{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40873580", "kind": "science-record", "revision": 1, "content_hash": "sha256:49f9e47b2d844116fa055cf9e7d8401938a09efbcc01e5ee39df3709710677ea", "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": "Identification of the prognostic effect of mitophagy-related genes in acute myeloid leukemia.", "doi": "10.3389/fimmu.2025.1580597", "pmid": "40873580", "authors": null, "journal": "Frontiers in immunology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "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:40873580"], "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:40873580", "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:40873580' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40873580", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2025.1580597", "sha256": "sha256:c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2025.1580597", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40873580 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:40873580"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40873580"]}, "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": "d7dcd2ddffcdbbda54223fdca6065927230e1ea86bdbce4b62f8484826596618", "source_hash": "c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398", "raw_response_sha256": "sha256:26e80e78afe75c77cb4caf17f87ea6c0431f461417b841b1198e9b8f987ab967", "raw_response_chars": 5960}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "cdc39688c6db38d9291e8209732ed402506be6a4aee9b92eee2deb102112cf26", "source_hash": "c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398", "raw_response_sha256": "sha256:796128d08d2c6706c4f4537b60d48b345e1bc3fc039b8e8a1d866c20827e29ca", "raw_response_chars": 64676}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "0e67e6954c6a8c00d7719655d3fccf56655b2b372368b5ebe614bf84b23be25d", "source_hash": "c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398", "raw_response": "{\"parent_value\":5,\"unit\":\"genes\",\"evidence\":\"Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model that stratified patients into high- and low-risk groups with significantly different overall survival.\",\"target_result\":\"The paper identifies five mitophagy-related genes as prognostic biomarkers in AML.\",\"number_stated\":true}", "reading": {"parent_value": 5, "unit": "genes", "evidence": "Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model that stratified patients into high- and low-risk groups with significantly different overall survival.", "target_result": "The paper identifies five mitophagy-related genes as prognostic biomarkers in AML.", "number_stated": true, "source_locator": "chars 1204-1409 of source sha256 c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398"}, "recorded_at": "2026-10-31T15:32:46.189603+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "286bedbeb4dacd1b09426e0168b44b644b0ee0395b4b1846c2932b414ceb4c33", "source_hash": "c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline main finding registered target. Paper text. Main finding: five MRG-associated genes selected prognostic model. Headline numerical result likely 5 genes. Need exact contiguous quote contains number and attribution. \"Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model...\" Number word Five, parent_value numeric 5, unit perhaps \"genes\" or maybe \"MRG-associated genes\". User says unit paper prints. They ask headline number only, value paper itself states, not calculated. Evidence exact contiguous quotation. If textual number \"Five\", parent_value schema number 5. Unit paper prints maybe \"MRG-associated genes\" or \"genes\". Need determine likely expected. Main finding perhaps \"five mitophagy-related genes as prognostic biomarkers\". Registered target \"the headline numerical result the paper states for its main finding\" clearly number five genes. Need quote whole clause. Could use conclusion exact: \"This study identified five mitophagy-related genes as prognostic biomarkers in AML and developed a robust risk model that correlates with survival outcome, immune infiltration, and drug sensitivity.\" This directly attaches five to genes/main finding. Unit \"mitophagy-related genes\" perhaps paper's unit. They say unit must be unit paper prints. Usually JSON tasks numerical result extraction: parent_value, unit. Could set unit \"genes\" because printed noun. Evidence exact sentence. target_result perhaps describe \"Five mitophagy-related genes were identified as prognostic biomarkers in AML.\" But \"Report headline number only\" likely target_result should concise. Must include evidence despite \"headline number only\" schema. number_stated true.\n\nCould unit be \"prognostic biomarkers\" rather than genes? Main result is five genes, unit genes. Exact quote: \"Five prognostic biomarkers—ITGB2, VIP, PTK2, FHL2, and BAG3—were identified and integrated into a novel risk model...\" This says five biomarkers. Better direct headline. Number is word not digit. They say numerical result, paper states \"Five\". parent_value 5 is conversion? They demand not value you calculated, converted. Reporting word Five as numeric 5 is normalization, surely allowed, schema number. Evidence contains word Five. Unit perhaps \"prognostic biomarkers\". They may expect \"genes\" based abstract. Let's parse wording: \"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.\" Target is headline numerical result main finding. Source likely perhaps extraction task where parent_value numerical count. Need output number. \"Five MRG-associated genes ... selected\". Unit likely \"MRG-associated genes\" or simply \"genes\". The source prints \"genes\". We should avoid overcomplication.\n\nEvidence must exact contiguous quotation and not shortened. Could quote sentence exactly. Evidence: \"Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model that stratified patients into high- and low-risk groups with significantly different overall survival.\" This exact contiguous sentence. This directly attributes number to genes. target_result perhaps \"5 MRG-associated genes were selected to construct the prognostic risk model.\" Is that headline number only? They explicitly \"Report the headline number only\" perhaps target_result should just state \"Five MRG-associated genes\". Schema asks target_result, likely concise natural language.\n\nNeed JSON valid. Ensure unit maybe \"MRG-associated genes\". Is unit supposed singular measurement unit? I'd use \"genes\" because numerical unit. But perhaps exact printed phrase needed. The unit paper prints is \"MRG-associated genes\", not merely \"genes\"? It prints the phrase. User says \"The unit must be the unit the paper prints.\" In extraction tasks, if count of genes, unit \"genes\". Let's formulate.\n\nCould main finding instead be \"72 MRGs analyzed\", \"five genes\", \"26 DEGs\", \"731 pathways\", \"84 compounds\". Main conclusion emphasizes five. Registered target broad; likely five genes. Headline numerical result. Answer.\n\nNeed only JSON no markdown.</think>\n\n{\"parent_value\":5,\"unit\":\"MRG-associated genes\",\"evidence\":\"Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model that stratified patients into high- and low-risk groups with significantly different overall survival.\",\"target_result\":\"Five MRG-associated genes were selected to construct the prognostic model.\",\"number_stated\":true}", "reading": {"parent_value": 5, "unit": "MRG-associated genes", "evidence": "Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model that stratified patients into high- and low-risk groups with significantly different overall survival.", "target_result": "Five MRG-associated genes were selected to construct the prognostic model.", "number_stated": true, "source_locator": "chars 1204-1409 of source sha256 c3a39adb85eee652e4c8d1145755fecccf7d01e4e041dc6daeff5ae1ac88a398"}, "recorded_at": "2026-10-31T15:32:51.026787+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, and BAG3) were selected to construct a prognostic model that stratified AML patients into high- and low-risk groups with significantly different overall survival.", "minimax_alt": "Five MRG-associated genes (ITGB2, VIP, PTK2, FHL2, BAG3) were selected to construct a prognostic model that stratified patients into high- and low-risk groups with significantly different overall survival.", "decisive": false}, "analysis_methods": {"minimax": ["Univariate Cox regression analysis", "Least absolute shrinkage and selection operator (Lasso) regression", "Multivariate Cox regression analysis", "Kaplan-Meier survival analysis", "Nomogram construction and validation", "Time-dependent ROC analysis", "Gene set enrichment analysis", "CIBERSORT immune cell infiltration analysis", "Wilcoxon signed-rank test", "Spearman correlation analysis", "pRRophetic drug sensitivity prediction", "Consensus clustering", "Differential expression analysis"], "minimax_alt": ["consensus clustering based on MRG expression", "differential expression analysis using limma and DESeq2", "univariate Cox regression", "least absolute shrinkage and selection operator (Lasso) regression", "Kaplan-Meier (K-M) survival analysis", "proportional hazards assumption testing", "multivariate Cox regression", "nomogram development", "calibration plots", "time-dependent ROC curves", "chi-square tests"], "decisive": false}, "statistical_method": {"minimax": "Univariate Cox regression and least absolute shrinkage and selection operator (Lasso) regression were used to screen prognostic genes, followed by multivariate Cox regression to identify independent prognostic indicators.", "minimax_alt": "univariate Cox regression and least absolute shrinkage and selection operator (Lasso) regression analyses", "decisive": true}, "unit": {"minimax": "genes", "minimax_alt": "MRG-associated genes", "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:a4e0aca4bd91ad4687e63baa11c5ca0adea2f5aa4ab186cc97c2a23414685dcc", "type": "sep_package", "label": "SEP v1 package for pmid:40873580"}], "activities": [{"id": "activity:conversion:pmid:40873580", "type": "conversion", "used": ["package:a4e0aca4bd91ad4687e63baa11c5ca0adea2f5aa4ab186cc97c2a23414685dcc"], "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": "c030ffae-7e25-4cdb-b5d4-ad4f98e3f24a", "parent_hash": "a4e0aca4bd91ad4687e63baa11c5ca0adea2f5aa4ab186cc97c2a23414685dcc", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40873580 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:40873580' 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":"2026-11-04T00:32:31+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}}}