{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41544137", "kind": "science-record", "revision": 3, "content_hash": "sha256:373e81d3d21b21a8c3e46fd01409b1e7e6abe0e37b117e8114e28c037d6c4076", "created_at": "2026-11-01T20:31:30Z", "updated_at": "2026-11-01T22:15:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of cell senescence-related genes in spontaneous preterm birth based on bioinformatics analysis and machine learning.", "doi": "10.1371/journal.pone.0340809", "pmid": "41544137", "authors": ["Guo Juan", "Li Ting", "Wang Yahui", "Zuo Luguang"], "journal": "PloS one", "year": 2026, "abstract": "Spontaneous premature birth (SPTB) is a common pregnancy complication; however, few studies have explored cell senescence-related markers in SPTB. Bioinformatics and machine learning approaches were used to predict potential biomarkers associated with SPTB. Normal and SPTB gene expression profiles were obtained from the Gene Expression Omnibus (GEO) database, and cell senescence-associated genes from the Human Aging Genomic Resources (HAGR) database. Functional enrichment analysis and protein-protein interaction (PPI) network analysis of differentially expressed senescence-related genes in SPTB were conducted using Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and STRING databases. The infiltration of 22 types of immune cells in SPTB was calculated using the CIBERSORT deconvolution algorithm. Machine learning methods were employed to identify hub differentially expressed genes (DEGs). Datasets GSE174415 and GSE118442 were extracted for validation to determine the final hub genes. Additionally, receiver operating characteristic (ROC) curves were constructed to assess the diagnostic potential of the hub genes, and significant pathways associated with the final hub gene were explored by Gene Set Enrichment Analysis (GSEA). Finally, real-time quantitative polymerase chain reaction (RT-qPCR) was performed to validate the hub gene in clinical specimens. A total of 923 DEGs were identified, including 525 upregulated and 398 downregulated in the SPTB group. These 923 genes were intersected with 866 cell senescence-related genes, yielding 48 intersection genes. Functional enrichment analysis indicated that these intersection genes were primarily associated with cytokine-cytokine receptor interactions and the PI3K-Akt signaling pathway. The expression of activated dendritic cells and follicular helper T cells was significantly lower in the SPTB group compared to the full-term pregnancy group. A total of six hub genes, LGALS3, ESR1, PLA2G2A, TWIST1, CBS, and PLA2R1, were identified by machine learning. According to dataset validation, TWIST1 was identified as the final hub gene. TWIST1 was downregulated in placental tissues of the SPTB group and demonstrated high diagnostic value for SPTB. Thus, TWIST1 may be a novel molecular target for predicting and diagnosing SPTB, providing diagnostic value and novel insights into this condition.", "claims": [{"id": "claim-method", "statement": "ROC curves of hub genes were generated using GSE174415 and GSE118442 datasets via the pROC package in R. Area under the curve (AUC) values were calculated to evaluate the diagnostic efficacy of the identified hub genes and an AUC value > 0.7 was considered to have great diagnostic efficacy.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41544137", "locator": "sections[9] \"Evaluation of hub genes\" paragraph 2", "quote": "ROC curves of hub genes were generated using GSE174415 and GSE118442 datasets via the pROC package in R. Area under the curve (AUC) values were calculated to evaluate the diagnostic efficacy of the identified hub genes and an AUC value > 0.7 was considered to have great diagnostic efficacy."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41544137", "locator": "sections[4] \"Screening and analysis of differential expressed genes\" paragraph 2", "quote": "The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set."}], "state": "complete"}, {"id": "claim-target-result", "statement": "TWIST1 was identified as the final hub gene and demonstrated high diagnostic value for SPTB, with AUC values of 0.8984 and 0.8194 in the GSE174415 and GSE118442 datasets, respectively.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41544137", "locator": "sections[18] \"Evaluation of hub gene diagnostic efficacy\" paragraph 2", "quote": "The AUC values for TWIST1 in the two datasets were 0.8984 and 0.8194, respectively (Fig 5). These results indicate that TWIST1 is a reliable biomarker with high diagnostic value for SPTB."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "TWIST1 was identified as the final hub gene and demonstrated high diagnostic value for SPTB, with AUC values of 0.8984 and 0.8194 in the GSE174415 and GSE118442 datasets, respectively.", "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:41544137"], "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:GSE118442"], "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:GSE118442"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41544137", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0340809", "sha256": "sha256:836249cd2da147f6361162c99f38d590861953e4076017c793da56c37f029782", "bytes": 26445, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0340809", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12810911", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE118442", "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=GSE118442", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE118442", "version": null, "note": "The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3330252", "GSM3330253", "GSM3330254", "GSM3330255", "GSM3330256", "GSM3330257", "GSM3330258", "GSM3330259", "GSM3330260", "GSM3330261", "GSM3330262", "GSM3330263", "GSM3330264", "GSM3330265", "GSM3330266", "GSM3330267", "GSM3330268"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Assessing placental maturity through histological and transcriptomic analyses in idiopathic spontaneous preterm birth", "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:GSE174415", "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=GSE174415", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE174415", "version": null, "note": "The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM5310050", "GSM5310051", "GSM5310052", "GSM5310053", "GSM5310054", "GSM5310055", "GSM5310056", "GSM5310057", "GSM5310058", "GSM5310059", "GSM5310060", "GSM5310061", "GSM5310062", "GSM5310063", "GSM5310064", "GSM5310065", "GSM5310066", "GSM5310067", "GSM5310068", "GSM5310069", "GSM5310070", "GSM5310071", "GSM5310072", "GSM5310073", "GSM5310074", "GSM5310075", "GSM5310076", "GSM5310077", "GSM5310078", "GSM5310079", "GSM5310080", "GSM5310081"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Human Placental Transcriptome and fetal sex differences in Spontaneous Preterm Birth", "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:GSE118442 not downloaded", "asset:data:geo:GSE118442 licence not read", "asset:data:geo:GSE174415 not downloaded", "asset:data:geo:GSE174415 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": "DESeq2"}}, {"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": "GO enrichment"}}, {"id": "method-4", "family": null, "specific": null, "label": "Receiver operating characteristic (ROC) curve analysis using the pROC package, with area under the curve (AUC) values used to assess diagnostic efficacy.", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "ROC curves of hub genes were generated using GSE174415 and GSE118442 datasets via the pROC package in R. Area under the curve (AUC) values were calculated to evaluate the diagnostic efficacy of the identified hub genes and an AUC value > 0.7 was considered to have great diagnostic efficacy."}}], "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": ["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: deseq2."}, "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": ["GSE174415", "GSE118442"], "resolved_accessions": ["GSE174415", "GSE118442"], "statements": ["The GSE174415 dataset, containing 16 SPTB samples and 16 full-term pregnancy placenta samples, was selected as the training set."], "basis": "The paper names GSE174415, GSE118442 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:41544137", "data:geo:GSE118442"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE118442"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:10:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 7534, "completion_tokens": 1357, "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:41544137", "type": "paper", "label": "pmid:41544137"}, {"id": "source:pmid:41544137", "type": "manuscript", "label": "PMID 41544137 full text"}, {"id": "data:geo:GSE118442", "type": "dataset", "label": "GEO GSE118442"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41544137", "type": "paper", "label": "pmid:41544137"}, {"id": "source:pmid:41544137", "type": "manuscript", "label": "PMID 41544137 full text"}, {"id": "data:geo:GSE118442", "type": "dataset", "label": "GEO GSE118442"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41544137", "type": "extraction", "used": ["source:pmid:41544137"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE118442", "type": "accession_resolution", "used": ["data:geo:GSE118442"], "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:41544137", "parent_hash": "sha256:3afd995405763dd6bf8dd7d985a22e400b8c6210d1e72b2db80a5d3abeb4412e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE118442 licence not read", "asset:data:geo:GSE118442 not downloaded", "asset:data:geo:GSE174415 licence not read", "asset:data:geo:GSE174415 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": ["time quantitative polymerase chain reaction (RT-qPCR) was performed to validate the hub gene in c", "e quantitative polymerase chain reaction (RT-qPCR) was performed to validate the hub gene in c", "nescence-related genes. Clinical samples and RT-qPCR Placental tissue samples were collected from", "Biotech, China). Real-time quantitative PCR (RT-qPCR) was performed using SuperReal PreMix Plus ("], "order_basis": "paper_text_order:1408", "id": "assay:1"}, {"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": ["DESeq2"], "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":"2026-11-04T02:14:05+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}}}