{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26947931", "kind": "science-record", "revision": 6, "content_hash": "sha256:b629530d2884cc630e5e977d471655e7514e1daa0c0db5517ae1ca0e3ed2acfd", "created_at": "2026-11-01T15:40:16Z", "updated_at": "2026-11-01T21:20:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomics study reveals that the dysregulation of focal adhesion and ribosome contribute to early pregnancy loss.", "doi": "10.1002/prca.201500136", "pmid": "26947931", "authors": ["Lingli Xin", "Benhong Xu", "Li Ma", "Qingxiang Hou", "Mei Ye", "Shu Meng", "Xiaoping Ding", "Wei Ge"], "journal": "Proteomics. Clinical applications", "year": 2016, "abstract": "PURPOSE: Early pregnancy loss (EPL) affects 50-70% pregnant women in first trimester. The precise molecular mechanisms underlying EPL are far from being fully understood. Therefore, we aim to identify the molecular signaling pathways relating to EPL.\nEXPERIMENTAL DESIGN: We performed proteomics and bioinformatics analysis of the placental villi in women who have undergone EPL and in normal pregnant women. The proteomics data were validated by Western blot analysis.\nRESULTS: We identified a total of 5952 proteins in placental villi, of which 588 proteins were differentially expressed in the EPL women. Bioinformatics analysis revealed that these differentially expressed proteins participated in a variety of signaling pathways, including the focal adhesion pathway and ribosome pathway. Moreover, results of the Western blot confirmed that Desmin, Lamin A/C, MMP-9, and histone H4 were upregulated in EPL and the Lamin C/ Lamin A ratio decreased obviously in EPL. These proteins could be associated with the pathophysiology of EPL. The data have been deposited to the ProteomeXchange with identifier PXD002391.\nCONCLUSION AND CLINICAL RELEVANCE: Our study demonstrated that the focal adhesion pathway and ribosome pathway are involved in EPL, and these findings might contribute to unveil the pathophysiology of EPL.", "claims": [{"id": "claim-data-access", "statement": "The MS proteomics data have been deposited to the ProteomeXchange Consortium 15 via PRIDE partner repository with the data identifier PXD002391.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26947931", "locator": "sections[9] \"Data analysis\" paragraph 2", "quote": "The MS proteomics data have been deposited to the ProteomeXchange Consortium 15 via PRIDE partner repository with the data identifier PXD002391."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using TMT-labeled quantitative proteomics with pathway enrichment analysis, the study found that the focal adhesion and ribosome pathways are involved in early pregnancy loss; the source data are publicly available through ProteomeXchange/PRIDE under accession PXD002391.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26947931", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "Our study demonstrated that the focal adhesion pathway and ribosome pathway are involved in EPL, and these findings might contribute to unveil the pathophysiology of EPL."}, {"asset": "source:pmid:26947931", "locator": "sections[2] \"Introduction\" paragraph 6", "quote": "To comprehensively study the molecular signaling pathways related to EPL, we used TMT labeling‐based proteomics analysis to identify differentially expressed proteins between placental villi from EPL and normal pregnant women."}, {"asset": "source:pmid:26947931", "locator": "sections[9] \"Data analysis\" paragraph 2", "quote": "The thresholds for downregulation and upregulation were set at 0.8 and 1.2, respectively."}, {"asset": "source:pmid:26947931", "locator": "sections[9] \"Data analysis\" paragraph 2", "quote": "The WebGestalt online toolkit was also used to conduct enrichment analysis based on Wikipathways and KEGG analysis databases. The significance level was set at 0.0001."}, {"asset": "source:pmid:26947931", "locator": "sections[9] \"Data analysis\" paragraph 2", "quote": "The MS proteomics data have been deposited to the ProteomeXchange Consortium 15 via PRIDE partner repository with the data identifier PXD002391."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using TMT-labeled quantitative proteomics with pathway enrichment analysis, the study found that the focal adhesion and ribosome pathways are involved in early pregnancy loss; the source data are publicly available through ProteomeXchange/PRIDE under accession PXD002391.", "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:26947931"], "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:PXD002391"], "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:PXD002391"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26947931", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/prca.201500136", "sha256": "sha256:06adc07b9d363e0feead5c70aa8fe115d75babad2d2e5afcbcc2eac66f88e68a", "bytes": 41901, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/prca.201500136", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5084743", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002391", "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=PXD002391", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002391", "version": null, "note": "The MS proteomics data have been deposited to the ProteomeXchange Consortium 15 via PRIDE partner repository with the data identifier PXD002391.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The MS proteomics data have been deposited to the ProteomeXchange Consortium 15 via PRIDE partner repository with the data identifier PXD002391.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomics Study of Molecular Mechanisms Involved in Early Pregnancy Loss", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:26947931:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7129adbaafbd2431b4a60e30a51048f31a983a754795583dff2f055915f85a4a", "bytes": 576, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#prca1742-tbl-0001", "version": null, "note": "Comparison of subject characteristics between the EPL group and normal group", "structure": {"pmcid": "PMC5084743", "section_index": 11, "section_title": "Subjects characteristics", "row_count": 7, "column_count": 4}, "table": {"label": "Table 1", "caption": "Comparison of subject characteristics between the EPL group and normal group", "rows": [["Subject characteristics", "Group", "Mean ± SD (n = 5)", "p‐Value"], ["Age (years)", "EPL", "30.6 ± 2.015", "0.54"], ["", "Control", "29.0 ± 1.517", ""], ["Pregnancy duration (days)", "EPL", "47.0 ± 6.301", "0.57"], ["", "Control", "42.8 ± 3.338", ""], ["Number of previous pregnancies", "EPL", "1.8 ± 0.374", "0.69"], ["", "Control", "2.0 ± 0.316", ""]], "row_count": 7, "column_count": 4, "numeric_cells": 10, "header_rows": 1, "locator": "section[11]/table-wrap[1]#prca1742-tbl-0001"}}, {"id": "asset:table:pmid:26947931:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a01f01e0f71b21bacf49907247bcedd05b2cff8ffc1c3f764bd3b663945a4110", "bytes": 2843, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#prca1742-tbl-0002", "version": null, "note": "Pathways in which differentially expressed proteins are involved, based on Wikipathway database", "structure": {"pmcid": "PMC5084743", "section_index": 14, "section_title": "Pathways involving the differentially expressed proteins", "row_count": 15, "column_count": 4}, "table": {"label": "Table 2", "caption": "Pathways in which differentially expressed proteins are involved, based on Wikipathway database", "rows": [["Pathway name", "Gene no.", "Entrez Gene", "Statistics"], ["Glycolysis and gluconeogenesis", "13", "6515 2597 2806 5230 3939 4190 2805 2821 5315 2023 5223 7167 3945", "C = 50; O = 13; E = 0.66; R = 19.71; rawp = 7.28 × 10−14; adjp = 7.50 × 10−12"], ["Epithelium TarBase", "23", "10105 5236 5270 3915 3035 4677 5725 10061 10971 4691 51809 5315 4144 10797 488 83858 23603 822 396 5878 1021 143888 4907", "C = 340; O = 23; E = 4.49; R = 5.13 rawp = 2.37 × 10−10; adjp = 1.22 × 10−8"], ["Lymphocyte TarBase", "28", "10105 10484 5236 5270 3915 3035 4677 5725 26973 10061 10971 4691 51809 5315 4144 11137 10797 488 83858 23603 822 396 6902 10642 5878 1021 143888 4907", "C = 533; O = 28; E = 7.03; R = 3.98 rawp = 8.98 × 10−10; adjp = 3.08 × 10−8"], ["Focal adhesion", "16", "2335 3915 208 3684 7148 3908 284217 3371 3689 7448 2321 3912 5062 1282 3694 3911", "C = 185; O = 16; E = 2.44; R = 6.56 rawp = 4.07 × 10−9; adjp = 1.05 × 10−7"], ["Statin pathway", "7", "6646 341 336 348 6713 5360 335", "C = 30; O = 7; E = 0.40; R = 17.69 rawp = 1.05 × 10−7; adjp = 2.16 × 10−6"], ["Leukocyte TarBase", "13", "10105 5270 26973 10971 5315 10797 488 23603 822 396 6902 5878 1021", "C = 160; O = 13; E = 2.11; R = 6.16 rawp = 2.40 × 10−7; adjp = 3.61 × 10−6"], ["Vitamin A and carotenoid metabolism", "8", "1382 948 5950 54884 8854 220 216 5947", "C = 49; O = 8; E = 0.65; R = 12.37; rawp = 2.45 × 10−7; adjp = 3.61 × 10−6"], ["Muscle cell TarBase", "21", "10105 10484 5236 3915 26973 10971 4691 51809 5315 11137 10797 488 83858 23603 822 396 6902 10642 1021 143888 4907", "C = 424; O = 21; E = 5.59; R = 3.75 rawp = 3.03 × 10−7; adjp = 3.90 × 10−6"], ["mRNA processing", "11", "3178 3182 5725 3183 22826 10236 27316 3184 3191 4904 3192", "C = 132; O = 11; E = 1.74; R = 6.32 rawp = 1.57 × 10−6; adjp = 1.80 × 10−5"], ["Cytoplasmic ribosomal proteins", "9", "6202 6154 6230 6204 4736 3921 6147 6201 6223", "C = 88; O = 9; E = 1.16; R = 7.75 rawp = 2.58 × 10−6; adjp = 2.66 × 10−5"], ["Complement and coagulation cascades", "7", "718 2 336 5265 5340 2244 717", "C = 51; O = 7; E = 0.67; R = 10.40 rawp = 4.70 × 10−6; adjp = 4.03 × 10−5"], ["Translation factors", "7", "1984 1975 7458 5610 1938 10209 26986", "C = 51; O = 7; E = 0.67; R = 10.40 rawp = 4.70 × 10−6; adjp = 4.03 × 10−5"], ["AGE‐RAGE pathway", "8", "4318 6647 3958 5578 1729 5579 6772 4478", "C = 76; O = 8; E = 1.00; R = 7.98 rawp = 7.50 × 10−6; adjp = 5.94 × 10−5"], ["G13 signaling pathway", "6", "397 1729 10788 5216 9138 1072", "C = 37; O = 6; E = 0.49; R = 12.29 rawp = 8.44 × 10−6; adjp = 6.21 × 10−5"]], "row_count": 15, "column_count": 4, "numeric_cells": 43, "header_rows": 1, "locator": "section[14]/table-wrap[1]#prca1742-tbl-0002"}}], "gaps": ["asset:data:geo:PXD002391 not downloaded", "asset:data:geo:PXD002391 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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"}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["PXD002391"], "resolved_accessions": ["PXD002391"], "statements": ["The MS proteomics data have been deposited to the ProteomeXchange Consortium 15 via PRIDE partner repository with the data identifier PXD002391."], "basis": "The paper names PXD002391 in ProteomeXchange Consortium via PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pathway_enrich"], "assets": ["source:pmid:26947931", "data:geo:PXD002391", "asset:table:pmid:26947931:1", "asset:table:pmid:26947931:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002391"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:31Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 83450, "completion_tokens": 2272, "cached_tokens": 1536}}, "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:26947931", "type": "paper", "label": "pmid:26947931"}, {"id": "source:pmid:26947931", "type": "manuscript", "label": "PMID 26947931 full text"}, {"id": "data:geo:PXD002391", "type": "dataset", "label": "GEO PXD002391"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26947931", "type": "paper", "label": "pmid:26947931"}, {"id": "source:pmid:26947931", "type": "manuscript", "label": "PMID 26947931 full text"}, {"id": "data:geo:PXD002391", "type": "dataset", "label": "GEO PXD002391"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26947931", "type": "extraction", "used": ["source:pmid:26947931"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002391", "type": "accession_resolution", "used": ["data:geo:PXD002391"], "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:26947931", "parent_hash": "sha256:04da975ea94ef89a467f521bc6d586af9d5db4aa37aafeb7aab77674ed91dc79", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD002391 licence not read", "asset:data:geo:PXD002391 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["women. The proteomics data were validated by Western blot analysis. RESULTS: We identified a total of", "d ribosome pathway. Moreover, results of the Western blot confirmed that Desmin, Lamin A/C, MMP-9, and", "in −80°C until further proteomics analysis. Western blot analysis of the differentially expressed pro", "results of the proteomics data, we performed Western blot analysis of four relevant proteins in four E"], "order_basis": "paper_text_order:517", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["pathway enrichment"], "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":"2026-11-04T01:49:02+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}}}