{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41283652", "kind": "science-record", "revision": 4, "content_hash": "sha256:7746e8d66945f1e6fdea8450465acae5171d124d07f5f185da6048936a081176", "created_at": "2026-11-01T20:31:19Z", "updated_at": "2026-11-01T22:57:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comparative Proteomic Analysis of Aqueous Humor, Anterior Lens Capsules, and Crystalline Lenses in Different Human Cataract Subtypes Versus Healthy Controls.", "doi": "10.3390/proteomes13040062", "pmid": "41283652", "authors": ["Christina Karakosta", "Martina Samiotaki", "Anastasios Bisoukis", "Konstantinos I Bougioukas", "George Panayotou", "Nantieznta Kyriakidou", "Konstantinos Moschou", "Marilita M Moschos"], "journal": "Proteomes", "year": 2025, "abstract": "BACKGROUND: The aim of this study is to investigate the pathophysiology of cataract by analyzing signaling pathways in three sample types obtained from four different lens groups: age-related (ARC), diabetic (DC), post-vitrectomy cataract (PVC) and clear control lenses.\nMETHODS: Three sample types-the aqueous humor, the anterior capsule and the phaco cassette content-were collected during cataract surgery from 39 participants (ARC = 12, DC = 11, PVC = 7 and control = 9). The samples were prepared based on Sp3 protocol. The recognition and quantification of proteins were performed with liquid chromatography online with tandem mass spectrometry using the DIA-NN software. Perseus software (v1.6.15.0) was used for statistical analysis. Data are available via ProteomeXchange with identifiers PXD045547, PXD045554, PXD045557, and PXD069667.\nRESULTS: In total, 1986 proteins were identified in the aqueous humor, 2804 in the anterior capsule, and 3337 in the phaco cassette samples. Proteins involved in actin and microtubule cytoskeleton organization, including ACTN4, were downregulated in all three cataract groups compared to controls. Proteins involved in glycolipid metabolic process, including GAL3ST1, GAL3ST4, and GLA, were upregulated in ARC compared to controls. Proteins involved in the non-canonical Wnt receptor signaling pathway, including FRZB, SFRP1, SFRP2, SFRP5, WNT5A, and WNT7A, were upregulated in ARC compared to DC, PVC, and controls.\nCONCLUSIONS: Comprehensive proteomic profiles were generated using DIA proteomics by comparing ARC, DC, and PVC versus controls. This is the first study to use phaco cassette contents to investigate cataract formation in comparison to controls. Our findings significantly enhance the current understanding of human cataract pathophysiology and provide novel insights into the mechanisms underlying cataract formation.", "claims": [{"id": "claim-method", "statement": "Group comparisons among ARC–controls, DC–controls, and PVC–controls were conducted using two-sample t-tests, and volcano plots were generated with a permutation-based false discovery rate (FDR) threshold of 1% and an S0 parameter of 0.1. To assess differences across all cohorts, one-way ANOVA was applied, and results were visualized as heatmaps using the same FDR and S0 parameters, with hierarchical clustering based on Euclidean distance.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41283652", "locator": "sections[8] \"2.6. Statistical Analysis\" paragraph 2", "quote": "Group comparisons among ARC–controls, DC–controls, and PVC–controls were conducted using two-sample t-tests, and volcano plots were generated with a permutation-based false discovery rate (FDR) threshold of 1% and an S0 parameter of 0.1. To assess differences across all cohorts, one-way ANOVA was applied, and results were visualized as heatmaps using the same FDR and S0 parameters, with hierarchical clustering based on Euclidean distance."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41283652", "locator": "sections[23] \"Data Availability Statement\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46]."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 1,986 proteins in aqueous humor, 2,804 in the anterior capsule, and 3,337 in phaco cassette samples.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41283652", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In total, 1986 proteins were identified in the aqueous humor, 2804 in the anterior capsule, and 3337 in the phaco cassette samples."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified 1,986 proteins in aqueous humor, 2,804 in the anterior capsule, and 3,337 in phaco cassette samples.", "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:41283652"], "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:PXD045547"], "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:PXD045547"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41283652", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/proteomes13040062", "sha256": "sha256:9cfcf0739690ce544996b7ac12a0ed9c8bff35e7fcc4244bbcdf423549573acc", "bytes": 46711, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/proteomes13040062", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12641653", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD045547", "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=PXD045547", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD045547", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic changes in anterior capsule of diabetic, age-related and post-vitrectomy cataract.", "resolution_checked_at": "2026-11-01T20:16:17Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD045554", "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=PXD045554", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD045554", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic changes in aqueous humor of diabetic, age-related and post-vitrectomy cataract.", "resolution_checked_at": "2026-11-01T20:16:17Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD045557", "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=PXD045557", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD045557", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46].", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic changes in lens of diabetic, age-related and post-vitrectomy cataract.", "resolution_checked_at": "2026-11-01T20:16:17Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD045547 not downloaded", "asset:data:geo:PXD045547 licence not read", "asset:data:geo:PXD045554 not downloaded", "asset:data:geo:PXD045554 licence not read", "asset:data:geo:PXD045557 not downloaded", "asset:data:geo:PXD045557 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Group comparisons among ARC–controls, DC–controls, and PVC–controls were conducted using two-sample t-tests, and volcano plots were generated with a permutation-based false discovery rate (FDR) threshold of 1% and an S0 parameter of 0.1. To assess differences across all cohorts, one-way ANOVA was applied, and results were visualized as heatmaps using the same FDR and S0 parameters, with hierarchical clustering based on Euclidean distance."}}, {"id": "method-2", "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-3", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["PXD045547", "PXD045554", "PXD045557", "and PXD069667"], "resolved_accessions": ["PXD045547", "PXD045554", "PXD045557"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD045547, PXD045554, PXD045557, PXD069667 [46]."], "basis": "The paper names PXD045547, PXD045554, PXD045557 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:41283652", "data:geo:PXD045547"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD045547"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:06:23Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13103, "completion_tokens": 1297, "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:41283652", "type": "paper", "label": "pmid:41283652"}, {"id": "source:pmid:41283652", "type": "manuscript", "label": "PMID 41283652 full text"}, {"id": "data:geo:PXD045547", "type": "dataset", "label": "GEO PXD045547"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41283652", "type": "paper", "label": "pmid:41283652"}, {"id": "source:pmid:41283652", "type": "manuscript", "label": "PMID 41283652 full text"}, {"id": "data:geo:PXD045547", "type": "dataset", "label": "GEO PXD045547"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41283652", "type": "extraction", "used": ["source:pmid:41283652"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD045547", "type": "accession_resolution", "used": ["data:geo:PXD045547"], "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:41283652", "parent_hash": "sha256:7a7c451e8ae2a60cb3f643e86b88e7adf71231763facfc7b5ebff09aea124968", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD045547 licence not read", "asset:data:geo:PXD045547 not downloaded", "asset:data:geo:PXD045554 licence not read", "asset:data:geo:PXD045554 not downloaded", "asset:data:geo:PXD045557 licence not read", "asset:data:geo:PXD045557 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Group comparisons among ARC–controls, DC–controls, and PVC–controls were conducted using two-sample t-tests, and volcano plots were generated with a permutation-based false discovery rate (FDR) threshold of 1% and an S0 parameter of 0.1. To assess differences across all cohorts, one-way ANOVA was applied, and results were visualized as heatmaps using the same FDR and S0 parameters, with hierarchical clustering based on Euclidean distance."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:16:56+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}}}