{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35132338", "kind": "science-record", "revision": 6, "content_hash": "sha256:97caead2a4f06bd52e0994ce3d97e1e3895a06291dcc00c97eff2db85cc5a4ec", "created_at": "2026-11-01T17:36:53Z", "updated_at": "2026-11-01T22:48:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Driver Genes and Interaction Networks Related to Brain Metastasis in Breast Cancer Patients.", "doi": "10.1155/2022/7631456", "pmid": "35132338", "authors": ["Haojie Zhang", "Xiaohong Wang", "Changran Hou", "Zhenlin Yang"], "journal": "Disease markers", "year": 2022, "abstract": "Brain metastasis is a common complication of breast cancer (BC); however, the interaction networks and driver genes that lead to brain metastasis in BC patients are still unknown. In this study, we employed bioinformatics analyses to discover hub genes and long noncoding RNA- (lncRNA-) protein-coding gene (PCG) networks related to BC brain metastasis (BCBM). Firstly, we screened differentially expressed PCGs and lncRNAs in normal and BCBM samples using the GSE52604 dataset. Subsequently, differentially expressed genes (DEGs) and overall interaction networks were constructed, and topological degrees were analyzed to identify potential driver genes. After identifying the hub pathogenic module by weighted gene coexpression network analysis (WGCNA), the genes in the hub module were evaluated for functional enrichment. Finally, we constructed multiple interaction networks associated with BCBM and identified seven potential driver genes, out of which MYBPC1 was the only overlapping gene in the adopted analytical methods. It is worth mentioning that we validated the prognostic value of the identified hub genes in TCGA database and evaluated the prediction ability of MYBPC1 in the GSE38057 dataset. In addition, the CIBERSORT algorithm revealed changes in the immune microenvironment. In conclusion, the driver PCGs and lncRNAs in the interaction networks can be utilized as a promising therapeutic strategy for the treatment of brain metastasis in BC patients.", "claims": [{"id": "claim-method", "statement": "The ROC analysis of the GSE38057 dataset indicated that MYBPC1 could well confirm the possibility of brain metastasis in BC patients (AUC = 0.959), as shown in Figure 8.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35132338", "locator": "sections[17] \"3.7. Prognostic Analysis and External Validation\" paragraph 2", "quote": "The ROC analysis of the GSE38057 dataset indicated that MYBPC1 could well confirm the possibility of brain metastasis in BC patients (AUC = 0.959), as shown in Figure 8."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35132338", "locator": "sections[22] \"Data Availability\" paragraph 2", "quote": "The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "MYBPC1 demonstrated strong predictive ability for identifying brain metastasis in breast cancer patients, with an AUC of 0.959.", "kind": "quantitative", "target": {"value": 0.959, "unit": "auc", "tolerance": null, "source": "The ROC analysis of the GSE38057 dataset indicated that MYBPC1 could well confirm the possibility of brain metastasis in BC patients (AUC = 0.959), as shown in Figure 8."}, "evidence": [{"asset": "source:pmid:35132338", "locator": "sections[17] \"3.7. Prognostic Analysis and External Validation\" paragraph 2", "quote": "The ROC analysis of the GSE38057 dataset indicated that MYBPC1 could well confirm the possibility of brain metastasis in BC patients (AUC = 0.959), as shown in Figure 8."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "MYBPC1 demonstrated strong predictive ability for identifying brain metastasis in breast cancer patients, with an AUC of 0.959.", "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:35132338"], "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:GSE38057"], "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:GSE38057"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35132338", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2022/7631456", "sha256": "sha256:89e8dc8314be87fd6cb8d9775f24d0423063f9d6a07d3959ea5a96cf66d644d9", "bytes": 25220, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2022/7631456", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8817105", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE38057", "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=GSE38057", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38057", "version": null, "note": "The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM933102", "GSM933103", "GSM933104", "GSM933105", "GSM933106", "GSM933107", "GSM933108", "GSM933109", "GSM933110", "GSM933111", "GSM933112", "GSM933113", "GSM933114", "GSM933115", "GSM933116", "GSM933117", "GSM933118", "GSM933119", "GSM933120", "GSM933121", "GSM933122", "GSM933123", "GSM933124", "GSM933125", "GSM933126", "GSM933127", "GSM933128", "GSM933129", "GSM933130", "GSM933131", "GSM933132", "GSM933133", "GSM933134", "GSM933135", "GSM933136", "GSM933137", "GSM933138", "GSM933139", "GSM933140", "GSM933141", "GSM933142", "GSM933143", "GSM933144", "GSM933145", "GSM933146", "GSM933147", "GSM933148", "GSM933149", "GSM933150", "GSM933151", "GSM933152", "GSM933153", "GSM933154", "GSM933155", "GSM933156", "GSM933157", "GSM933158", "GSM933159", "GSM933160", "GSM933161", "GSM933162", "GSM933163", "GSM933164", "GSM933165", "GSM933166", "GSM933167", "GSM933168", "GSM933169", "GSM933170", "GSM933171", "GSM933172", "GSM933173", "GSM933174", "GSM933175", "GSM933176", "GSM933177", "GSM933178", "GSM933179", "GSM933180", "GSM933181", "GSM933182", "GSM933183", "GSM933184", "GSM933185", "GSM933186", "GSM933187", "GSM933188"], "sample_count": 87, "group_sizes": null, "group_sizes_basis": null, "platform": "5826", "taxon": "Homo sapiens", "title": "A 13-gene signature predicting rapid development of brain metastases in breast cancer", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE52604", "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=GSE52604", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52604", "version": null, "note": "The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1272403", "GSM1272404", "GSM1272405", "GSM1272406", "GSM1272407", "GSM1272408", "GSM1272409", "GSM1272410", "GSM1272411", "GSM1272412", "GSM1272413", "GSM1272414", "GSM1272415", "GSM1272416", "GSM1272417", "GSM1272418", "GSM1272419", "GSM1272420", "GSM1272421", "GSM1272422", "GSM1272423", "GSM1272424", "GSM1272425", "GSM1272426", "GSM1272427", "GSM1272428", "GSM1272429", "GSM1272430", "GSM1272431", "GSM1272432", "GSM1272433", "GSM1272434", "GSM1272435", "GSM1272436", "GSM1272437", "GSM1272438", "GSM1272439", "GSM1272440", "GSM1272441", "GSM1272442", "GSM1272443", "GSM1272444", "GSM1272445", "GSM1272446", "GSM1272447", "GSM1272448", "GSM1272449", "GSM1272450", "GSM1272451", "GSM1272452", "GSM1272453", "GSM1272454", "GSM1272455", "GSM1272456", "GSM1272457"], "sample_count": 55, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Breast Brain Metastasis, Non-Neoplastic Brain, and Non-Neoplastic Breast Gene Expression", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE38057 not downloaded", "asset:data:geo:GSE38057 licence not read", "asset:data:geo:GSE52604 not downloaded", "asset:data:geo:GSE52604 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The ROC analysis of the GSE38057 dataset indicated that MYBPC1 could well confirm the possibility of brain metastasis in BC patients (AUC = 0.959), as shown in Figure 8."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "classification_metrics", "expected_value": 0.959, "unit": "auc", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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": ["GSE38057", "GSE52604"], "resolved_accessions": ["GSE38057", "GSE52604"], "statements": ["The following information was supplied regarding data availability: data is available at TCGA (https://portal.gdc.cancer.gov/) and GEO databases (https://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE38057, GSE52604 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:35132338", "data:geo:GSE38057"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE38057"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:33:33Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8426, "completion_tokens": 1860, "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:35132338", "type": "paper", "label": "pmid:35132338"}, {"id": "source:pmid:35132338", "type": "manuscript", "label": "PMID 35132338 full text"}, {"id": "data:geo:GSE38057", "type": "dataset", "label": "GEO GSE38057"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35132338", "type": "paper", "label": "pmid:35132338"}, {"id": "source:pmid:35132338", "type": "manuscript", "label": "PMID 35132338 full text"}, {"id": "data:geo:GSE38057", "type": "dataset", "label": "GEO GSE38057"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35132338", "type": "extraction", "used": ["source:pmid:35132338"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE38057", "type": "accession_resolution", "used": ["data:geo:GSE38057"], "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:35132338", "parent_hash": "sha256:12f22850d532057e329ae02a87f9c76cc8f276afeb9273478653fed20a192ae8", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE38057 licence not read", "asset:data:geo:GSE38057 not downloaded", "asset:data:geo:GSE52604 licence not read", "asset:data:geo:GSE52604 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The ROC analysis of the GSE38057 dataset indicated that MYBPC1 could well confirm the possibility of brain metastasis in BC patients (AUC = 0.959), as shown in Figure 8."], "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":"2026-11-04T00:38:32+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}}}