{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40791155", "kind": "science-record", "revision": 4, "content_hash": "sha256:5e62ae37130d0d428b5023abcca91b69f773815d576527a184162f3dea15dc1e", "created_at": "2026-11-01T20:30:53Z", "updated_at": "2026-11-01T22:56:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and validation of TUBB, CLTA, and FBXL5 as potential diagnostic markers of postmenopausal osteoporosis.", "doi": "10.17305/bb.2025.12019", "pmid": "40791155", "authors": ["Yue Tan", "Yujing Wang", "Qin Zhu", "Yan Xue", "Xuhao Ji", "Zhenkun Li", "Jiawen Shen", "Chengming Sun", "Shiqi Ren", "Chenlin Zhang", "Jianfeng Chen"], "journal": "Biomolecules & biomedicine", "year": 2025, "abstract": "Postmenopausal osteoporosis (PMOP) is recognized as the most prevalent bone disease worldwide. N6-methyladenosine (m6A) is one of the most common RNA modifications influencing the progression of various disorders; however, its specific role in PMOP remains unexplored. This study aims to investigate the expression profiles of m6A-related genes and their impact on the prognosis of PMOP patients. We utilized the GSE56815 expression analysis dataset obtained from the Gene Expression Omnibus (GEO) database and extracted m6A-related genes for further examination. Our analysis revealed that m6A-related genes exhibited differential expression between PMOP patients and healthy controls. We employed consensus clustering to identify subgroups within the PMOP cohort and conducted immunological analyses on these clusters. Additionally, we intersected the clusters to identify differentially expressed genes (DEGs) and analyzed potential diagnostic markers for PMOP using support vector machine recursive feature elimination (SVM-RFE), LASSO, and random forest (RF) algorithms, which were subsequently validated in the GSE56116 dataset. The receiver operating characteristic (ROC) curve was employed to assess the diagnostic significance of these markers. Furthermore, quantitative PCR (qPCR) was performed to validate the expression of the identified genes. In the GSE56815 dataset, we identified three subtypes associated with m6A modifications, leading to the identification of 302 shared DEGs among these subtypes. Gene ontology (GO) analysis indicated that the DEGs were predominantly enriched in nuclear specks, the nuclear envelope, and nucleocytoplasmic transport processes. Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis further revealed that DEGs were primarily associated with endocytosis and nucleocytoplasmic transport pathways. Through the application of SVM, LASSO, and RF algorithms, we identified three potential diagnostic markers: TUBB, CLTA, and FBXL5, which demonstrated promising diagnostic capabilities when tested against an independent dataset. qPCR validation confirmed significant expression differences of these genes between the control and PMOP groups. The genetic markers identified in this study hold potential for accurately predicting the risk of PMOP in patients. The findings contribute to understanding the underlying molecular mechanisms of CLTA, TUBB, and FBXL5 in PMOP and may facilitate the development of novel therapeutic strategies and improved monitoring of the disease.", "claims": [{"id": "claim-method", "statement": "Three types of intersection genes, A-B, B-C, and C-A, were selected for algorithm screening, including minimum absolute contraction and selection operator (LASSO) logistic regression, SVM-RFE, and RandomForest (RF) [14, 17, 18].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40791155", "locator": "sections[8] \"Acquisition of diagnostic markers\" paragraph 2", "quote": "Three types of intersection genes, A-B, B-C, and C-A, were selected for algorithm screening, including minimum absolute contraction and selection operator (LASSO) logistic regression, SVM-RFE, and RandomForest (RF) [14, 17, 18]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40791155", "locator": "sections[3] \"Data retrieval\" paragraph 2", "quote": "GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified TUBB, CLTA, and FBXL5 as potential diagnostic markers for PMOP.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40791155", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Through the application of SVM, LASSO, and RF algorithms, we identified three potential diagnostic markers: TUBB, CLTA, and FBXL5, which demonstrated promising diagnostic capabilities when tested against an independent dataset."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified TUBB, CLTA, and FBXL5 as potential diagnostic markers for PMOP.", "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:40791155"], "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:GSE56116"], "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:GSE56116"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40791155", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.17305/bb.2025.12019", "sha256": "sha256:d9bbb9016177be4fcde681aa0aed32122871738eb75552a50aa0c5aade8c018d", "bytes": 50632, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.17305/bb.2025.12019", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12505522", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE56116", "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=GSE56116", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE56116", "version": null, "note": "GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1356155", "GSM1356156", "GSM1356157", "GSM1356158", "GSM1356159", "GSM1356160", "GSM1356161", "GSM1356162", "GSM1356163", "GSM1356164", "GSM1356165", "GSM1356166", "GSM1356167"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Genes expression profiles of postmenopausal osteoporosis with kidney Yin deficiency", "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:GSE56815", "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=GSE56815", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE56815", "version": null, "note": "GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1369756", "GSM1369757", "GSM1369758", "GSM1369759", "GSM1369760", "GSM1369761", "GSM1369762", "GSM1369763", "GSM1369764", "GSM1369765", "GSM1369766", "GSM1369767", "GSM1369768", "GSM1369769", "GSM1369770", "GSM1369771", "GSM1369772", "GSM1369773", "GSM1369774", "GSM1369775", "GSM1369776", "GSM1369777", "GSM1369778", "GSM1369779", "GSM1369780", "GSM1369781", "GSM1369782", "GSM1369783", "GSM1369784", "GSM1369785", "GSM1369786", "GSM1369787", "GSM1369788", "GSM1369789", "GSM1369790", "GSM1369791", "GSM1369792", "GSM1369793", "GSM1369794", "GSM1369795", "GSM1369796", "GSM1369797", "GSM1369798", "GSM1369799", "GSM1369800", "GSM1369801", "GSM1369802", "GSM1369803", "GSM1369804", "GSM1369805", "GSM1369806", "GSM1369807", "GSM1369808", "GSM1369809", "GSM1369810", "GSM1369811", "GSM1369812", "GSM1369813", "GSM1369814", "GSM1369815", "GSM1369816", "GSM1369817", "GSM1369818", "GSM1369819", "GSM1369820", "GSM1369821", "GSM1369822", "GSM1369823", "GSM1369824", "GSM1369825", "GSM1369826", "GSM1369827", "GSM1369828", "GSM1369829", "GSM1369830", "GSM1369831", "GSM1369832", "GSM1369833", "GSM1369834", "GSM1369835"], "sample_count": 80, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression study of blood monocytes in pre- and postmenopausal females with low or high bone mineral density (HG-U133A)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE56116 not downloaded", "asset:data:geo:GSE56116 licence not read", "asset:data:geo:GSE56815 not downloaded", "asset:data:geo:GSE56815 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Three types of intersection genes, A-B, B-C, and C-A, were selected for algorithm screening, including minimum absolute contraction and selection operator (LASSO) logistic regression, SVM-RFE, and RandomForest (RF) [14, 17, 18]."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-4", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE56815", "GSE56116"], "resolved_accessions": ["GSE56815", "GSE56116"], "statements": ["GSE56815 contains 80 samples, including 40 postmenopausal osteoporosis samples and 40 premenopausal samples."], "basis": "The paper names GSE56815, GSE56116 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": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:40791155", "data:geo:GSE56116"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE56116"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:59:02Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 14774, "completion_tokens": 1610, "cached_tokens": 256}}, "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:40791155", "type": "paper", "label": "pmid:40791155"}, {"id": "source:pmid:40791155", "type": "manuscript", "label": "PMID 40791155 full text"}, {"id": "data:geo:GSE56116", "type": "dataset", "label": "GEO GSE56116"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40791155", "type": "paper", "label": "pmid:40791155"}, {"id": "source:pmid:40791155", "type": "manuscript", "label": "PMID 40791155 full text"}, {"id": "data:geo:GSE56116", "type": "dataset", "label": "GEO GSE56116"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40791155", "type": "extraction", "used": ["source:pmid:40791155"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE56116", "type": "accession_resolution", "used": ["data:geo:GSE56116"], "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:40791155", "parent_hash": "sha256:305e5bb90cbee1b99c0f1bc0aaa90704ef1b324f565a86eacc3e63bb5b1c848e", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE56116 licence not read", "asset:data:geo:GSE56116 not downloaded", "asset:data:geo:GSE56815 licence not read", "asset:data:geo:GSE56815 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": ["hese markers. Furthermore, quantitative PCR (qPCR) was performed to validate the expression of", "when tested against an independent dataset. qPCR validation confirmed significant expression"], "order_basis": "paper_text_order:1359", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Three types of intersection genes, A-B, B-C, and C-A, were selected for algorithm screening, including minimum absolute contraction and selection operator (LASSO) logistic regression, SVM-RFE, and RandomForest (RF) [14, 17, 18]."], "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":"2026-11-04T02:51:01+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}}}