{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40672061", "kind": "science-record", "revision": 2, "content_hash": "sha256:19a82fb07aaa89f9d459cb95a110bec45fdfebd0fb1bbeffc40da7414980e0aa", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:44Z", "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 miRNA-based model for predicting the 3-year recurrence risk of hepatocellular carcinoma following liver transplantation.", "doi": "10.21037/jgo-2025-9", "pmid": "40672061", "authors": null, "journal": "Journal of gastrointestinal oncology", "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:40672061"], "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:40672061", "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:40672061' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40672061", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/jgo-2025-9", "sha256": "sha256:2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/jgo-2025-9", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40672061:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d0aa2b68028b5da6bebec976bec79c7efb0a44138618700c12e6c647b8013cb3", "bytes": 724, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t1", "version": null, "note": "Logistic regression model analyses of the correlations between the five miRNAs expression in HCC tissues and the 3-year recurrence of HCC following liver transplantation", "structure": {"pmcid": "PMC12261023", "section_index": 11, "section_title": "Construction and validation of a miRNA-based risk score", "row_count": 7, "column_count": 5}, "table": {"label": "Table 1", "caption": "Logistic regression model analyses of the correlations between the five miRNAs expression in HCC tissues and the 3-year recurrence of HCC following liver transplantation", "rows": [["Variables", "Univariate analysis", "", "Multivariate analysis"], ["OR (95% CI)", "P value", "Coefficient (β)"], ["hsa-miR-454", "2.877 (1.398, 5.922)", "0.004", "", "1.232"], ["hsa-miR-1293", "2.207 (1.211, 4.021)", "0.01", "", "1.259"], ["hsa-miR-139", "0.434 (0.239, 0.787)", "0.006", "", "−1.004"], ["hsa-miR-99a", "0.466 (0.252, 0.862)", "0.02", "", "−0.493"], ["hsa-miR-130a", "0.428 (0.234, 0.783)", "0.006", "", "−0.449"]], "row_count": 7, "column_count": 5, "numeric_cells": 21, "header_rows": 2, "locator": "section[11]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:40672061:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0c7c0468c4a4e2b72eb1da7f0452f7d7438047e4cfb151d8e7b8d44450f93213", "bytes": 558, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t2", "version": null, "note": "Logistic regression model analyses of risk factors of hepatocellular carcinoma recurrence within 3 years after liver transplantation", "structure": {"pmcid": "PMC12261023", "section_index": 12, "section_title": "Establishment and validation of a combined model", "row_count": 4, "column_count": 6}, "table": {"label": "Table 2", "caption": "Logistic regression model analyses of risk factors of hepatocellular carcinoma recurrence within 3 years after liver transplantation", "rows": [["Variables", "Univariate analysis", "", "Multivariate analysis"], ["OR (95% CI)", "P value", "OR (95% CI)", "P value"], ["Milan criteria", "2.955 (1.049, 8.325)", "0.04", "", "7.494 (1.444, 38.908)", "0.02"], ["Risk score", "2.718 (1.683, 4.390)", "<0.001", "", "3.074 (1.760, 5.372)", "<0.001"]], "row_count": 4, "column_count": 6, "numeric_cells": 10, "header_rows": 2, "locator": "section[12]/table-wrap[1]#t2"}}], "gaps": ["asset:source:pmid:40672061 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:40672061", "asset:table:pmid:40672061:1", "asset:table:pmid:40672061:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40672061"]}, "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": "5a17f1b4010e8b53774efe188d78493cf4ec17ab4aa844ef889e7f4de3ac6d1f", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response_sha256": "sha256:63e32721c8fa3afe54a6559e3f60fea63d039d32292019adf35b1f834dc39c94", "raw_response_chars": 4908}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "2bf20f01b60a880d58c2f1a6bad4bce9b1d10a0765d81cc44f2a3a7b4dbc0f8f", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response_sha256": "sha256:3187882ab9e7b4029ead2b94f52f54d569fa33e26883c9e434a0dac32a3e77fd", "raw_response_chars": 60262}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "19ac11d2620bfbc676ec6d75454e8a0484c7d278b3e7281fd87bb338e51fdf9e", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response": "{\"parent_value\":0.901,\"unit\":\"AUC\",\"evidence\":\"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].\",\"target_result\":\"AUC = 0.901\",\"number_stated\":true}", "reading": {"parent_value": 0.901, "unit": "AUC", "evidence": "The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].", "target_result": "AUC = 0.901", "number_stated": true, "source_locator": "chars 1203-1363 of source sha256 2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b"}, "recorded_at": "2026-10-31T15:21:18.735523+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "af0ce5158e01bde795837fb8d19da34f995600c53861de3c1ecb0d9d02227044", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response": "<think>We need answer JSON only. Need identify headline numerical result paper states for main finding. Registered target vague \"headline numerical result ... main finding\". Likely AUC=0.901 for five miRNA-based risk score. Or combined nomogram AUC=0.926? Need parse wording. Abstract: \"The five miRNA-based risk score displayed a good predictive efficacy ... [area under curve (AUC)=0.901...]. Furthermore, a nomogram integrating... high predictive accuracy (AUC=0.926)... remarkably better than MC...\" Main model headline result perhaps AUC 0.901; ultimate combined model perhaps 0.926. User asks \"single numerical result that a replication of the registered target has to reproduce\" and target registered \"headline numerical result the paper itself states for its main finding\". Need infer which number is headline. Likely 0.901 AUC because \"five miRNA-based risk score\" is main finding; combined nomogram also major. Title novel miRNA-based model. Headline numerical result likely AUC=0.901. Need unit exactly paper prints. Unit could \"area under the curve (AUC)\" or \"AUC\". Schema parent_value number, unit string. They request unit paper prints, evidence exact contiguous quotation containing number, don't shorten quote. Quote whole clause as needed. We can quote: \"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P&lt;0.001].\" This exact contiguous. Unit likely \"AUC\" (dimensionless). Target result sentence perhaps same. Need JSON valid escaping. number_stated true. parent_value 0.901, unit \"AUC\". Could unit be \"area under the curve (AUC)\"? \"The unit must be the unit the paper prints.\" For AUC, dimensionless but paper prints \"area under the curve (AUC)\". Usually these extraction tasks expect unit perhaps \"AUC\". Need be precise. Maybe parent value 0.901 and unit \"area under the curve (AUC)\". Evidence exact quote.\n\nBut determine headline number perhaps 0.926. Let's deeply assess likely source/task conventions. The prompt generated to extract claims only, registered target is semantic. \"headline numerical result the paper itself states for its main finding.\" Main finding described perhaps five miRNA risk score, AUC 0.901. Combined nomogram is further development. \"a replication of registered target has to reproduce.\" Likely expected metric from abstract. Could target_result say \"AUC = 0.901 for five miRNA-based risk score predicting 3-year recurrence risk after LT.\" Evidence full sentence. Good.\n\nNeed \"headline number only\" means only numeric result, but JSON includes evidence etc. We comply.\n\nExact quote punctuation? Source has \"[area under the curve (AUC) =0.901, P&lt;0.001].\" Need exact spacing. Quote whole clause/sentence. Evidence exact contiguous. Unit must be paper prints. Could set \"area under the curve (AUC)\" precisely. Parent_value 0.901. target_result maybe \"The five miRNA-based risk score had an area under the curve (AUC) =0.901 for predicting the 3-year recurrence risk of HCC post-LT.\" Though says only headline number, perhaps target_result should mention target, no extraneous numbers? They ask \"Report headline number only: value ...\". But schema includes target_result. Likely concise. We need not include P. Evidence necessarily includes P because exact sentence and cannot shorten? Could perhaps quote exact contiguous subclause \"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901\" but that ends awkwardly and is exact contiguous, yet \"do not shorten it\" means perhaps quote full clause including P. They explicitly say exact contiguous quotation contains number, do not shorten it, no ellipsis. \"When that is how text links them, quote the whole clause.\" So full sentence including P best.\n\nCould evidence instead be exactly \"[area under the curve (AUC) =0.901, P&lt;0.001]\" but target attribution is previous sentence context, likely whole sentence. Yes.\n\nDoes \"unit\" need no unit, because AUC is unitless? They say unit must be unit paper prints. In paper the metric label \"area under the curve (AUC)\" not a physical unit. Many schemas use unit string perhaps \"AUC\". Use \"AUC\". Yet \"The unit must be the unit the paper prints.\" Paper prints AUC, so fine.\n\nJSON only. Ensure no markdown.</think>\n\n{\"parent_value\":0.901,\"unit\":\"area under the curve (AUC)\",\"evidence\":\"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].\",\"target_result\":\"The five miRNA-based risk score achieved an AUC of 0.901 for predicting 3-year HCC recurrence risk after liver transplantation.\",\"number_stated\":true}", "reading": {"parent_value": 0.901, "unit": "area under the curve (AUC)", "evidence": "The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].", "target_result": "The five miRNA-based risk score achieved an AUC of 0.901 for predicting 3-year HCC recurrence risk after liver transplantation.", "number_stated": true, "source_locator": "chars 1203-1363 of source sha256 2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b"}, "recorded_at": "2026-10-31T15:21:22.610368+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The nomogram integrating the miRNA-based model with Milan criteria achieved an area under the curve (AUC) of 0.926 (P<0.001) for predicting 3-year HCC recurrence after liver transplantation.", "minimax_alt": "The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].", "decisive": false}, "analysis_methods": {"minimax": ["differential expression analysis", "Kaplan-Meier method", "least absolute shrinkage and selection operator (LASSO)-logistic regression", "multivariate logistic regression", "receiver operating characteristic curve analysis", "area under the curve (AUC)", "concordance index", "calibration plots", "decision curve analysis"], "minimax_alt": ["Differential expression analysis", "Kaplan-Meier method", "Least absolute shrinkage and selection operator (LASSO)-logistic regression", "Multivariate logistic regression", "Concordance index", "Calibration plots", "Decision curve analysis", "Receiver operating characteristic curves and area under the curve (AUC)", "Student’s t-test", "Mann-Whitney test", "DIANA-microT-CDS miRNA target prediction with Targetscan validation", "Overlapping analysis of miRNA-mRNA negative regulatory relationships", "Gene Ontology and KEGG pathway enrichment analysis with DAVID 6.7"], "decisive": false}, "statistical_method": {"minimax": "receiver operating characteristic curve analysis evaluated using the area under the curve (AUC)", "minimax_alt": "Area under the curve (AUC) analysis", "decisive": true}, "unit": {"minimax": "AUC", "minimax_alt": "area under the curve (AUC)", "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:3342053886f181f92f8af3bf09000d5b38ead8a0593ea1f14ac24c9ed84772b5", "type": "sep_package", "label": "SEP v1 package for pmid:40672061"}], "activities": [{"id": "activity:conversion:pmid:40672061", "type": "conversion", "used": ["package:3342053886f181f92f8af3bf09000d5b38ead8a0593ea1f14ac24c9ed84772b5"], "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:40672061", "parent_hash": "sha256:5b4561e45e0dc008e93815f6faa92c4abb194289e2db489aa363b9f1e3888ec1", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40672061 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:40672061' 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":"2026-11-04T03:38:23+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}}}