{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39955536", "kind": "science-record", "revision": 1, "content_hash": "sha256:08f5334626873becd742de78c638eb35817e013d9f83bed3da18aba3d95680a9", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T10:25:49Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia.", "doi": "10.1186/s12885-025-13658-3", "pmid": "39955536", "authors": null, "journal": "BMC cancer", "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": 13.0, "unit": "cell death patterns", "tolerance": null, "source": "chars 0-165 of source sha256 5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3"}, "evidence": [{"asset": "source:pmid:39955536", "locator": "chars 0-165 of source sha256 5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3", "quote": "Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia"}]}], "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:39955536"], "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:39955536", "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:39955536' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39955536", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-025-13658-3", "sha256": "sha256:5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-025-13658-3", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:39955536 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:39955536"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39955536"]}, "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": "f1af013edc9b167c461014eb0ae8ca40bf6e5ed4843b7d4e38bc08fce72cd706", "source_hash": "5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3", "raw_response_sha256": "sha256:3f795ef154ce7430db59db1a729d500cd4436fabdcbe626c607a13097da0483e", "raw_response_chars": 5126}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "b7542e5ba3e983aa304a77a31334d692c5395cfc7bfce0aaa48c15e2cac90ffc", "source_hash": "5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3", "raw_response_sha256": "sha256:1cb59a00371789c70ff4328ecb27068932ac6ad02dc8d7e97b295d95d0322404", "raw_response_chars": 59485}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "2a73c6f1184dcaac11e8f15d45ce1c15ccb338b0e4fa05e23e665c96fdb439aa", "source_hash": "5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3", "raw_response": "{\"parent_value\":13,\"unit\":\"cell death patterns\",\"evidence\":\"Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia\",\"target_result\":\"The paper states a prognostic signature comprising 13 cell death patterns.\",\"number_stated\":true}", "reading": {"parent_value": 13, "unit": "cell death patterns", "evidence": "Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia", "target_result": "The paper states a prognostic signature comprising 13 cell death patterns.", "number_stated": true, "source_locator": "chars 0-165 of source sha256 5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3"}, "recorded_at": "2026-10-31T15:29:46.032578+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "38612579785e059a6933f43db67249cf3eb43468141a83fa789cd3929d8e0704", "source_hash": "5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3", "raw_response": "<think>We need answer JSON only. Need interpret \"single numerical result that a replication of registered target has to reproduce. headline number only: value paper itself states for registered target, not calculated/converted/averaged/reconstructed. Unit paper prints. Evidence exact contiguous quote containing number. Attribution may via parenthetical list, respectively, or words naming target. Target: headline numerical result paper states for main finding.\"\n\nWe need identify headline numerical result. Source abstract/results. Potential numbers: 13 cell death patterns, 1394 genes, 101 models, ten algorithms, 214 upregulated, 39 prognostic, AUC ≥0.7. Which is \"headline numerical result\" perhaps title says prognostic signature of 13 cell death patterns. Main finding likely \"13 cell death patterns\" (headline numerical result), title exact. They ask \"the headline numerical result the paper itself states for its registered target\" perhaps benchmark extraction task where target broad \"headline numerical result the paper states for its main finding\". Need select single number likely 13 cell death patterns, unit maybe \"cell death patterns\". Need carefully parse.\n\nPaper title: \"Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia\". Headline number likely 13 cell death patterns. But replication must reproduce perhaps main finding \"13 different PCD pathways\" examined. They may expect 13? Let's understand task framing. \"Read supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints.\" This is likely asking extract \"headline number\" from paper, registered target is description. Could be abstract's key result number, perhaps AUC values ≥ 0.7. We need infer exact intended.\n\nThey explicitly define target as \"the headline numerical result the paper states for its main finding.\" This could be a general extraction where find key quantitative finding, not necessarily title. Candidate:\n- 13 cell death patterns (title, also abstract)\n- 1394 genes representing 13 pathways examined\n- 214 upregulated genes, 39 prognostic\n- 101 models, 10 algorithms\n- AUC ≥0.7\nNo single primary performance metric (C-index values omitted). Which number is \"headline numerical result\"? Title likely gives 13. Since title says \"prognostic signature of 13 cell death patterns\" and target main finding likely this. Unit \"cell death patterns\". Evidence exact contiguous quote containing number and attribution. Could quote title exactly: \"Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia\". parent_value 13, unit \"cell death patterns\". target_result maybe concise \"The prognostic signature comprises 13 cell death patterns.\" Evidence whole title. number_stated true.\n\nNeed ensure \"headline number only\" perhaps they want \"13\" and unit \"PCD pathways.\" They insist unit paper prints. Title prints \"cell death patterns.\" If use abstract: \"A total of 1394 genes representing 13 different PCD pathways were examined...\" But that number is genes examined, not signature number. The title directly attaches 13 to cell death patterns, best evidence.\n\nCould there be a hidden expectation of \"39\" as main finding? Let's investigate. Main study finding is prognostic signature of 13 cell death patterns. The \"headline numerical result\" likely title metric. Prompt perhaps generated around \"registered target\" from some paper replication benchmark, asks identify single numerical result. They intentionally say \"the value the paper itself states for the registered target\" and target description vague. Need determine most salient number.\n\nTitle includes \"13 cell death patterns\". Abstract first line includes 1394 genes representing 13 pathways, then 214, 39, 101, ten, AUC. Among these, title's 13 likely \"headline.\" Word \"headline\" might literally mean in title/headline. Also registered target says main finding; title's main finding exactly \"a prognostic signature of 13 cell death patterns\". So yes.\n\nNeed output valid JSON, no markdown. Parent value number 13. unit perhaps \"cell death patterns\" exactly. evidence exact contiguous source quote. target_result maybe \"The paper states that its prognostic signature comprises 13 cell death patterns.\" Ensure evidence exact quote: source title exact. Could quote full title. They say \"do not shorten it\" likely quote whole clause where target attached, perhaps exact title. Use full title as evidence.\n\nQuestion: \"Report the headline number only\" Could target_result perhaps just number? But schema includes target_result string. We can say \"13 cell death patterns\". Unit \"cell death patterns\". Evidence full title. Is \"pattern\" count considered unit? Yes.</think>\n\n{\"parent_value\":13,\"unit\":\"cell death patterns\",\"evidence\":\"Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia\",\"target_result\":\"The prognostic signature comprises 13 cell death patterns.\",\"number_stated\":true}", "reading": {"parent_value": 13, "unit": "cell death patterns", "evidence": "Machine learning-based bulk RNA analysis reveals a prognostic signature of 13 cell death patterns and potential therapeutic target of SMAD3 in acute myeloid leukemia", "target_result": "The prognostic signature comprises 13 cell death patterns.", "number_stated": true, "source_locator": "chars 0-165 of source sha256 5267ca5dd4599ec7991507f7cde8591334079cddb8daa242330f39c203de4cd3"}, "recorded_at": "2026-10-31T15:29:52.573271+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The PCD index and prognostic nomogram predicted overall survival in AML with satisfactory predictive power (AUC values ≥ 0.7).", "minimax_alt": "An AML prognostic signature comprising 13 programmed cell death patterns, with a validated nomogram showing AUC values ≥ 0.7 and SMAD3 identified as a potential therapeutic target.", "decisive": false}, "physical_methods": {"minimax": ["In vitro validation of SMAD3 expression", "Treatment with the SMAD3 inhibitor SIS3 as monotherapy and in combination", "Assessment of autophagy-related marker LC3 expression"], "minimax_alt": ["In vitro validation of SMAD3 expression.", "Assessment of AML-cell sensitivity to the SMAD3 inhibitor SIS3.", "Assessment of LC3 expression after SIS3 monotherapy and combined treatment in KMT2A-rearranged cell lines."], "decisive": false}, "analysis_methods": {"minimax": ["Integrated construction of 101 models based on ten machine learning algorithms", "Evaluation of models using the average C-index and number of model genes", "Gene Ontology enrichment analysis", "KEGG enrichment analysis", "Gene set enrichment analysis (GSEA)", "Fisher’s exact test", "Chi-square test", "Wilcoxon rank-sum test", "T test", "Pearson correlation", "Spearman correlation", "Kaplan-Meier analysis", "Cox regression"], "minimax_alt": ["Bulk RNA transcriptome analysis of PCD-related genes.", "Individual prediction of overall survival for upregulated PCD-related genes.", "Integrated machine-learning modelling with 101 models based on ten machine-learning algorithms.", "PCD-index development based on the average C-index and number of model genes identified from machine-learning combinations.", "Prognostic nomogram development and validation using the PCD index, age and ELN risk stratification.", "GO and KEGG enrichment analysis and gene set enrichment analysis.", "Mutation-profile comparison using Fisher’s exact test.", "Kaplan–Meier and Cox regression analyses.", "Pearson and Spearman correlation analyses."], "decisive": false}, "statistical_method": {"minimax": "Kaplan-Meier and Cox regression analyses", "minimax_alt": "Integrated machine-learning modelling consisting of 101 models based on ten machine-learning algorithms.", "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:d1c5583c73e782e92d55a99772de35feb88dba07139279e8c6a9b5752bb5b8de", "type": "sep_package", "label": "SEP v1 package for pmid:39955536"}], "activities": [{"id": "activity:conversion:pmid:39955536", "type": "conversion", "used": ["package:d1c5583c73e782e92d55a99772de35feb88dba07139279e8c6a9b5752bb5b8de"], "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": "428d16cf-f2e3-4f3e-8319-9c2d58f8f02f", "parent_hash": "d1c5583c73e782e92d55a99772de35feb88dba07139279e8c6a9b5752bb5b8de", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:39955536 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:39955536' 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":"2026-11-04T02:52:06+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}}}