{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33344076", "kind": "science-record", "revision": 7, "content_hash": "sha256:495a9831a200d54ff017827610fdd140f9fea525a84cbe0722f3cfae5e020ee0", "created_at": "2026-11-01T15:41:20Z", "updated_at": "2026-11-01T22:02:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comprehensive analysis of circRNA expression profiles and circRNA-associated competing endogenous RNA networks in IgA nephropathy.", "doi": "10.7717/peerj.10395", "pmid": "33344076", "authors": ["Haiyang Liu", "Di Liu", "Yexin Liu", "Ming Xia", "Yan Li", "Mei Li", "Hong Liu"], "journal": "PeerJ", "year": 2020, "abstract": "BACKGROUND: Immunoglobulin A nephropathy (IgAN) is immune-mediated primary glomerulonephritis, which is the most common reason leading to renal failure worldwide. The exact pathogenesis of IgAN is not well defined. Accumulating evidence indicates that circular RNAs (circRNAs) play crucial roles in the immune disease by involving in the competing endogenous RNA (ceRNA) network mechanism. At present, the studies of the circRNA profiles and circRNA-associated ceRNA networks in the IgAN are still scarce. This study aimed to elucidate the potential roles of circRNA-associated ceRNA networks of peripheral blood mononuclear cells (PBMCs) in IgAN patients.\nMETHOD: CircRNA sequencing was used to identify the differential expressed circRNAs (DEcircRNAs) of PBMCs in IgAN and healthy controls; limma packages from data sets GSE25590 and GSE73953 in the Gene Expression Omnibus (GEO) database, were used to identify differentially expressed micro RNAs (miRNAs) and message RNAs (mRNAs). A circRNA-miRNA-mRNA ceRNA network was constructed to further investigate the mechanisms of IgAN. Then, GO analysis and KEGG enrichment analyses were used to annotate the genes involved in the circRNA-associated ceRNA network. Further, Protein-protein interaction (PPI) networks were established to screen potential hub genes, by using Search Tool for the Retrieval of Interacting Genes/Proteins (STRING). Last, a quantitative real-time polymerase chain reaction (qRT-PCR) was applied to verify the hub genes in the ceRNA network.\nRESULT: A total of 145 circRNAs, 22 miRNAs, and 1,117 mRNAs were differentially expressed in IgAN compared with controls (P < 0.05). A ceRNA network was constructed which contained 16 DEcircRNAs, 72 differential expressed mRNAs (DEmRNAs) and 11 differential expressed miRNAs (DEmiRNAs). KEGG pathway enrichment analysis illustrated the underlying biological functions of the ceRNA-associated genes, such as Nitrogen compound metabolic process, COPII-coated ER to Golgi transport vesicle, CAMP response element protein binding process (P < 0.01); meanwhile, Hepatitis B, GnRH signaling, and Prion disease were the most significant enrichment GO terms (P < 0.01). PPI network based on STRING analysis identified 4 potentially hub genes. Finally, Ankyrin repeat and SOCS box containing 16 (ASB16), SEC24 homolog C, COPII coat complex component (SEC24C) were confirmed by qRT-PCR (P < 0.05) and were identified as the hub genes of the ceRNA network in our study.\nCONCLUSION: Our study identified a novel circRNA-mediated ceRNA regulatory network mechanisms in the pathogenesis of IgAN.", "claims": [{"id": "claim-data-access", "statement": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33344076", "locator": "sections[19] \"Additional Information and Declarations\" paragraph 5", "quote": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33344076"], "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:GSE154046"], "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:GSE154046"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33344076", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.10395", "sha256": "sha256:02434d282f1d6c0026a76a260eaac562135193094a934c9813104605358452d5", "bytes": 41908, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.10395", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7719294", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE154046", "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=GSE154046", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE154046", "version": null, "note": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4663157", "GSM4663158", "GSM4663159", "GSM4663160", "GSM4663161", "GSM4663162"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "20301", "taxon": "Homo sapiens", "title": "Comprehensive analysis of circRNA expression profiles and circRNA associated competing endogenous RNA networks in IgA nephropathy", "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:GSE25590", "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=GSE25590", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25590", "version": null, "note": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM627751", "GSM627779", "GSM627781", "GSM627926", "GSM627964", "GSM627983", "GSM627984", "GSM627998", "GSM627999", "GSM628000", "GSM628001", "GSM628002", "GSM628003", "GSM628004"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "7731", "taxon": "Homo sapiens", "title": "miR-148b modulates the C1GALT1 expression explaining the abnormal glycosylation process in IgA Nephropathy", "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:GSE73953", "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=GSE73953", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73953", "version": null, "note": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1906717", "GSM1906718", "GSM1906719", "GSM1906720", "GSM1906721", "GSM1906722", "GSM1906723", "GSM1906724", "GSM1906725", "GSM1906726", "GSM1906727", "GSM1906728", "GSM1906729", "GSM1906730", "GSM1906731", "GSM1906732", "GSM1906733", "GSM1906734", "GSM1906735", "GSM1906736", "GSM1906737", "GSM1906738", "GSM1906739", "GSM1906740", "GSM1906741"], "sample_count": 25, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Microarray analysis of peripheral blood mononuclear cells (PBMCs) from IgA nephropathy patients, membranous nephropathy patients and healthy controls.", "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:33344076:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:491e09985cff79214b492e9e1dd6f84b7464efd58e535691ac2ec13b6aac0b33", "bytes": 242, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "The ten most dysregulated circRNA transcripts between IgAN patients and healthy controls.", "structure": {"pmcid": "PMC7719294", "section_index": 10, "section_title": "Overview of circRNA-Seq and identification of DEcircRNAs", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "The ten most dysregulated circRNA transcripts between IgAN patients and healthy controls.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[10]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:33344076:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8c09c3ad0060b63b7780da9defe904d6671540795172020d866315d3b305f905", "bytes": 229, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#table-2", "version": null, "note": "Statistical analysis of differentially expressed circRNAs, miRNAs and mRNAs.", "structure": {"pmcid": "PMC7719294", "section_index": 11, "section_title": "Identification of DEmiRNAs and DEmRNAs", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Statistical analysis of differentially expressed circRNAs, miRNAs and mRNAs.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[11]/table-wrap[1]#table-2"}}], "gaps": ["asset:data:geo:GSE154046 not downloaded", "asset:data:geo:GSE154046 licence not read", "asset:data:geo:GSE25590 not downloaded", "asset:data:geo:GSE25590 licence not read", "asset:data:geo:GSE73953 not downloaded", "asset:data:geo:GSE73953 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "edger", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "edgeR"}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "limma"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-protein interaction"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: edger."}, "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": ["GSE154046", "GSE25590", "GSE73953"], "resolved_accessions": ["GSE154046", "GSE25590", "GSE73953"], "statements": ["The raw data are available in the Supplemental File and the circRNA sequences are available at GEO: GSE154046."], "basis": "The paper names GSE154046, GSE25590, GSE73953 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33344076", "data:geo:GSE154046", "asset:table:pmid:33344076:1", "asset:table:pmid:33344076:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE154046"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:19:37Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 31267, "completion_tokens": 1797, "cached_tokens": 512}}, "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:33344076", "type": "paper", "label": "pmid:33344076"}, {"id": "source:pmid:33344076", "type": "manuscript", "label": "PMID 33344076 full text"}, {"id": "data:geo:GSE154046", "type": "dataset", "label": "GEO GSE154046"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33344076", "type": "paper", "label": "pmid:33344076"}, {"id": "source:pmid:33344076", "type": "manuscript", "label": "PMID 33344076 full text"}, {"id": "data:geo:GSE154046", "type": "dataset", "label": "GEO GSE154046"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33344076", "type": "extraction", "used": ["source:pmid:33344076"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE154046", "type": "accession_resolution", "used": ["data:geo:GSE154046"], "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:33344076", "parent_hash": "sha256:b8f9e0d27e8bb5ac8b56146062696864ce67930ea79be58cca989ad5a6503c6b", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE154046 licence not read", "asset:data:geo:GSE154046 not downloaded", "asset:data:geo:GSE25590 licence not read", "asset:data:geo:GSE25590 not downloaded", "asset:data:geo:GSE73953 licence not read", "asset:data:geo:GSE73953 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["edgeR"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:12:18+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}}}