{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40746721", "kind": "science-record", "revision": 1, "content_hash": "sha256:13e9215edc6bf2bc97690329c0abd604b8713f6821ad302e449b3c6a5d2f97bc", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T10:25:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Machine learning-enhanced discovery of tsRNA-mRNA regulatory networks: identifying novel diagnostic biomarkers and therapeutic targets in breast cancer.", "doi": "10.3389/fphar.2025.1640192", "pmid": "40746721", "authors": null, "journal": "Frontiers in pharmacology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 0.98, "unit": "auc", "tolerance": null, "source": "chars 1305-1371 of source sha256 82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df"}, "evidence": [{"asset": "source:pmid:40746721", "locator": "chars 1305-1371 of source sha256 82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df", "quote": "achieving AUC of 0.98 in discovery and 0.82 in validation cohorts."}]}], "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:40746721"], "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:40746721", "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:40746721' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40746721", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphar.2025.1640192", "sha256": "sha256:82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphar.2025.1640192", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40746721 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:40746721"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40746721"]}, "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": "af88fc5e6ec5ed2d008aa6036d054c0b6371d8ab99b9198af435e0978a40773c", "source_hash": "82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df", "raw_response_sha256": "sha256:dff1159e651ecef5d7263ffda070fcbb488181f8543ac18676d73b6dd02c71a2", "raw_response_chars": 5825}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "73203f22639d14c1f095d0f0933119d87c24b34100fb61149e8695a1af0bdb1f", "source_hash": "82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df", "raw_response_sha256": "sha256:9572f83d08f427bb57d74685c0c0f2e688c6836eb5b0a23ea0ec9fdea6ec7d00", "raw_response_chars": 49246}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "e0c4eaaffcb8a2dbad3933943dd6e77f843b2a9d9d406f24ff935213c65d3d68", "source_hash": "82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df", "raw_response": "{\"parent_value\":0.98,\"unit\":\"AUC\",\"evidence\":\"achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.\",\"target_result\":\"0.98\",\"number_stated\":true}", "reading": {"parent_value": 0.98, "unit": "AUC", "evidence": "achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.", "target_result": "0.98", "number_stated": true, "source_locator": "chars 1305-1371 of source sha256 82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df"}, "recorded_at": "2026-10-31T15:24:35.529110+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "c4fb1dd6fceee421e4169df3e01c3ccae7e83dc07fa061a371b2f4348f45f983", "source_hash": "82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states main finding. Source abstract/results: four-tsRNA signature achieving AUC 0.98 discovery and 0.82 validation. Registered target vaguely \"the headline numerical result the paper states for its main finding\". Need choose headline number. Likely AUC 0.98, unit AUC. Need exact contiguous quotation containing number and attribution whole clause. Evidence exact quote perhaps \"We identified 297 differentially expressed tsRNAs and developed a four-tsRNA signature (...) achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.\" But asks single numerical result and headline number only, value paper states for registered target. Is target perhaps main finding is diagnostic signature performance. Which one? Headline AUC likely 0.98 discovery. Yet there are two AUC values. They ask \"single numerical result\" perhaps headline number only likely AUC 0.98. Unit must printed: \"AUC\" (dimensionless, paper prints AUC). Evidence exact clause. Need target_result perhaps brief statement, maybe \"The four-tsRNA diagnostic signature achieved an AUC of 0.98 in the discovery cohort.\" Ensure no paraphrase in evidence. Could quote full sentence. parent_value 0.98, unit \"AUC\". number_stated true.\n\nBut think deeply: registered target \"the headline numerical result the paper states for its main finding\". Main finding perhaps four-tsRNA signature, headline numerical result AUC 0.98 in discovery and 0.82 validation. User says single numerical result, headline number only. There is ambiguity which AUC. Maybe headline is discovery AUC 0.98. The wording \"value the paper itself states for the registered target\" likely benchmark setup expects one parent value. The source's abstract main result includes AUC 0.98 discovery and 0.82 validation. Which registered target? Registered target itself generic. Perhaps target asks \"headline numerical result the paper states for its main finding\" means identify primary number, likely 0.98. Need not output multiple. Could evidence quote complete clause including both, but parent_value one. Exact quote includes number. They might want whole clause because attribution may be carried by wording. Quote sentence is safe.\n\nNeed valid JSON no markdown. target_result string. Unit \"AUC\" rather than \"AUC (area under curve)\" because paper prints AUC. Could unit perhaps empty because AUC dimensionless? User says unit must be unit paper prints. It prints \"AUC of 0.98\"; so unit \"AUC\". Let's formulate.\n\nEvidence exact contiguous quote from source. Could quote:\n\"We identified 297 differentially expressed tsRNAs and developed a four-tsRNA signature (tRF-21-FSXMSL73E, tRF-20-XSXMSL73, tRF-23-FSXMSL73 30H, tRF-23-YJE76INB0J) achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.\"\nThis contains headline 0.98 and full clause. Is quote \"do not shorten it\" perhaps they mean evidence quote containing number cannot truncate sentence? Exact full sentence ideal. target_result \"The four-tsRNA diagnostic signature achieved AUC of 0.98 in the discovery cohort.\" This is paraphrase okay outside evidence. Could say headline number only in parent_value. Fine.\n\nPotential issue: registered target is perhaps \"headline numerical result\" and both AUC values mean no single numerical result? But likely benchmark expects 0.98. Let's inspect language. They ask find \"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.\" This is generic extraction instruction, target description generic perhaps deliberately asks headline. The abstract says \"develop a four-tsRNA signature ... achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.\" Which is the headline numerical result? Usually headline metric is AUC 0.98 discovery, 0.82 validation. But they demand single. Perhaps \"registered target\" may refer to \"headline numerical result the paper states for its main finding,\" and likely target result selected in source's title/abstract. The main finding is signature, and there are two cohort results. Maybe target could be discovery performance only because headline is 0.98. Evidence could include both, though they requested headline number only perhaps evidence can contain other number because exact clause includes both. Is that violating \"Report headline number only\"? The JSON evidence quote necessarily includes 0.82 if full sentence. They said exact contiguous quotation containing the number; don't shorten it; attribution can be carried by parenthetical list etc. \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" Could quote a narrower contiguous exact clause that attributes 0.98, but source has no subordinate clause separately except entire sentence. Yet \"four-tsRNA signature (...) achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.\" includes both. Can't omit. Could perhaps quote \"achieving AUC of 0.98 in discovery\" but not contiguous because source says \"and 0.82...\" after. They insist exact contiguous and do not shorten. So whole sentence with both is right. But report number only in parent_value.\n\nCould evidence use abstract first sentence exactly. Ensure punctuation and Unicode. JSON escapes? Fine.\n\nCould target_result mention both? They say target_result what text states if no number only. Since number stated, likely concise \"The four-tsRNA signature achieved AUC of 0.98 in discovery and 0.82 in validation cohorts.\" But then reports second number in target_result despite headline only? Better \"The four-tsRNA signature achieved an AUC of 0.98 in the discovery cohort.\" Yet this paraphrases. Fine.\n\nNeed perhaps parent_value=0.98, unit=\"AUC\", evidence exact full sentence, target_result \"The four-tsRNA diagnostic signature achieved AUC of 0.98 in the discovery cohort.\", true.\n\nLet's ensure no issue with \"developed a four-tsRNA signature\" also has number four but not numerical result. Main finding could be 297 DE tsRNAs? No, headline result likely diagnostic AUC. The title emphasizes biomarkers and targets. Abstract's most salient performance number is AUC. \"headline numerical result\" likely 0.98. Let's answer JSON only.</think>\n\n{\"parent_value\":0.98,\"unit\":\"AUC\",\"evidence\":\"We identified 297 differentially expressed tsRNAs and developed a four-tsRNA signature (tRF-21-FSXMSL73E, tRF-20-XSXMSL73, tRF-23-FSXMSL730H, tRF-23-YJE76INB0J) achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.\",\"target_result\":\"The four-tsRNA diagnostic signature achieved an AUC of 0.98 in the discovery cohort.\",\"number_stated\":true}", "reading": {"parent_value": 0.98, "unit": "AUC", "evidence": "We identified 297 differentially expressed tsRNAs and developed a four-tsRNA signature (tRF-21-FSXMSL73E, tRF-20-XSXMSL73, tRF-23-FSXMSL730H, tRF-23-YJE76INB0J) achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.", "target_result": "The four-tsRNA diagnostic signature achieved an AUC of 0.98 in the discovery cohort.", "number_stated": true, "source_locator": "chars 1144-1371 of source sha256 82aa03dcc4f36ab4475e71e4eb195be0e5947f7f673c0975fd671a0b74a619df"}, "recorded_at": "2026-10-31T15:24:43.800186+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "A four-tsRNA signature (tRF-21-FSXMSL73E, tRF-20-XSXMSL73, tRF-23-FSXMSL730H, tRF-23-YJE76INB0J) achieved AUC of 0.98 in the discovery cohort and 0.82 in the validation cohort.", "minimax_alt": "We identified 297 differentially expressed tsRNAs and developed a four-tsRNA signature (tRF-21-FSXMSL73E, tRF-20-XSXMSL73, tRF-23-FSXMSL730H, tRF-23-YJE76INB0J) achieving AUC of 0.98 in discovery and 0.82 in validation cohorts.", "decisive": false}, "analysis_methods": {"minimax": ["Random forest algorithm", "DESeq2", "Wald test", "Benjamini-Hochberg false discovery rate control", "Unsupervised hierarchical clustering with Euclidean distance and complete linkage", "Wilcoxon rank-sum test", "ComBat batch-effect correction", "Kruskal-Wallis test followed by Dunn’s post hoc test", "Kaplan-Meier method", "Log-rank test", "Cox proportional hazards regression", "CIBERSORT", "Spearman’s correlation", "ESTIMATE algorithm", "Pearson correlation analysis", "GSVA", "GSEA", "WGCNA", "Student’s t-test", "One-way ANOVA"], "minimax_alt": ["Custom bioinformatics pipeline for tsRNA profile extraction", "DESeq2 differential expression analysis with median-of-ratios normalization and the Wald test", "Benjamini-Hochberg false discovery rate control", "Random forest algorithm for diagnostic model development", "Correlation analysis and RNAhybrid for tsRNA-mRNA regulatory relationship identification", "Wilcoxon rank-sum test and ComBat batch-effect correction for pan-cancer expression analysis", "Student's t-test, one-way ANOVA, Kruskal-Wallis test, and Dunn's post hoc test", "Kaplan-Meier method, log-rank test, and Cox proportional hazards regression", "CIBERSORT and ESTIMATE algorithms with Spearman's rank correlation for immune infiltration analysis", "Pearson correlation for drug sensitivity analysis", "Gene Set Variation Analysis (GSVA), Gene Set Enrichment Analysis (GSEA), and Weighted Gene Co-expression Network Analysis (WGCNA)"], "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:a79a77a0911a76d0697aa77d6a14eb3f32509e6dd31de73a87bff25b1888f78b", "type": "sep_package", "label": "SEP v1 package for pmid:40746721"}], "activities": [{"id": "activity:conversion:pmid:40746721", "type": "conversion", "used": ["package:a79a77a0911a76d0697aa77d6a14eb3f32509e6dd31de73a87bff25b1888f78b"], "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": "4c3857ac-5f1b-49ac-ac16-0d757dc207db", "parent_hash": "a79a77a0911a76d0697aa77d6a14eb3f32509e6dd31de73a87bff25b1888f78b", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40746721 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:40746721' 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":"2026-11-04T03:50:09+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}}}