{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40715243", "kind": "science-record", "revision": 1, "content_hash": "sha256:974be838cc872a47c01092bcb04f2983a6cc257783356d770ddc73f34773ae35", "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": "A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness.", "doi": "10.1038/s41598-025-11704-5", "pmid": "40715243", "authors": null, "journal": "Scientific reports", "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": 5.0, "unit": "protein kinases", "tolerance": null, "source": "chars 0-104 of source sha256 6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795"}, "evidence": [{"asset": "source:pmid:40715243", "locator": "chars 0-104 of source sha256 6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795", "quote": "A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness"}]}], "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:40715243"], "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:40715243", "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:40715243' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40715243", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-11704-5", "sha256": "sha256:6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-11704-5", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40715243 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:40715243"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40715243"]}, "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": "5df9614e4a8dcc9ded0c7df0086c3802685fbdd499fedbdee34eac6318520e12", "source_hash": "6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795", "raw_response_sha256": "sha256:0102b427a09d1913053cf9a2e8fa103795b38e4990cb91e69781a304470af344", "raw_response_chars": 5071}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "69254dafb97966665d9afa734f2be552a9f51241bd162b76de5a9f38f1cdc115", "source_hash": "6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795", "raw_response_sha256": "sha256:4dd7d682349061e259304553c2e54307e42664fee3332e172dcc3e28212e7b42", "raw_response_chars": 64067}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "012081f3d75d04ad2e06337de9fedd3700555dcdd2ef1cceeb2213d727ea1226", "source_hash": "6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795", "raw_response": "{\"parent_value\":5,\"unit\":\"protein kinases\",\"evidence\":\"A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\",\"target_result\":\"A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\",\"number_stated\":true}", "reading": {"parent_value": 5, "unit": "protein kinases", "evidence": "A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness", "target_result": "A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness", "number_stated": true, "source_locator": "chars 0-104 of source sha256 6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795"}, "recorded_at": "2026-10-31T15:23:17.912406+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "ebd1a7b0cff9088ddaef1e5b7a15fc4f58651e7f22d75c4cf41d59eda125cb9d", "source_hash": "6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states for main finding. Source supplied limited abstract/methods/results start. Main finding likely 5-protein kinase risk signature? Headline number perhaps 5 proteins? They ask \"value paper itself states for registered target, not calculated...\" Registered target headline numerical result for main finding. In title/abstract: \"novel 5-protein kinase risk signature\". Is that the numerical result? Maybe main finding headline numerical result could be 29 dysregulated kinases? Need infer expected extraction. Need report headline number only, unit paper prints, exact contiguous quote. They emphasize target main finding. Source text title says \"A novel 5-protein kinase risk signature...\" and abstract concludes signature. This likely registered target numerical result = 5 proteins. Unit \"protein kinases\"? Need evidence exact quote containing number, perhaps \"we developed a novel protein kinase prognostic risk signature comprising CAMKK2, PAK1, AK5, WEE1, and CDK4\" no number explicit. Title has \"5-protein kinase risk signature\". Exact quote. parent_value 5, unit perhaps \"protein kinases\" but title prints \"5-protein kinase\" (unit could \"protein kinases\" or \"protein kinase risk signature\"? Prompt unit must unit paper prints. Numerical headline result maybe five-protein signature. Evidence \"A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\" exact contiguous. target_result perhaps \"A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\". Number stated true.\n\nBut let's carefully parse request. \"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.\" REGISTERED TARGET: \"the headline numerical result the paper states for its main finding\". Likely ask extract headline result perhaps signature consists 5 proteins. Main numerical finding could be 29 differentially expressed kinases, but headline paper finding is novel 5-protein kinase risk signature. Need choose one. They want \"headline number only\". So 5 likely.\n\nNeed JSON fields:\nparent_value: 5\nunit: maybe \"protein kinases\" (paper prints \"5-protein kinase risk signature\"; if unit asked unit paper prints, could be \"protein kinase risk signature\"). Usually extraction task has numeric result with unit. A count of proteins has unit \"protein kinases\" perhaps inferred wording from title. Exact quote contains 5. target_result can explain. They said report headline number only perhaps target_result succinct. Evidence exact contiguous quotation, no shortening. We can quote title entire. Need valid JSON no markdown.\n\nCould evidence be: \"we developed a novel protein kinase prognostic risk signature comprising CAMKK2, PAK1, AK5, WEE1, and CDK4\" lacks number and no shorten. Better title.\n\nDoes \"do not shorten it\" refer evidence exact quote, perhaps quote whole clause. The title itself exact. \"Attribution may be carried by text's own wording ... words that name target directly. When that is how text links them, quote whole clause\". Title names result directly. Evidence whole title.\n\nUnit should perhaps be \"protein kinase risk signature\" as count of proteins in signature. But they insist unit paper prints. The printed unit adjacent to 5 is \"protein kinase risk signature\", grammatically 5-protein kinase risk signature. Could set unit \"protein kinases\". Is \"protein kinases\" exact contiguous phrase? In title: \"5-protein kinase risk signature\", singular modifier \"protein kinase\", but body: \"novel protein kinase prognostic risk signature\". If unit is \"protein kinases\", paper does use phrase \"five protein kinases\" in abstract: \"Finally, we confirmed the protein expression of five protein kinases...\" That's spelled five, not numeric. Yet unit concept okay.\n\nMaybe target result is \"29\" dysregulated kinases? Let's investigate possibility based on typical benchmark prompts. They supply paper excerpts, registered target generic \"headline numerical result the paper states for its main finding.\" Could be asking identify one numerical result from text. There are many: 29, 1078, 1217, etc. Main finding headline numerical likely title \"novel 5-protein kinase risk signature\". This is explicitly title and core output. The abstract says identified 29 and developed signature comprising 5. \"headline numerical result\" means likely 5. They ask \"single numerical result that a replication ... has to reproduce\". Replication of main finding would reproduce the 5-protein signature, not count DEGs. Yes.\n\nNeed target_result maybe \"The paper states a novel 5-protein kinase risk signature.\" But \"report headline number only\" perhaps target_result should just characterize. Number field separate. Could set target_result \"A 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\". Unit \"protein kinases\". Evidence exact title.\n\nEnsure JSON number. Let's formulate.</think>\n\n{\"parent_value\":5,\"unit\":\"protein kinases\",\"evidence\":\"A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\",\"target_result\":\"A 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness\",\"number_stated\":true}", "reading": {"parent_value": 5, "unit": "protein kinases", "evidence": "A novel 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness", "target_result": "A 5-protein kinase risk signature for predicting glioma prognosis and immunotherapy responsiveness", "number_stated": true, "source_locator": "chars 0-104 of source sha256 6a43fc52837af72578bbb8a4a8044a8f80871fd1b5d68513fe6cc49b7262d795"}, "recorded_at": "2026-10-31T15:23:23.456305+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "29 differentially expressed protein kinases were identified, and a 5-protein kinase prognostic risk signature comprising CAMKK2, PAK1, AK5, WEE1, and CDK4 was developed.", "minimax_alt": "A novel 5-protein kinase prognostic risk signature comprising CAMKK2, PAK1, AK5, WEE1, and CDK4, selected after identification of 29 differentially expressed protein kinases.", "decisive": false}, "physical_methods": {"minimax": [], "minimax_alt": ["Confirmation of protein expression of five protein kinases in glioma samples and normal samples; the specific assay is not stated in the supplied text."], "decisive": false}, "analysis_methods": {"minimax": ["Differential gene expression analysis", "GO enrichment analysis", "KEGG enrichment analysis", "Spearman correlation analysis", "STRING interaction analysis", "Univariate Cox regression", "LASSO regression", "Multivariate Cox regression", "Kaplan–Meier analysis", "Nomogram construction", "Gene set enrichment analysis", "Immune cell infiltration analysis"], "minimax_alt": ["Differential gene expression analysis", "Univariate Cox regression", "LASSO regression", "Multivariate Cox regression", "Kaplan–Meier analysis", "Nomogram construction", "Spearman correlation analysis", "GO enrichment analysis", "KEG enrichment analysis", "Gene set enrichment analysis (GSEA)", "Student’s t-test", "Welch t’ test", "Wilcoxon rank sum test", "One-way ANOVA", "Kruskal–Wallis test"], "decisive": false}, "statistical_method": {"minimax": "Univariate Cox regression, LASSO regression, and multivariate Cox regression", "minimax_alt": "univariate Cox, LASSO, and multivariate Cox regression", "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:69d5584c41833de037f328c85a1c6185e33a24137daf9dc085f66ffd62a4b87d", "type": "sep_package", "label": "SEP v1 package for pmid:40715243"}], "activities": [{"id": "activity:conversion:pmid:40715243", "type": "conversion", "used": ["package:69d5584c41833de037f328c85a1c6185e33a24137daf9dc085f66ffd62a4b87d"], "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": "bc1f0804-f6cf-4776-b42e-e4078a7c089c", "parent_hash": "69d5584c41833de037f328c85a1c6185e33a24137daf9dc085f66ffd62a4b87d", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40715243 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:40715243' 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":"2026-11-04T02:13:25+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}}}