{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41496025", "kind": "science-record", "revision": 2, "content_hash": "sha256:607f51e08c22c3b7e5f6b2d5e50d836fdec2d2c95728877937ce41cfe96779b9", "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": "Construction and validation of a prognostic model based on anoikis-fatty acid metabolism-related genes in colorectal cancer: A retrospective cohort study.", "doi": "10.1097/md.0000000000046863", "pmid": "41496025", "authors": null, "journal": "Medicine", "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:41496025"], "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:41496025", "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:41496025' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41496025", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/md.0000000000046863", "sha256": "sha256:cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/md.0000000000046863", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41496025:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f2c9a3188011c60a987dcc4a301c529b36e9c9c9e40a39231ec4b931ad7268c4", "bytes": 1427, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T1", "version": null, "note": "The clinicopathological features in the training and testing sets.", "structure": {"pmcid": "PMC12778156", "section_index": 15, "section_title": "3.4. Construction and validation of prognostic models based on AFRGs", "row_count": 22, "column_count": 6}, "table": {"label": "Table 1", "caption": "The clinicopathological features in the training and testing sets.", "rows": [["Covariates", "Type", "Total", "Test", "Train", "P-value"], ["Age", "≤65", "270 (43.55%)", "76 (40.86%)", "194 (44.7%)", ".4264"], [">65", "350 (56.45%)", "110 (59.14%)", "240 (55.3%)"], ["Gender", "Female", "291 (46.94%)", "83 (44.62%)", "208 (47.93%)", ".5046"], ["Male", "329 (53.06%)", "103 (55.38%)", "226 (52.07%)"], ["Stage", "Stage I", "105 (16.94%)", "34 (18.28%)", "71 (16.36%)", ".3952"], ["Stage II", "227 (36.61%)", "68 (36.56%)", "159 (36.64%)"], ["Stage III", "179 (28.87%)", "57 (30.65%)", "122 (28.11%)"], ["Stage IV", "89 (14.35%)", "20 (10.75%)", "69 (15.9%)"], ["unknown", "20 (3.23%)", "7 (3.76%)", "13 (3%)"], ["T", "T1", "20 (3.23%)", "4 (2.15%)", "16 (3.69%)", ".5155"], ["T2", "105 (16.94%)", "35 (18.82%)", "70 (16.13%)"], ["T3", "423 (68.23%)", "123 (66.13%)", "300 (69.12%)"], ["T4", "70 (11.29%)", "24 (12.9%)", "46 (10.6%)"], ["unknown", "2 (0.32%)", "0 (0%)", "2 (0.46%)"], ["M", "M0", "459 (74.03%)", "142 (76.34%)", "317 (73.04%)", ".1021"], ["M1", "88 (14.19%)", "19 (10.22%)", "69 (15.9%)"], ["unknown", "73 (11.77%)", "25 (13.44%)", "48 (11.06%)"], ["N", "N0", "351 (56.61%)", "107 (57.53%)", "244 (56.22%)", ".7865"], ["N1", "150 (24.19%)", "47 (25.27%)", "103 (23.73%)"], ["N2", "116 (18.71%)", "32 (17.2%)", "84 (19.35%)"], ["unknow", "3 (0.48%)", "0 (0%)", "3 (0.69%)"]], "row_count": 22, "column_count": 6, "numeric_cells": 71, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:41496025 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:41496025", "asset:table:pmid:41496025:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41496025"]}, "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": "e763144baead03ccf7b6e5a1eb95b00e046f169128d85e97d39bc15de13b3554", "source_hash": "cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d", "raw_response_sha256": "sha256:bfe491adf5e81e675b32c74e85c257f8537bc7bc961ce5bdf1e322ea1176bdb0", "raw_response_chars": 4574}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "f7acb1fac5ec065a026cdfd0469a0dd5000cc7dd9b6a90ed2290aa8c1f828f58", "source_hash": "cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d", "raw_response_sha256": "sha256:d6329de15a9d0120620e2c8385f1c3ed5b549470e26a1230bfee529efaad0888", "raw_response_chars": 46932}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "431876e9608144a0ba2ce33905d0515d933fd4a47edad9b7a98261dc102c5e5a", "source_hash": "cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d", "raw_response": "{\"parent_value\":0.889,\"unit\":\"area under the curve (AUC)\",\"evidence\":\"(e.g., the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible in larger independent cohorts)\",\"target_result\":\"The 1-year overall survival AUC in the GSE12945 external validation cohort.\",\"number_stated\":true}", "reading": {"parent_value": 0.889, "unit": "area under the curve (AUC)", "evidence": "(e.g., the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible in larger independent cohorts)", "target_result": "The 1-year overall survival AUC in the GSE12945 external validation cohort.", "number_stated": true, "source_locator": "chars 6222-6330 of source sha256 cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d"}, "recorded_at": "2026-10-31T15:26:25.864491+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "cd90a5d31f058ebcaf32282b2c3e3ab34d693801dfefd6e96e54d245787ec764", "source_hash": "cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d", "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. Ambiguity: headline result could external validation AUC perhaps 1-year OS AUC 0.889, explicitly singled in limitations \"the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible\". User asks \"find the single numerical result that a replication of the registered target has to reproduce. Report headline number only: value paper itself states for registered target, not calculated... Registered target: headline numerical result the paper states for its main finding.\" Need infer intended likely 0.889? They emphasize single numerical result replication. Main finding in abstract: 1-,3-,5-year OS AUC 0.889/0.795/0.740. That's three values, but asks single numerical result. Conclusion specifically flags 1-year OS AUC 0.889 might not be fully reproducible. Maybe expected number is 0.889 with unit \"AUC\". Evidence exact contiguous quote containing number and attribution whole clause. Need target_result wording.\n\nCould headline numerical result perhaps n=62? No, main finding likely prognostic model, and the prominent headline number is AUC. The question likely generated task to extract \"parent_value\" from paper, perhaps asks numerical result for \"registered target\" abstract. Registered target generic. Need pick one single. The conclusion's wording \"e.g., the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible...\" explicitly frames reproducibility, likely strongest clue. Quote whole clause maybe \"the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible in larger independent cohorts\". Exact contiguous. Unit should printed: likely \"AUC\" (unitless but paper prints AUC). parent_value 0.889. target_result perhaps \"The 1-year overall survival AUC in GSE12945 was 0.889.\" Evidence exact quote. Need not include full sentence? Requirement exact contiguous quotation, no shorten; can quote clause. \"the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible in larger independent cohorts\" is exact. Parent target result says what. JSON valid.\n\nCheck whether they perhaps expect 0.889/0.795/0.740 but parent_value must number, single numerical result. \"headline number only\" likely 0.889. Could be AUC as unit. The phrase \"registered target\" perhaps benchmark asks extract \"parent_value\" corresponding to some question, but registered target intentionally generic. Main finding headline numerical result maybe \"1-year OS AUC: 0.889/0.795/0.740\" and first is headline. They may expect 0.889.\n\nNeed ensure evidence attribution names target directly. Quote full clause includes GSE12945 and 1-year OS AUC. Good.\n\ntarget_result maybe \"The paper reports a 1-year overall survival AUC of 0.889 in GSE12945.\" This is paraphrase but allowed target_result. Unit \"AUC\" paper prints. Could unit be \"area under the curve (AUC)\"? They say unit must unit paper prints. Since AUC is metric, perhaps unit \"AUC\". Use exact printed term \"AUC\".\n\nReturn JSON only, no markdown.</think>\n\n{\"parent_value\":0.889,\"unit\":\"AUC\",\"evidence\":\"the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible in larger independent cohorts\",\"target_result\":\"The paper reports a 1-year overall survival AUC of 0.889 in GSE12945.\",\"number_stated\":true}", "reading": {"parent_value": 0.889, "unit": "AUC", "evidence": "the 1-year OS AUC of 0.889 in GSE12945 might not be fully reproducible in larger independent cohorts", "target_result": "The paper reports a 1-year overall survival AUC of 0.889 in GSE12945.", "number_stated": true, "source_locator": "chars 6229-6329 of source sha256 cf600883ee67f71fcbfdc6f75d6ed5b500b423d5eb27670126789fcf5454122d"}, "recorded_at": "2026-10-31T15:26:28.763083+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The 5-gene prognostic model had 1-, 3-, and 5-year overall survival AUC values of 0.889, 0.795, and 0.740, respectively, in GSE12945.", "minimax_alt": "A 5-gene (BRCA1, CD36, ENO3, INHBB, PHLDA2) model showed robust predictive efficacy (1-, 3-, 5-year OS area under the curve: 0.889/0.795/0.740 in GSE12945).", "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis using the Limma package", "ComBat batch-effect correction using the sva package", "Non-negative matrix factorization clustering", "Univariate Cox regression", "LASSO regression with cross-validation", "Multivariate Cox modeling", "Receiver operating characteristic curve analysis using the pROC roc function", "Area under the curve and confidence interval calculation using the pROC CI function", "Nomogram analysis", "Kaplan–Meier curve analysis", "Log-rank test"], "minimax_alt": ["Differential expression analysis using the Limma package", "ComBat batch-effect correction using the sva package", "NMF clustering", "Univariate Cox regression", "LASSO regression with cross-validation", "Multivariate Cox model for risk-score construction", "Receiver operating characteristic curve analysis and area under the curve estimation using the pROC package", "Nomogram", "Immune infiltration analysis", "Kaplan–Meier Curve analysis and log-rank test"], "decisive": false}, "statistical_method": {"minimax": "Receiver operating characteristic (ROC) curve analysis, with AUC values and confidence intervals calculated using the roc and CI functions in the pROC package", "minimax_alt": "Receiver operating characteristic (ROC) curve analysis with area under the curve (AUC) estimation", "decisive": true}, "unit": {"minimax": "area under the curve (AUC)", "minimax_alt": "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:d274b147281d80d024a3f73ce7445ec3f251834c0b127d5888403162b32c233e", "type": "sep_package", "label": "SEP v1 package for pmid:41496025"}], "activities": [{"id": "activity:conversion:pmid:41496025", "type": "conversion", "used": ["package:d274b147281d80d024a3f73ce7445ec3f251834c0b127d5888403162b32c233e"], "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:41496025", "parent_hash": "sha256:4bfc4b5898f668c8190841c3fc86200578f633a947e20ca319b02fabfe810e66", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41496025 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:41496025' 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":"2026-11-04T02:38:20+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}}}