{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40722666", "kind": "science-record", "revision": 1, "content_hash": "sha256:57f35ba7d5b9a2a5facc5ae20bcf112edc4042f9d2c25270c94cbc33ed13ff2f", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T10:25:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Expression Characteristics and Prognostic Value of KLRG2 in Endometrial Cancer: A Comprehensive Analysis Based on Multi-Omics Data.", "doi": "10.3390/biomedicines13071592", "pmid": "40722666", "authors": null, "journal": "Biomedicines", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 3.08, "unit": "hazard ratio", "tolerance": null, "source": "chars 1208-1308 of source sha256 bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54"}, "evidence": [{"asset": "source:pmid:40722666", "locator": "chars 1208-1308 of source sha256 bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54", "quote": "High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96)"}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40722666"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40722666", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40722666' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40722666", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/biomedicines13071592", "sha256": "sha256:bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/biomedicines13071592", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40722666 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40722666"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40722666"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "722d50752be0a285188af5584def54616da4e074100afde3673134d965d74c85", "source_hash": "bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54", "raw_response_sha256": "sha256:c164eb6da37ff402de0a80d6496aa873c4e898a52983c051a5f2eeaeb6e9ab17", "raw_response_chars": 5650}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "613d8ea079b7723ba7f4a0762cdb64c27a8992960d586e7f72e7ba84e705964b", "source_hash": "bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54", "raw_response_sha256": "sha256:52ac21753f656332f366a4d340fb20e7448c9b357c846351bd877b63e0be0f05", "raw_response_chars": 74006}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "d78206785e58cd68f1f2d433ff5f5ff2ca7da3e73ed2aa50be6f5cdc1201e78a", "source_hash": "bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54", "raw_response": "{\"parent_value\":3.08,\"unit\":\"HR\",\"evidence\":\"High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96)\",\"target_result\":\"High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96).\",\"number_stated\":true}", "reading": {"parent_value": 3.08, "unit": "HR", "evidence": "High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96)", "target_result": "High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96).", "number_stated": true, "source_locator": "chars 1208-1308 of source sha256 bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54"}, "recorded_at": "2026-10-31T15:23:24.872716+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "996f5f0b1a119e119dcfe59aa9b48260e2d783171af26959b739b7e825cf0be7", "source_hash": "bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for registered target main finding. Paper abstract: high KLRG2 independently predicted worse OS HR=3.08 and PFI HR=1.98. Which single numerical result headline? Need discern perhaps target is \"headline numerical result paper states for its main finding\" and likely one prominent number. They ask unit must paper prints. Could be HR = 3.08 (unit maybe \"HR\" or perhaps unitless?). Need report headline number only. We need exact contiguous quote containing number and attribution clause. Likely parent_value 3.08, unit \"HR\", evidence exact quote: \"High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96)\" target_result maybe \"HR = 3.08\". But question says report headline number only: value paper itself states for registered target, not calculated etc. The schema includes target_result perhaps describe. Unit must be unit paper prints. Could say unit \"HR\" because printed. But perhaps unit is \"hazard ratio (HR)\"? They say unit must be unit paper prints, so likely \"HR\". Evidence exact contiguous quotation. Maybe target result should be \"HR = 3.08\". number_stated true.\n\nYet ambiguity: Main finding could be overexpression p &lt;0.001, or HR. The \"single numerical result\" a replication target has to reproduce perhaps likely paper has a specific target inferred from \"registered target: headline numerical result ... main finding.\" We need extract main headline numerical result. Abstract first results: KLRG2 significantly overexpressed p&lt;.001; high expression predicted OS HR=3.08 and PFI HR=1.98. Which one is headline? The primary survival result likely HR 3.08. Need select one number. Could unit perhaps \"hazard ratio\". They demand headline number only, likely don't include CI in parent value but evidence can include exact clause. The target_result can likely be \"3.08\". We should not report extra numeric details outside evidence? JSON evidence necessarily includes quote with CI, which has other numbers. They say headline number only, evidence exact quotation containing number. Exact full clause likely includes CI. That's okay, parent_value only headline.\n\nNeed ensure quote exact contiguous. \"High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96) and progression-free interval (HR = 1.98, 95% CI = 1.37–2.87).\" Since attribution attached by target names and if number tied target quote whole clause. Could quote only first clause ending at \")\"—is that contiguous and attribution checkable. Yes. They said do not shorten it perhaps means evidence quote must be exact contiguous quotation, don't truncate? \"The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it.\" Ambiguity \"do not shorten it\" perhaps quote entire relevant clause rather than just \"(HR = 3.08)\"? Better quote full sentence including both OS and PFI? They say attribution may be carried by text wording; when linked, quote whole clause so reader can check. We could quote sentence through progression-free interval, which includes extra number. But \"headline number only\" refers reported number not evidence. Exact full sentence safest. Yet perhaps \"do not shorten it\" says don't shorten quotation, but source itself no designated quote. Usually extract evidence as exact quote. Full sentence ideal.\n\nUnit: paper prints \"HR\", so use \"HR\". target_result perhaps \"HR = 3.08\". Could mention no other prose. JSON valid with Unicode. Let's formulate:\n\n{\n \"parent_value\": 3.08,\n \"unit\":\"HR\",\n \"evidence\":\"High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96) and progression-free interval (HR = 1.98, 95% CI = 1.37–2.87).\",\n \"target_result\":\"HR = 3.08\",\n \"number_stated\":true\n}\n\nIs HR a unit? They might expect \"hazard ratio\" as unit. User says unit paper prints. It prints \"HR =\". Unit perhaps \"HR\". In extraction tasks, parent_value likely numeric, unit exact. Could be unit \"HR\". Good.\n\nBut let's carefully inspect possibility \"headline numerical result\" refers 223 DEGs? No, main finding in title and abstract. They may be testing extraction from paper text with a registered target deliberately generic. Need determine what \"paper itself states for registered target\" means. It asks \"find the single numerical result that a replication of the registered target has to reproduce.\" Target: headline numerical result the paper states for its main finding. The paper is likely synthetic abstract with headline HR 3.08. Could be p &lt;0.001, but less replicable? \"headline numerical result\" likely a benchmark target from source. The prominent result is HR = 3.08. Let's think if unit should be \"95% CI\" no.\n\nCould target result be \"3.08\" only and unit \"HR\"? \"Report the headline number only: the value ...\". target_result perhaps should describe result, perhaps they want \"High KLRG2 expression independently predicted worse overall survival (HR = 3.08...)\" But schema wants target_result string and evidence string separately. Usually output target_result might be e.g. \"HR = 3.08\". That's okay.\n\nNeed JSON no markdown.</think>\n\n{\"parent_value\":3.08,\"unit\":\"HR\",\"evidence\":\"High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96) and progression-free interval (HR = 1.98, 95% CI = 1.37–2.87).\",\"target_result\":\"HR = 3.08\",\"number_stated\":true}", "reading": {"parent_value": 3.08, "unit": "HR", "evidence": "High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96) and progression-free interval (HR = 1.98, 95% CI = 1.37–2.87).", "target_result": "HR = 3.08", "number_stated": true, "source_locator": "chars 1208-1371 of source sha256 bf25043efcea70a8d90c51fb7acd28283a3c684710dd508a4885c068704ada54"}, "recorded_at": "2026-10-31T15:23:39.293882+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96) and progression-free interval (HR = 1.98, 95% CI = 1.37–2.87).", "minimax_alt": "High KLRG2 expression independently predicted worse overall survival (HR = 3.08, 95% CI = 1.92–4.96)", "decisive": false}, "physical_methods": {"minimax": ["Immunohistochemistry", "Quantitative real-time PCR (qRT-PCR)"], "minimax_alt": ["qRT-PCR validation using 14 endometrial carcinoma tissues and 14 proliferative-phase endometrial controls", "Immunohistochemistry"], "decisive": false}, "analysis_methods": {"minimax": ["Cox proportional hazards regression with multivariable adjustment", "Kaplan–Meier survival curves compared by log-rank test", "Time-dependent ROC analysis", "Univariate and multivariate logistic regression", "Shapiro–Wilk test", "Unpaired Student's t-test", "Mann–Whitney U test", "Paired t-test", "Wilcoxon signed-rank test", "Chi-square test with Yates' continuity correction", "ROC curve analysis with DeLong's variance estimation", "Inverse probability of censoring weighting", "Differential expression analysis", "Gene Ontology enrichment analysis", "KEGG pathway analysis", "Gene Set Enrichment Analysis (GSEA)", "Spearman correlation analysis"], "minimax_alt": ["Cox proportional hazards regression with multivariable adjustment", "Kaplan–Meier curves with log-rank test", "Time-dependent ROC analysis", "Proportional-hazards assessment using Schoenfeld residuals"], "decisive": false}, "statistical_method": {"minimax": "Cox proportional hazards regression with multivariable adjustment for predefined clinical covariates", "minimax_alt": "Cox proportional hazards regression with multivariable adjustment", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:3d37c1804330551571b77dcfc373c39cebb8e69a3febb36a6c0044f2f5319bcb", "type": "sep_package", "label": "SEP v1 package for pmid:40722666"}], "activities": [{"id": "activity:conversion:pmid:40722666", "type": "conversion", "used": ["package:3d37c1804330551571b77dcfc373c39cebb8e69a3febb36a6c0044f2f5319bcb"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "4a9cbb1c-d2ef-4ed0-bae2-856d59753c4b", "parent_hash": "3d37c1804330551571b77dcfc373c39cebb8e69a3febb36a6c0044f2f5319bcb", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40722666 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40722666' does not resolve to a declared asset", "targets"]},"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":"2026-11-04T03:12:18+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}}}