{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40910032", "kind": "science-record", "revision": 3, "content_hash": "sha256:47c86fc5fb158b54bbcac15f60df8d95f600f1850f7ee57706524e526660f795", "created_at": "2026-11-01T20:31:01Z", "updated_at": "2026-11-01T22:14:41Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The ceRNA Regulatory Network in Vitiligo: Evidence from Bioinformatics Analysis.", "doi": "10.2147/CCID.S528604", "pmid": "40910032", "authors": ["Hedan Yang", "Xiuzhen Li", "Xiaoli Zhang", "Yiping Ge", "Yin Yang", "Tong Lin"], "journal": "Clinical, cosmetic and investigational dermatology", "year": 2025, "abstract": "Background: Vitiligo is an acquired depigmentary disorder caused by the loss of functional melanocytes. Increasing evidence suggests that competing endogenous RNA (ceRNA) interactions participate in this process, yet their global architecture in vitiligo remains unclear.\nObjective: To delineate a long non-coding RNA (lncRNA)-microRNA (miRNA)-mRNA ceRNA network associated with vitiligo and to identify blood-borne RNA markers with diagnostic potential.\nMethods: miRNA, mRNA, and lncRNA expression data from vitiligo patients and healthy controls were obtained from the GEO database (GSE141655 and GSE186928). Differentially expressed (DE) mRNAs, miRNAs and lncRNAs were screened (|log2 FC| > 0.5, adj. p< 0.05). Functional enrichment, STRING-based protein-protein interaction (PPI) mapping, and lncRNA-mRNA co-expression analysis (Pearson r > 0.9) was performed. miRNA-mRNA pairs were predicted with miRWalk 3.0, and miRNA-lncRNA pairs with miRanda v3.3a (score ≥ 140, energy ≤-20 kcal mol-¹). Triplets that shared the same miRNA, displayed positive lncRNA--mRNA correlation, and showed inverse expression relative to the miRNA were combined into a ceRNA network; hub nodes were ranked by degree centrality. Candidate lncRNAs were validated by RT-qPCR in peripheral blood from 20 vitiligo patients and 20 matched controls.\nResults: A total of 454 DE-mRNAs (341 down-, 113 up-regulated), 22 DE-miRNAs (6 down-, 16 up-regulated), and 281 DE-lncRNAs (112 down-, 169 up-regulated) were identified. Enrichment analysis highlighted pathways linked to melanogenesis, oxidative stress, PI3K-Akt, JAK-STAT and IL-17 signalling. The ceRNA network comprised 33 lncRNAs, 12 miRNAs and 58 mRNAs; SLC32A1, GRIA2, PRKACG and WNT1 were top hub proteins in the PPI sub-network. Blood validation confirmed up-regulation of CASC19, NUCB1-AS1 and LINC01485 and down-regulation of VAV3-AS1, SPATA13-AS1, ZNF350-AS1 and LINC00677 (all p< 0.05).\nConclusion: Our findings map a vitiligo-related ceRNA landscape and pinpoints seven circulating lncRNAs with diagnostic promise. The results provide a foundation for probing non-coding RNA-mediated mechanisms and developing targeted therapies for vitiligo.", "claims": [{"id": "claim-method", "statement": "To identify differences between groups, the Student’s t-test was utilized, with a significance threshold set at p < 0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40910032", "locator": "sections[13] \"Statistical Analysis\" paragraph 2", "quote": "To identify differences between groups, the Student’s t-test was utilized, with a significance threshold set at p < 0.05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40910032", "locator": "sections[3] \"miRNA and mRNA/lncRNA Data Sets\" paragraph 2", "quote": "The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 454 DE-mRNAs (341 down-, 113 up-regulated), 22 DE-miRNAs (6 down-, 16 up-regulated), and 281 DE-lncRNAs (112 down-, 169 up-regulated) were identified.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40910032", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "A total of 454 DE-mRNAs (341 down-, 113 up-regulated), 22 DE-miRNAs (6 down-, 16 up-regulated), and 281 DE-lncRNAs (112 down-, 169 up-regulated) were identified."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A total of 454 DE-mRNAs (341 down-, 113 up-regulated), 22 DE-miRNAs (6 down-, 16 up-regulated), and 281 DE-lncRNAs (112 down-, 169 up-regulated) were identified.", "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:40910032"], "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:GSE141655"], "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:GSE141655"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40910032", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/CCID.S528604", "sha256": "sha256:16ad540cb5fe5b4862a9d067b9b8155e95ac37d79fce77c45645d909afc0db78", "bytes": 24489, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/CCID.S528604", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12407014", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE141655", "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=GSE141655", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE141655", "version": null, "note": "The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM4210613", "GSM4210614", "GSM4210615", "GSM4210616", "GSM4210617", "GSM4210618", "GSM4210619", "GSM4210620", "GSM4210621", "GSM4210622", "GSM4210623", "GSM4210624", "GSM4210625", "GSM4210626", "GSM4210627", "GSM4210628", "GSM4210629", "GSM4210630", "GSM4210631", "GSM4210632"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "The miRNAs in plasma exosomes may serve as markers for non-segmental vitiligo", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE186928", "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=GSE186928", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE186928", "version": null, "note": "The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM5663816", "GSM5663817", "GSM5663818", "GSM5663819", "GSM5663820", "GSM5663821", "GSM5663822", "GSM5663823", "GSM5663824", "GSM5663825"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Expression pattens of long non-coding RNAs in peripheral blood mononuclear cells of non-segmental vitiligo", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE141655 not downloaded", "asset:data:geo:GSE141655 licence not read", "asset:data:geo:GSE186928 not downloaded", "asset:data:geo:GSE186928 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-2", "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-3", "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": 0.8, "band": "high", "quote": "Pathway Enrichment"}}, {"id": "method-4", "family": "network_analysis", "specific": "centrality", "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": "centrality"}}, {"id": "method-5", "family": null, "specific": null, "label": "Student’s t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify differences between groups, the Student’s t-test was utilized, with a significance threshold set at p < 0.05."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE141655", "GSE186928"], "resolved_accessions": ["GSE141655", "GSE186928"], "statements": ["The miRNA expression profiling data were sourced from the NCBI GEO database, specifically dataset GSE141655, which includes blood samples from 10 vitiligo patients and 10 healthy individuals."], "basis": "The paper names GSE141655, GSE186928 in NCBI GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:40910032", "data:geo:GSE141655"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE141655"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:01:06Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 8043, "completion_tokens": 1035, "cached_tokens": 264}}, "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:40910032", "type": "paper", "label": "pmid:40910032"}, {"id": "source:pmid:40910032", "type": "manuscript", "label": "PMID 40910032 full text"}, {"id": "data:geo:GSE141655", "type": "dataset", "label": "GEO GSE141655"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40910032", "type": "paper", "label": "pmid:40910032"}, {"id": "source:pmid:40910032", "type": "manuscript", "label": "PMID 40910032 full text"}, {"id": "data:geo:GSE141655", "type": "dataset", "label": "GEO GSE141655"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40910032", "type": "extraction", "used": ["source:pmid:40910032"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE141655", "type": "accession_resolution", "used": ["data:geo:GSE141655"], "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:40910032", "parent_hash": "sha256:25d673bab5a5bb62e84527c5d10c48e121f8a26af0b91c03f298934517393e60", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE141655 licence not read", "asset:data:geo:GSE141655 not downloaded", "asset:data:geo:GSE186928 licence not read", "asset:data:geo:GSE186928 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["trality. Candidate lncRNAs were validated by RT-qPCR in peripheral blood from 20 vitiligo patient", "lity. Candidate lncRNAs were validated by RT-qPCR in peripheral blood from 20 vitiligo patient", "raphPad Software, Inc., San Diego, CA, USA). RT-qPCR tests were conducted in triplicate or more.", "hPad Software, Inc., San Diego, CA, USA). RT-qPCR tests were conducted in triplicate or more."], "order_basis": "paper_text_order:1282", "id": "assay:1"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["onships). Validation of lncRNA Expression in Blood Samples from Vitiligo Patients To assess the reliability", "n levels of the aforementioned 16 lncRNAs in blood samples from 20 vitiligo patients and from 20 healthy con", "els (Figure 5). Figure 5lncRNA expression in blood samples from a total of 20 vitiligo patients and 20 healt"], "order_basis": "paper_text_order:6858", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Pearson correlation"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:19:55+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}}}