gaps": ["doi", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]},"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":"2026-11-04T00:32:25+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}}}