{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40916819", "kind": "science-record", "revision": 1, "content_hash": "sha256:45ee74c05e50c104b29161cdb519fb3a6a6268226a174fd3f77a6d9e0268b4f6", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T10:25:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "FTO-regulated m6A modification of pri-miR-139 represses papillary thyroid carcinoma metastasis.", "doi": "10.11817/j.issn.1672-7347.2025.250018", "pmid": "40916819", "authors": null, "journal": "Zhong nan da xue xue bao. Yi xue ban = Journal of Central South University. Medical sciences", "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:40916819"], "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:40916819", "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:40916819' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40916819", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.11817/j.issn.1672-7347.2025.250018", "sha256": "sha256:65fd8ebe404f1557eca0f3a9d381a59297e925b6a1a6ce1ee72709bb92e1f248", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.11817/j.issn.1672-7347.2025.250018", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40916819 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:40916819"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40916819"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "e24f94fc16b39653c56a9a7fefd9495b75432ba684e1e1e71083698bf77db310", "source_hash": "65fd8ebe404f1557eca0f3a9d381a59297e925b6a1a6ce1ee72709bb92e1f248", "raw_response_sha256": "sha256:58b344daa804a773a8a2f682f5a9ffb600c04b5ba60ef7e3d054c562c425c95e", "raw_response_chars": 2351}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "78ed9660f46552b388fcca1d939cdfb8797ae36a7be001553de775c09d17f3ad", "source_hash": "65fd8ebe404f1557eca0f3a9d381a59297e925b6a1a6ce1ee72709bb92e1f248", "raw_response_sha256": "sha256:5dc1a3fe44e4a0d098f577da6ceafa6556199cd8ec6558a75142f9b4da107f8b", "raw_response_chars": 47471}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "11941f42dab8c6dbbdc38e76956e226095c0d069defcfcb58a29e291230d9ac2", "source_hash": "65fd8ebe404f1557eca0f3a9d381a59297e925b6a1a6ce1ee72709bb92e1f248", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The paper states that circulating miR-139-5p could serve as a biological indicator for detecting PTC metastasis and that FTO affects miR-139-5p expression and function by regulating m6A modification of pri-miR-139, but it does not state a headline numerical result for the main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The paper states that circulating miR-139-5p could serve as a biological indicator for detecting PTC metastasis and that FTO affects miR-139-5p expression and function by regulating m6A modification of pri-miR-139, but it does not state a headline numerical result for the main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:34:08.556568+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "17bca913d4197286db1d1cd4dd7612bfd368b524e046804a8ea855d1a104e22f", "source_hash": "65fd8ebe404f1557eca0f3a9d381a59297e925b6a1a6ce1ee72709bb92e1f248", "raw_response": "<think>We need answer JSON only. Need interpret task. Need find single numerical result replication registered target headline numerical result paper states for main finding. Source text appears abstract no specific effect sizes/AUC etc. Numbers: 13,18 cohorts/sample counts, P<0.05, GSE130512. \"headline numerical result\" perhaps P<0.05 attached to findings. Need identify whether any numerical result for main finding. They want exact contiguous quote contains number. Registered target main finding headline numerical result. Source has \"(P<0.05)\" for FTO mechanism and MTT proliferation, not maybe main headline result? \"single numerical result that a replication ... has to reproduce.\" We should likely extract 0.05? Unit perhaps \"P\"?? But instruction unit must paper prints. Evidence exact quote. Parent_value numerical number. They explicitly says if text states no number for registered target, number_stated false, parent_value 0, unit/evidence empty, and say what text does state instead.\n\nNeed reason what \"registered target\" refers to: headline numerical result paper states for its main finding. The source only reports qualitative findings and p-values, not main quantitative result. Could say no headline numerical result. Yet perhaps 13 metastatic and 18 non-metastatic are sample sizes, not outcome numerical result. P<0.05 is a statistical threshold attached to finding, but not \"headline numerical result\" likely. They ask \"find the single numerical result ... report headline number only: value the paper itself states for registered target, not calculated...\" Often these tasks concern extracting a parent value from paper where headline metric in abstract/title perhaps e.g. \"AUC = 0.888\". Here source text doesn't provide. Need set false.\n\nNeed target_result describe what text states instead, likely circulating m6A-miR-139-5p could serve as biological indicator, and FTO inhibits pri-miR-139 processing by reducing methylation leading dysregulation. Since \"main finding\" headline perhaps \"serum circulating miR-139-5p can serve as biomarker for detecting PTC metastasis.\" We can state no numerical result; qualitative conclusion. JSON valid. Ensure no evidence because empty. parent_value 0 number. unit \"\". number_stated false. target_result in Chinese or English. Could say \"The text states that circulating m6A-miR-139-5p can serve as a biological indicator for detecting PTC metastasis, but it gives no numerical value for that finding.\" Is P&lt;0.05 numerical result? Let's inspect wording. Abstract's main results: \"Detection of 13 metastatic and 18 non-metastatic clinical specimens showed that FTO ... (P&lt;0.05).\" That is a p-value threshold, not headline numerical result perhaps. MTT also P&lt;0.05. There are two identical P values, no single headline number. \"single numerical result\" probably expected perhaps P&lt;0.05? Yet asked unit must unit paper prints. Parent_value 0.05 and unit maybe \"P\" weird. Maybe parent_value refers \"parent value\" from some benchmark generated target like a coefficient. We need not overthink? Let's understand likely task origin. User asks extraction: \"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. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\"\n\nThis is perhaps a benchmark to find \"headline numerical result\" from source. Need decide if source contains one. The registered target is generic: \"the headline numerical result the paper states for its main finding.\" Could be asking identify metric from abstract. Here no effect sizes. Counts 13 and 18, p&lt;0.05. Main finding perhaps detection via circulating m6A-miR-139-5p. No AUC/sensitivity/specificity numbers. Therefore false.\n\nNeed answer JSON only. target_result should mention text does state instead. Could quote qualitatively? They say evidence empty when no number. target_result can summarize. Maybe Chinese. Let's make concise.\n\nPotential issue: \"main finding\" title: FTO suppresses PTC metastasis by regulating m6A modification of pri-miR-139. Numerical result maybe P<0.05 in result. But \"headline number only\" could be p=0.05. Yet p is not necessarily result (only threshold). They might accept 0.05 with unit \"P\"? But unit needs printed unit; P<0.05 has no unit. The schema allows empty only if no number. If numerical result exists but unitless, unit perhaps \"\". Yet requirement \"unit must be unit the paper prints\" could permit empty for dimensionless. But parent_value is number, and exact evidence. Which target would 0.05 attach to? There are two occurrences. \"single numerical result\" cannot uniquely identify because P<0.05 repeated. Also 13 and 18. Main finding maybe sample detection statement. The title itself has no number. So no.\n\nCould target_result mention exact qualitative main result and P threshold? \"The text reports only qualitative findings (and P<0.05 thresholds): circulating m6A-miR-139-5p can serve as a biological indicator for detecting PTC metastasis; FTO inhibits pri-miR-139 processing by reducing methylation, causing miR-139-5p dysregulation.\" This makes clear. No need quote because evidence empty.\n\nNeed ensure valid JSON no extra.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that circulating m6A-miR-139-5p can serve as a biological indicator for detecting PTC metastasis and that FTO inhibits pri-miR-139 processing by reducing its methylation level, but it reports no numerical value for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that circulating m6A-miR-139-5p can serve as a biological indicator for detecting PTC metastasis and that FTO inhibits pri-miR-139 processing by reducing its methylation level, but it reports no numerical value for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:34:14.757618+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "FTO通过降低其甲基化水平抑制pri-miR-139的加工，导致miR-139-5p在PTC中表达失调(P<0.05)", "minimax_alt": "Detection of 13 metastatic and 18 non-metastatic clinical specimens showed that FTO inhibited the processing of pri-miR-139 by reducing its methylation level, leading to the dysregulation of miR-139-5p in PTC (P<0.05).", "decisive": false}, "physical_methods": {"minimax": ["13例转移和18例非转移临床标本检测", "MTT实验", "Transwell侵袭实验"], "minimax_alt": ["收集13例PTC转移患者和18例非转移患者的临床标本，检测m6A-miR-139-5p的表达水平，分析其与转移的相关性。", "Functional experiments were conducted to investigate the effect of fat mass and obesity-associated protein (FTO) on pri-miR-139 methylation and processing, clarifying its regulatory role in miR-139-5p expression.", "In TPC-1 cells, MTT assays were performed to evaluate whether miR-139-5p overexpression could counteract FTO-mediated cell proliferation.", "Transwell invasion assays were used to determine the impact of miR-139-5p on PTC cell invasion, exploring whether it functions through the ZEB1/E-cadherin axis."], "decisive": false}, "analysis_methods": {"minimax": ["TCGA和GSE130512队列比较", "m6A-miR-139-5p表达及其与转移的相关性分析"], "minimax_alt": ["Expression profiles of m6A-miRNAs were compared between the The Cancer Genome Atlas (TCGA) and GSE130512 cohorts to identify metastasis-associated candidates.", "Clinical specimens from 13 metastasis and 18 non-metastasis PTC patients were analyzed to assess m6A-miR-139-5p expression and its correlation with metastasis."], "decisive": false}}, "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": "passed", "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.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:b056af0992615b2a9daf0faac22f3a4aa42eac202b84ab70684c7b0b04bd49ab", "type": "sep_package", "label": "SEP v1 package for pmid:40916819"}], "activities": [{"id": "activity:conversion:pmid:40916819", "type": "conversion", "used": ["package:b056af0992615b2a9daf0faac22f3a4aa42eac202b84ab70684c7b0b04bd49ab"], "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": "7e5dafe9-8090-4189-a9ab-8acd0d0fa1ec", "parent_hash": "b056af0992615b2a9daf0faac22f3a4aa42eac202b84ab70684c7b0b04bd49ab", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40916819 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "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:40916819' 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":"2026-11-04T01:21:57+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}}}