{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40830065", "kind": "science-record", "revision": 2, "content_hash": "sha256:88a511e2b9e2ab6da25c2cedf4878e41a6f0d883be0a0c2a731d4b6b6e308283", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:46Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Anoikis-related genes predicts prognosis and therapeutic response in renal cell carcinoma.", "doi": "10.1080/07853890.2025.2548042", "pmid": "40830065", "authors": null, "journal": "Annals of medicine", "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": 0.79, "unit": "auc", "tolerance": null, "source": "chars 1324-1480 of source sha256 5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1"}, "evidence": [{"asset": "source:pmid:40830065", "locator": "chars 1324-1480 of source sha256 5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1", "quote": "Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance."}]}], "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:40830065"], "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:40830065", "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:40830065' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40830065", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/07853890.2025.2548042", "sha256": "sha256:5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/07853890.2025.2548042", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40830065:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:76997f6e318632882f1e07016715210ac42583482a833811b617c8833a658343", "bytes": 1074, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#t0001", "version": null, "note": "Summary of datasets used in current study.", "structure": {"pmcid": "PMC12366518", "section_index": 20, "section_title": "Data acquisition", "row_count": 12, "column_count": 3}, "table": {"label": "Table 1.", "caption": "Summary of datasets used in current study.", "rows": [["Datasets", "Brief description (n = enrolled)", "Type"], ["TCGAa-KIRCb", "ccRCCc patients (n = 518) and healthy controls (n = 71)", "RNA-seqd"], ["E-MTAB-1980", "ccRCC patients (n = 101)", "RNA-seq"], ["E-MTAB-3218", "ccRCC patients (n = 114) treated by nivolumab", "RNA-seq"], ["E-MTAB-3267", "ccRCC patients (n = 59) treated by sunitinib", "RNA-seq"], ["CHECKMATE-009", "ccRCC patients (n = 16) treated by nivolumab", "RNA-seq"], ["CHECKMATE-010", "ccRCC patients (n = 45) treated by nivolumab", "RNA-seq"], ["CHECKMATE-025", "ccRCC patients (n = 250) treated by nivolumab and everolimus", "RNA-seq"], ["GSE22541", "Primary and pulmonary metastasis of ccRCC (n = 68)", "RNA-seq"], ["GSE85258", "Primary and pulmonary metastasis of ccRCC (n = 29)", "RNA-seq"], ["GSE113204", "Primary, pulmonary metastasis and tumour thrombus of ccRCC (n = 14)", "RNA-seq"], ["GSE159115", "ccRCC patients (n = 7)", "scRNA-seqe"]], "row_count": 12, "column_count": 3, "numeric_cells": 21, "header_rows": 1, "locator": "section[20]/table-wrap[1]#t0001"}}], "gaps": ["asset:source:pmid:40830065 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:40830065", "asset:table:pmid:40830065:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40830065"]}, "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": "be95ad2aec9130180eb77086ea2335d1b636cf3795957660ad7f0f274d6bd866", "source_hash": "5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1", "raw_response_sha256": "sha256:60a6e5b9201c5a4c18197bca259f41d096c83501c968cbe929f377f18ff9233b", "raw_response_chars": 5095}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "a2848f8898cffd868eb97754f3d569442d9a1c9a277ac9b55f3b9d911836012d", "source_hash": "5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1", "raw_response_sha256": "sha256:7094f55cb9954cc564870325f81ef4403438b14be18f99cbc2383ae08e704ff1", "raw_response_chars": 53846}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "b10ba375fdeba416ff106ae7a72983f74ce0c890fa714e714bad19aad0e59ae9", "source_hash": "5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1", "raw_response": "{\"parent_value\":0.79,\"unit\":\"AUC\",\"evidence\":\"Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance.\",\"target_result\":\"5-year area under curve (AUC) of 0.79\",\"number_stated\":true}", "reading": {"parent_value": 0.79, "unit": "AUC", "evidence": "Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance.", "target_result": "5-year area under curve (AUC) of 0.79", "number_stated": true, "source_locator": "chars 1324-1480 of source sha256 5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1"}, "recorded_at": "2026-10-31T15:30:34.998324+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "1b7c0a8389cd3639cefd96008900205ca23e2b602b95203ac5fb437009d56e66", "source_hash": "5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1", "raw_response": "<think>We need answer JSON object only. Need identify single numerical result replication registered target headline numerical result paper states for main finding. Likely 5-year AUC 0.79. Need exact contiguous quote containing number, likely sentence: \"Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance.\" Unit paper prints? AUC dimensionless, perhaps unit \"AUC\" or \"\"? Asked unit must be unit paper prints. Headline number only value. parent_value 0.79. unit perhaps \"AUC\" because metric labeled area under curve (AUC), no physical unit. Need evidence exact contiguous quote whole clause attribution. target_result perhaps \"5-year area under curve (AUC) of 0.79\". number_stated true. Ensure valid JSON, no extra. But perhaps headline result could be 59% anoikis? Let's parse request carefully: REGISTERED TARGET: \"the headline numerical result the paper states for its main finding\". Main finding perhaps abstract/result summary includes model achieved 5-year AUC 0.79; MMP9 HR 1.5; functional effects. Which is \"headline numerical result\" singular? Likely central headline metric is AUC 0.79. User wants single numerical result replication of registered target has to reproduce. The source says model achieved 5-year AUC of 0.79, likely intended. Need exact quote no shortening/ellipsis/paraphrase. Evidence can whole sentence. Unit must be unit paper prints. Since AUC is metric not unit. Could set unit \"AUC\" perhaps. But perhaps unit should be \"area under curve (AUC)\" as printed. They say unit must be unit paper prints, often extraction task expects number and unit like \"5-year AUC\" perhaps unit \"AUC\". Let's inspect wording. \"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.\" Registered target broad. Number 0.79. The unit associated is likely AUC. Evidence exact quote. Target result text perhaps \"5-year area under curve (AUC) of 0.79\". Could parent_value 0.79, unit \"AUC\". Is \"5-year\" part unit? Usually target result asks result for parent? Here \"parent_value\" schema perhaps generic. They might want \"5-year AUC\" as unit? Let's think likely benchmark design. They give a registered target and ask numerical result. Source text. Need infer headline numerical result. Could be \"5-year area under curve (AUC) of 0.79.\" They expect value 0.79, unit \"AUC\" (dimensionless), evidence. target_result perhaps wording.\n\nNeed obey \"headline number only\" perhaps target_result should only mention 0.79? Yet evidence necessarily full quote. JSON fields. We can state unit \"AUC\" and target_result \"5-year area under curve (AUC) of 0.79\". Good.\n\nExact contiguous quotation: sentence appears twice identically. Quote whole sentence:\n\"Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance.\"\nThat is exact. Attribution via \"our model achieved...\" directly. Could quote clause rather than full sentence, but whole sentence safest. No ellipsis. JSON escaped apostrophes not issue.\n\nCould unit be \"5-year AUC\"? If field unit expected unit printed, \"AUC\" is dimensionless. The 5-year is time horizon not unit. Maybe empty unit because no unit, but instruction says unit must be unit paper prints. For AUC, conventional unit \"AUC\". We can use \"AUC\". Number is 0.79.\n\nLet's ensure no markdown.</think>\n\n{\"parent_value\":0.79,\"unit\":\"AUC\",\"evidence\":\"Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance.\",\"target_result\":\"5-year area under curve (AUC) of 0.79\",\"number_stated\":true}", "reading": {"parent_value": 0.79, "unit": "AUC", "evidence": "Using Cox regression and machine learning, our model achieved a 5-year area under curve (AUC) of 0.79, surpassing existing models in predictive performance.", "target_result": "5-year area under curve (AUC) of 0.79", "number_stated": true, "source_locator": "chars 1324-1480 of source sha256 5540c1ed9e37c944674dbf5ae297aa013a92d4650ebe16903acdf0bbccd761e1"}, "recorded_at": "2026-10-31T15:30:40.292386+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The ARG-based prognostic model achieved a 5-year area under curve (AUC) of 0.79.", "minimax_alt": "The ARG-based prognostic model achieved a 5-year area under curve (AUC) of 0.79 for predicting survival in RCC.", "decisive": false}, "physical_methods": {"minimax": ["In vitro anoikis assays using poly-HEMA-treated 786-O and Achn renal carcinoma cell lines", "MMP9 knockdown using lentivirus", "Wound-healing migration assay", "Transwell invasion assay", "Western blot analysis of MMP9 and cleaved caspase 3", "RT-qPCR analysis of MMP9 expression", "Flow cytometric analysis of apoptosis using Annexin V and DAPI"], "minimax_alt": ["in vitro experiments in 786 O and Achn RCC cell lines", "lentivirus-mediated MMP9 knockdown", "poly-HEMA treatment for anoikis assays", "wound-healing assay", "transwell invasion assay", "western blot analysis", "RT-qPCR", "Annexin V and DAPI flow cytometric analysis"], "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis with DESeq2", "Median-split survival screening with log-rank tests", "LASSO regression", "SVM-RFE", "Random forest", "Cox regression", "Kaplan-Meier survival analysis", "Time-dependent ROC analysis with TimeROC", "Gene Ontology and KEGG over-representation analysis", "GSVA", "GSEA", "Monocle 2 pseudotime analysis", "NicheNet cell-cell interaction analysis", "pySCENIC transcription factor analysis"], "minimax_alt": ["Cox regression", "machine learning using LASSO, SVM-RFE, and random forest", "receiver operating characteristic (ROC) curves with AUC calculated by R package ‘TimeROC’", "log-rank test and Kaplan-Meier curves", "DESeq2 differential expression analysis", "Gene Set Variation Analysis (GSVA)", "Gene Set Enrichment Analysis (GSEA)", "Monocle 2 pseudotime analysis", "NicheNet ligand-receptor-target network analysis", "pySCENIC regulon analysis", "Student’s t-test or one-way ANOVA for experimental comparisons"], "decisive": false}, "statistical_method": {"minimax": "Receiver operating characteristic (ROC) curves were used, with AUC calculated by the TimeROC R package.", "minimax_alt": "Cox regression and machine learning", "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:f66d6c7d6ea5c43de51a7ac1fbd03ca16f69563e47689e3714a2e1b59f5b6378", "type": "sep_package", "label": "SEP v1 package for pmid:40830065"}], "activities": [{"id": "activity:conversion:pmid:40830065", "type": "conversion", "used": ["package:f66d6c7d6ea5c43de51a7ac1fbd03ca16f69563e47689e3714a2e1b59f5b6378"], "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:40830065", "parent_hash": "sha256:de49848bf5ebf8599ababa12c20fda77215f0a23d333c669cf2b2fbb6233bb1b", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40830065 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:40830065' 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":"2026-11-04T03:13:11+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}}}