{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41523911", "kind": "science-record", "revision": 1, "content_hash": "sha256:da5911c7db43a1ab0316a293d981fe72bacc9cb7652498f8d413a99eccf6d931", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T10:25:54Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Itaconate-Related Gene Signatures as Prognostic Markers in Colon Cancer: Insights From Transcriptomic and Spatial Analysis.", "doi": "10.1155/humu/7928082", "pmid": "41523911", "authors": null, "journal": "Human mutation", "year": 2026, "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:41523911"], "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:41523911", "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:41523911' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41523911", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/humu/7928082", "sha256": "sha256:06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/humu/7928082", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:41523911 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:41523911"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41523911"]}, "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": "30aefe6cfc2007a598e84b81324d8936387c253787e99a88080e0685951a5a83", "source_hash": "06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4", "raw_response_sha256": "sha256:c628e848082a0b6bb630fac041fade6c58c8d248aa3f0f57cb817d5dddfb0dd8", "raw_response_chars": 4075}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "12408c44cf5686c7ebdb4b5048344d838db2f93e1fe3a7dee5662e92ee0809c4", "source_hash": "06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4", "raw_response_sha256": "sha256:0847aac922bf764ac078ea36b467faa725b422c0e84cf89f4b439469129d17ef", "raw_response_chars": 50787}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "db102302a9e9d179fc8c2d05923ab98db2051e4b8105a967dede4f995db24957", "source_hash": "06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4", "raw_response": "{\"parent_value\":0.7,\"unit\":\"C-index\",\"evidence\":\"The optimal prognostic prediction model (Enet [alpha = 0.2]) was constructed and validated, which showed good prognostic predictive value in both the training and validation sets (average C‐index > 0.7) and was superior to previous conventional clinical features and 22 prognostic models developed by researchers in the past 4 years.\",\"target_result\":\"The optimal prognostic prediction model achieved an average C-index greater than 0.7 in the training and validation sets.\",\"number_stated\":true}", "reading": {"parent_value": 0.7, "unit": "C-index", "evidence": "The optimal prognostic prediction model (Enet [alpha = 0.2]) was constructed and validated, which showed good prognostic predictive value in both the training and validation sets (average C‐index > 0.7) and was superior to previous conventional clinical features and 22 prognostic models developed by researchers in the past 4 years.", "target_result": "The optimal prognostic prediction model achieved an average C-index greater than 0.7 in the training and validation sets.", "number_stated": true, "source_locator": "chars 957-1290 of source sha256 06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4"}, "recorded_at": "2026-10-31T15:16:44.637753+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "03043bb822ec6b80fa3c96cd397fac2c628ac3c8e5fd8232837a5e4a0e4f8bc9", "source_hash": "06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4", "raw_response": "<think>We need answer JSON object. Need interpret \"single numerical result that replication registered target has to reproduce. Headline number only: value paper itself states for registered target, main finding.\" Source likely abstract headline numerical result: average C-index &gt; 0.7? Need identify exact headline numerical result. Could be \"10 prognosis-related genes\", \"average C-index &gt; 0.7\". Registered target vague \"the headline numerical result the paper states for its main finding\". Need infer intended target perhaps \"average C-index &gt; 0.7\" because model performance headline result. Need report number, unit paper prints. They require parent_value number, unit string. What is number? 0.7, unit perhaps \"C-index\" or maybe \"&gt; 0.7\" unit? Exact evidence contiguous quote containing number, whole clause attribution. Need target_result perhaps describe.\n\nLet's parse task wording. \"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 likely benchmark asks extract one key number associated with registered target. Here registered target generic headline numerical result. Paper abstract reports many numbers: 448 patients, 7 models, 1473 cases, 10 genes, alpha .2, average C-index &gt; .7, 22 models, 4 years. Main finding's headline performance number likely C-index &gt; 0.7. \"unit must be unit paper prints\" likely unit might \"C-index\" but C-index dimensionless. Could say \"C-index &gt; 0.7\". parent_value 0.7, unit \"C-index\". Evidence exact contiguous quote perhaps \"The optimal prognostic prediction model (Enet [alpha = 0.2]) was constructed and validated, which showed good prognostic predictive value in both the training and validation sets (average C‐index &gt; 0.7) and was superior to previous conventional clinical features and 22 prognostic models developed by researchers in the past 4 years.\" This is whole sentence/clause and attribution. They ask \"headline number only.\" Evidence can quote whole clause. target_result maybe \"average C-index &gt; 0.7\". Need JSON valid, unicode hyphen exact? Use C‐index with U+2010? Source uses nonbreaking hyphen perhaps \"C‐index\" U+2010. Evidence exact. Unit \"C-index\" maybe paper prints \"C‐index\". Since exact unit printed, use \"C‐index\". Parent_value must number 0.7. target_result perhaps \"average C‐index > 0.7\". number_stated true.\n\nBut let's carefully consider possibility intended numerical result is \"10 prognosis-related genes\" or sample size. The registered target says \"the headline numerical result the paper states for its main finding\" rather than naming metric. Maybe task designed to identify headline abstract finding. Could be one number: 10 genes? Let's examine title and abstract: study comprehensively analyzes expression/biology/prognosis; through screening, 10 genes selected; optimal model, average C-index > 0.7. \"Headline numerical result\" generally result metric is C-index > .7. They ask \"unit must be the unit the paper prints,\" suggesting performance measure with unit perhaps C-index. Need only one numerical result. Could be \"average C-index > 0.7\" certainly replication target.\n\nCould parent_value need 0.7 despite >. Since JSON number no comparator. target_result preserves >. unit maybe \"C-index\". Evidence exact quotation. We can quote sentence. Exact contiguous from source. Ensure no inadvertent changes. Source: \"The optimal prognostic prediction model (Enet [alpha = 0.2]) was constructed and validated, which showed good prognostic predictive value in both the training and validation sets (average C‐index > 0.7) and was superior to previous conventional clinical features and 22 prognostic models developed by researchers in the past 4 years.\" We could evidence only clause \"(average C‐index > 0.7)\" but attribution to model requires surrounding clause. Instructions: \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" So whole sentence is safest. \"Evidence must be exact, contiguous quotation.\" We can quote exactly. target_result could be \"average C‐index > 0.7\". Is target_result supposed plain text. Unit perhaps \"C‐index\" (dimensionless). Maybe unit empty because C-index is unitless? Yet schema says unit string. They demand \"unit must be the unit the paper prints.\" If paper prints C-index as metric, call it unit. Could use \"C‐index\". Parent_value 0.7.\n\nNeed no markdown, just JSON. Ensure JSON valid Unicode.</think>\n\n{\"parent_value\":0.7,\"unit\":\"C‐index\",\"evidence\":\"The optimal prognostic prediction model (Enet [alpha = 0.2]) was constructed and validated, which showed good prognostic predictive value in both the training and validation sets (average C‐index > 0.7) and was superior to previous conventional clinical features and 22 prognostic models developed by researchers in the past 4 years.\",\"target_result\":\"average C‐index > 0.7\",\"number_stated\":true}", "reading": {"parent_value": 0.7, "unit": "C‐index", "evidence": "The optimal prognostic prediction model (Enet [alpha = 0.2]) was constructed and validated, which showed good prognostic predictive value in both the training and validation sets (average C‐index > 0.7) and was superior to previous conventional clinical features and 22 prognostic models developed by researchers in the past 4 years.", "target_result": "average C‐index > 0.7", "number_stated": true, "source_locator": "chars 957-1290 of source sha256 06f4b51dc4b71760f8a37018023331aace1391b3d2ee7fc866b579dec8b6d6d4"}, "recorded_at": "2026-10-31T15:16:50.916931+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The Enet (alpha = 0.2) prognostic model achieved an average C-index > 0.7 in the training and validation sets.", "minimax_alt": "The Enet [alpha = 0.2] prognostic prediction model achieved an average C‐index > 0.7 in the training and validation sets, comprising 448 TCGA training patients and 1473 GEO validation cases.", "decisive": false}, "work_type": {"minimax": "analysis_only_for_target", "minimax_alt": "analysis_plus_physical_validation", "decisive": true}, "physical_methods": {"minimax": [], "minimax_alt": ["Tissue microarray (TMA)"], "decisive": false}, "analysis_methods": {"minimax": ["Enet (elastic net) prognostic prediction model with alpha = 0.2", "C-index evaluation", "Univariate and multivariate survival analysis", "Gene Set Enrichment Analysis (GSEA)", "CIBERSORT", "TIMER", "MCPcounter", "ESTIMATE"], "minimax_alt": ["Enet [alpha = 0.2]", "Seurat package (v4.3.0)", "AUCell package (v1.16.0)", "Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses", "CARD algorithm (v0.1.0)", "Gene Set Enrichment Analysis (GSEA, v4.3.2)", "CIBERSORT (v1.06)", "TIMER (v2.0)", "MCPcounter (v1.2.0)", "ESTIMATE (v1.0.13)", "maftools package (v2.14.0)", "CellChat package (v1.5.0)"], "decisive": false}, "statistical_method": {"minimax": "Enet (alpha = 0.2)", "minimax_alt": "Enet [alpha = 0.2]", "decisive": true}, "unit": {"minimax": "C-index", "minimax_alt": "C‐index", "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:4c9a8a1940e0fa378100213d3db83ed91923300d2dfe5e7e1b0a5ce764e5753d", "type": "sep_package", "label": "SEP v1 package for pmid:41523911"}], "activities": [{"id": "activity:conversion:pmid:41523911", "type": "conversion", "used": ["package:4c9a8a1940e0fa378100213d3db83ed91923300d2dfe5e7e1b0a5ce764e5753d"], "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": "e8738768-4fe4-49c6-a9d8-7eb3852a5e46", "parent_hash": "4c9a8a1940e0fa378100213d3db83ed91923300d2dfe5e7e1b0a5ce764e5753d", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:41523911 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:41523911' 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":"2026-11-04T02:59:58+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}}}