{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41484064", "kind": "science-record", "revision": 2, "content_hash": "sha256:821e09475b1c6c6b1495d528abbc0bac60efe4809320381b2ed7a5d96ed6e021", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "SOX4-STAT6-MTHFD2 axis drives hepatocellular carcinoma progression and treatment resistance.", "doi": "10.1038/s41419-025-08394-2", "pmid": "41484064", "authors": null, "journal": "Cell death & disease", "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:41484064"], "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:41484064", "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:41484064' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41484064", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41419-025-08394-2", "sha256": "sha256:d62027b0c50c992cec31d53810239315a085be219622fa088690b4ee6a866866", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41419-025-08394-2", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41484064:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:96fddb6f394526afe4488e04010805a9701a21b2f50eca0a560cbdd0ebf1ed17", "bytes": 1753, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#Tab1", "version": null, "note": "The clinical treatment, drug responses, and treatment duration of patients with HCC.", "structure": {"pmcid": "PMC12858837", "section_index": 8, "section_title": "Expression of SOX4/STAT6/MTHFD2 in HCC specimen and their association with metabolite profiles and drug resistance", "row_count": 19, "column_count": 9}, "table": {"label": "Table 1", "caption": "The clinical treatment, drug responses, and treatment duration of patients with HCC.", "rows": [["Patient number", "Target lesions", "Treatment line", "Combination", "Outcome", "Survival time (m)", "DOT (m)", "Clinical Response", "Best clinical Response (BCR)"], ["#6", "Liver", "AB", "Nil", "Alive, off treatment", "25.3", "8", "CR", "CR"], ["#12", "Peritoneum", "S → R", "Surgical resection", "Alive, off treatment", "24.2", "12.4", "CR", "CR"], ["#54", "Liver", "AB", "RFA", "Alive and treatment", "8.7", "8.7", "SD", "PR"], ["#28", "Liver, adrenal", "S → P → L", "Nil", "Alive and treatment", "20.3", "20.3", "SD", "PR"], ["#8", "Liver", "S → R", "Nil", "Death", "15.8", "15.8", "PD", "SD"], ["#45*", "Liver", "AB", "RFA, TACE", "Death", "5.1", "5.1", "PD", "PD"], ["#42", "Liver, lymph nodes", "DB", "Nil", "Death", "24.5", "24.5", "PD", "CR"], ["#38", "Liver", "S → R", "TACE", "Death", "6.8", "6", "PD", "PD"], ["#31", "Liver", "AB → N → S", "Nil", "Death", "18", "18", "PD", "PR"], ["#29*", "Liver, bone", "P → N", "TACE", "Alive and treatment", "10.7", "10.7", "PD", "SD"], ["#41", "Lung", "S", "TACE", "Death", "0.4", "0.4", "PD", "PD"], ["#40", "Peritoneum", "S → R", "Radiotherapy", "Death", "28.3", "28.3", "PD", "SD"], ["#19", "Liver", "AB → S → R → CT", "Nil", "Death", "7.3", "7.3", "PD", "PD"], ["#58", "Lung", "S → R → S", "Radiotherapy", "Death", "6.5", "5.9", "PD", "SD"], ["#59", "Lung, bone", "S → R", "Surgical resection", "Alive and treatment", "16.9", "16.9", "PD", "SD"], ["#60", "Liver", "P → RM", "Nil", "Death", "10.5", "7.5", "PD", "PD"], ["#61", "Liver, lung", "S → R → AB → CT", "Nil", "Death", "26.1", "24.1", "PD", "SD"], ["#62", "Liver, lymph nodes", "AB → L → CT", "Nil", "Death", "1.8", "1.8", "PD", "PD"]], "row_count": 19, "column_count": 9, "numeric_cells": 54, "header_rows": 1, "locator": "section[8]/table-wrap[1]#Tab1"}}], "gaps": ["asset:source:pmid:41484064 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:41484064", "asset:table:pmid:41484064:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41484064"]}, "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": "1c57b26aa7e66bb607a925247698cc01708e663ca2b07a8c9bc144ba5c56e28d", "source_hash": "d62027b0c50c992cec31d53810239315a085be219622fa088690b4ee6a866866", "raw_response_sha256": "sha256:0484c4de6c543b6f3c2fd7be81191f86536bd4705da43ebbf3002b805369a59f", "raw_response_chars": 5130}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "a6dc5aeac3da5053b9d568ed28200edd1a366b4425d215dfb2ffaa1d8f42649f", "source_hash": "d62027b0c50c992cec31d53810239315a085be219622fa088690b4ee6a866866", "raw_response_sha256": "sha256:751e34e0bb1e30b4f8c55cc607cc3bd5bfb40f63ea36e3009f2ef511c66e8473", "raw_response_chars": 54377}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "4f1c324fdde780e4185893f437993415e42b099f59fd75d1bb36d41839f7ca4b", "source_hash": "d62027b0c50c992cec31d53810239315a085be219622fa088690b4ee6a866866", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The source text states the main finding qualitatively: the SOX4–STAT6–MTHFD2 axis is a critical driver of hepatocellular carcinoma progression and therapeutic resistance. It gives no headline numerical result for this registered target.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The source text states the main finding qualitatively: the SOX4–STAT6–MTHFD2 axis is a critical driver of hepatocellular carcinoma progression and therapeutic resistance. It gives no headline numerical result for this registered target.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:27:38.150352+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "c6eab4bb2890ea2663fc1423d4dec92b3d14a05bd3f80395a9038f0340b26fe8", "source_hash": "d62027b0c50c992cec31d53810239315a085be219622fa088690b4ee6a866866", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline main finding for registered target. Source is abstract + methods, no quantitative headline result perhaps Y641, P <0.05, 62 etc. User asks numerical result replication target reproduce, paper states for registered target. We need determine perhaps target result absent because source text doesn't state a headline numerical finding. Need not mistake cohort 62 or residue 641 as main finding result. The abstract mostly qualitative. Registered target: headline numerical result paper states for main finding. There is no headline numerical result. So number_stated false, parent_value 0, unit \"\", evidence \"\", target_result what text states instead. Need JSON valid. target_result concise describe main finding from text, perhaps \"The SOX4–STAT6–MTHFD2 axis drives HCC progression and treatment resistance; SOX4/STAT6 regulate MTHFD2, NADPH production and nucleotide biosynthesis, and targeting STAT6 or MTHFD2 suppresses tumor growth in TKI-resistant patient-derived xenograft models.\" They insist if no number, say in target_result what text does state instead. We should exact? No requirement exact quote for target_result in false case, likely okay paraphrase? \"Never invent source.\" Better quote exact clauses? The output target_result could say paper states main finding qualitatively. Evidence must empty. We must ensure no other numbers.\n\nCould there be a number intended as 641 Y641? \"single numerical result that a replication of registered target has to reproduce\" Registered target broad \"headline numerical result the paper states for its main finding.\" This supplied text likely excerpt lacking results section; no headline number. The answer false. Need only JSON object. Let's formulate target_result perhaps exact source wording from abstract, preserving enough: \"The SOX4–STAT6–MTHFD2 axis is a critical driver of HCC progression and therapeutic resistance; elevated axis activity is associated with resistance to immunotherapy or TKIs, and targeting STAT6 or MTHFD2 suppresses tumor growth in TKIs-resistant patient-derived xenograft models.\" That's paraphrase but source grounded. Maybe exact contiguous quote can go there though evidence empty. User says evidence empty in false case. target_result \"The text states that...\" Fine.\n\nNeed parent_value number 0, unit empty, evidence empty, boolean false.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The paper states that the SOX4–STAT6–MTHFD2 axis drives hepatocellular carcinoma progression and treatment resistance, with elevated axis activity associated with resistance to immunotherapy or TKIs and targeting STAT6 or MTHFD2 suppressing tumor growth in TKI-resistant patient-derived xenograft models.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The paper states that the SOX4–STAT6–MTHFD2 axis drives hepatocellular carcinoma progression and treatment resistance, with elevated axis activity associated with resistance to immunotherapy or TKIs and targeting STAT6 or MTHFD2 suppressing tumor growth in TKI-resistant patient-derived xenograft models.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:27:31.161698+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "No headline numerical result is stated in the supplied source text; the main finding is stated qualitatively as the SOX4–STAT6–MTHFD2 axis driving HCC progression and therapeutic resistance.", "minimax_alt": "unclear", "decisive": false}, "physical_methods": {"minimax": ["co-immunoprecipitation", "immunofluorescence", "chromatin immunoprecipitation (ChIP) assays", "genetic ablation or knockdown of SOX4", "knockdown of SOX4 or STAT6", "mutation of SOX4/STAT6 binding sites within the MTHFD2 promoter", "DNA methyltransferase inhibitor treatment with 5-Aza-2’-deoxycytidine", "patient-derived xenograft models"], "minimax_alt": ["Genetic ablation or knockdown of SOX4", "treatment with the DNA methyltransferase inhibitor 5-Aza-2’-deoxycytidine", "co-immunoprecipitation", "immunofluorescence", "ChIP assays", "mutation of their binding sites within the MTHFD2 promoter", "Metabolomic profiling", "patient-derived xenograft models", "DNA methylation, ChIP-seq, and RNA-seq profiles"], "decisive": false}, "analysis_methods": {"minimax": ["Student’s t test for quantitative data", "Kaplan–Meier survival analysis", "percentile normalization of gene-expression data", "transcriptomic analysis", "metabolomic profiling"], "minimax_alt": ["GraphPad Prism 9", "Student’s t test for quantitative data", "Kaplan–Meier", "SPSS 21", "normalized as percentile gene expression for statistical analysis", "Transcriptomic analyses"], "decisive": false}, "statistical_method": {"minimax": "Student’s t test for quantitative data; overall survival was analyzed by Kaplan–Meier.", "minimax_alt": "unclear", "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:2e864f3a7dd740b3f97a366bb5d991ae46d379201c75668ec9288776d240f1c5", "type": "sep_package", "label": "SEP v1 package for pmid:41484064"}], "activities": [{"id": "activity:conversion:pmid:41484064", "type": "conversion", "used": ["package:2e864f3a7dd740b3f97a366bb5d991ae46d379201c75668ec9288776d240f1c5"], "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": "pmid:41484064", "parent_hash": "sha256:30f36305ad45d8ae560d1c7c0c09065436400b045dbc40feb927be61d2405072", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41484064 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:41484064' 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":"2026-11-04T01:20:39+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}}}