{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34738881", "kind": "science-record", "revision": 4, "content_hash": "sha256:f44c1b51837641fb5dd90fb1939be226eb2d90e6f691b270eab02d1b44720e5a", "created_at": "2026-11-01T17:36:25Z", "updated_at": "2026-11-01T22:05:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Multi-Omics analysis identifies a lncRNA-related prognostic signature to predict bladder cancer recurrence.", "doi": "10.1080/21655979.2021.2000122", "pmid": "34738881", "authors": ["Zhipeng Xu", "Hui Chen", "Jin Sun", "Weipu Mao", "Shuqiu Chen", "Ming Chen"], "journal": "Bioengineered", "year": 2021, "abstract": "Bladder cancer (BLCA) is one of the most common cancers worldwide with high recurrence rate. Hence, we intended to establish a recurrence-related long non-coding RNA (lncRNA) model of BLCA as a potential biomarker based on multi-omics analysis. Multi-omics data including copy number variation (CNV) data, mutation annotation files, RNA expression profiles and clinical data of The Cancer Genome Atlas (TCGA) BLCA cohort (303 cases) and GSE31684 (93 cases) were downloaded from public database. With multi-omics analysis, twenty lncRNAs were identified as the candidates related with BLCA recurrence, CNVs and mutations in training set. Ten-lncRNA signature were established using least absolute shrinkage and selection operation (LASSO) and Cox regression. Then, various survival analysis was used to assess the power of lncRNA model in predicting BLCA recurrence. The results showed that the recurrence-free survival time of high-risk group was significantly shorter than that of low-risk group in training and testing sets, and the predictive value of ten-lncRNA signature was robust and independent of other clinical variables. Gene Set Enrichment Analysis (GSEA) showed this signature were associated with immune disorders, indicating this signature may be involved in tumor immunology. After compared with the other reported lncRNA signatures, ten-lncRNA signature was validated as a superior prognostic model in predicting the recurrence of BLCA. The effectiveness of the model was also evaluated in bladder cancer samples via qRT-PCR. Thus, the novel ten-lncRNA signature, constructed based on multi-omics data, had robust prognostic power in predicting the recurrence of BLCA and potential clinical implications as biomarkers.", "claims": [{"id": "claim-method", "statement": "Ten-lncRNA signature were established using least absolute shrinkage and selection operation (LASSO) and Cox regression.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34738881", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Ten-lncRNA signature were established using least absolute shrinkage and selection operation (LASSO) and Cox regression."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Original data were uploaded to a recognized data repository (URL: https://zenodo.org/record/5153530#.YZtEZU5ByUk; DOI: 10.5281/zenodo.5153530)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34738881", "locator": "sections[31] \"Data availability statement\" paragraph 2", "quote": "Original data were uploaded to a recognized data repository (URL: https://zenodo.org/record/5153530#.YZtEZU5ByUk; DOI: 10.5281/zenodo.5153530)"}], "state": "complete"}, {"id": "claim-target-result", "statement": "Thus, the novel ten-lncRNA signature, constructed based on multi-omics data, had robust prognostic power in predicting the recurrence of BLCA and potential clinical implications as biomarkers.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:34738881", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Thus, the novel ten-lncRNA signature, constructed based on multi-omics data, had robust prognostic power in predicting the recurrence of BLCA and potential clinical implications as biomarkers."}, {"asset": "source:pmid:34738881", "locator": "sections[18] \"Validating prognostic power of the relapse-associated lncRNA signature\" paragraph 2", "quote": "AUC for ten-lncRNA signature was 0.73 at the RFS in the fifth year (Figure 3(b))."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Thus, the novel ten-lncRNA signature, constructed based on multi-omics data, had robust prognostic power in predicting the recurrence of BLCA and potential clinical implications as biomarkers.", "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:34738881"], "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:GSE31684"], "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:GSE31684"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34738881", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/21655979.2021.2000122", "sha256": "sha256:57c71187a66a4e1e018e02428bda2ff3dade49fc2e6234852dd2ef05070dd9ec", "bytes": 51579, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/21655979.2021.2000122", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8810060", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31684", "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=GSE31684", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31684", "version": null, "note": "Original data were uploaded to a recognized data repository (URL: https://zenodo.org/record/5153530#.YZtEZU5ByUk; DOI: 10.5281/zenodo.5153530)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Original data were uploaded to a recognized data repository (URL: https://zenodo.org/record/5153530#.YZtEZU5ByUk; DOI: 10.5281/zenodo.5153530)", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM786491", "GSM786492", "GSM786493", "GSM786494", "GSM786495", "GSM786496", "GSM786497", "GSM786498", "GSM786499", "GSM786500", "GSM786501", "GSM786502", "GSM786503", "GSM786504", "GSM786505", "GSM786506", "GSM786507", "GSM786508", "GSM786509", "GSM786510", "GSM786511", "GSM786512", "GSM786513", "GSM786514", "GSM786515", "GSM786516", "GSM786517", "GSM786518", "GSM786519", "GSM786520", "GSM786521", "GSM786522", "GSM786523", "GSM786524", "GSM786525", "GSM786526", "GSM786527", "GSM786528", "GSM786529", "GSM786530", "GSM786531", "GSM786532", "GSM786533", "GSM786534", "GSM786535", "GSM786536", "GSM786537", "GSM786538", "GSM786539", "GSM786540", "GSM786541", "GSM786542", "GSM786543", "GSM786544", "GSM786545", "GSM786546", "GSM786547", "GSM786548", "GSM786549", "GSM786550", "GSM786551", "GSM786552", "GSM786553", "GSM786554", "GSM786555", "GSM786556", "GSM786557", "GSM786558", "GSM786559", "GSM786560", "GSM786561", "GSM786562", "GSM786563", "GSM786564", "GSM786565", "GSM786566", "GSM786567", "GSM786568", "GSM786569", "GSM786570", "GSM786571", "GSM786572", "GSM786573", "GSM786574", "GSM786575", "GSM786576", "GSM786577", "GSM786578", "GSM786579", "GSM786580", "GSM786581", "GSM786582", "GSM786583"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Combination of a novel gene expression signature with a clinical nomogram improves the prediction of survival in high-risk bladder cancer  ", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE31684 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Ten-lncRNA signature were established using least absolute shrinkage and selection operation (LASSO) and Cox regression."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE31684"], "resolved_accessions": ["GSE31684"], "statements": ["Original data were uploaded to a recognized data repository (URL: https://zenodo.org/record/5153530#.YZtEZU5ByUk; DOI: 10.5281/zenodo.5153530)"], "basis": "The paper names GSE31684 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:34738881", "data:geo:GSE31684"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31684"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:06:17Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14802, "completion_tokens": 1733, "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:34738881", "type": "paper", "label": "pmid:34738881"}, {"id": "source:pmid:34738881", "type": "manuscript", "label": "PMID 34738881 full text"}, {"id": "data:geo:GSE31684", "type": "dataset", "label": "GEO GSE31684"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34738881", "type": "paper", "label": "pmid:34738881"}, {"id": "source:pmid:34738881", "type": "manuscript", "label": "PMID 34738881 full text"}, {"id": "data:geo:GSE31684", "type": "dataset", "label": "GEO GSE31684"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34738881", "type": "extraction", "used": ["source:pmid:34738881"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31684", "type": "accession_resolution", "used": ["data:geo:GSE31684"], "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:34738881", "parent_hash": "sha256:0304172f387d5c08af4631c15383e711277b6a7c5776806df81747dc01c39860", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE31684 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["carcinoma cell lines (UM-UC-3 and T24) were cultured in DMEM (Gibco, USA) containing 10% fetal bovin"], "order_basis": "paper_text_order:2396", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["f) Colony formation assay on the BLCA cells transfected with siRNA. (g, h) Transwell assay was used", "used to evaluate the migration of BLCA cells transfected with siRNA Supplementary Material Supplement", ". (c) Evaluating the efficiency of AGAP2-AS1 knockdown via qRT-PCR. (d) CCK-8 assay on the effect o", ". (d) CCK-8 assay on the effect of AGAP2-AS1 knockdown on cell proliferation. The OD value among di"], "order_basis": "paper_text_order:5441", "id": "assay:2"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ency of AGAP2-AS1 knockdown via qRT-PCR. (d) CCK-8 assay on the effect of AGAP2-AS1 knockdown o"], "order_basis": "paper_text_order:5468", "id": "assay:3"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Ten-lncRNA signature were established using least absolute shrinkage and selection operation (LASSO) and Cox regression."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T00:47:21+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}}}