{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40085377", "kind": "science-record", "revision": 1, "content_hash": "sha256:46c3113eea1c63953de2701e2bcb7e5625a3b1438b2cfb5823e9bb14e2a8ebd7", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T10:25:49Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrated bulk and single-cell transcriptomic analysis unveiled a novel cuproptosis-related lipid metabolism gene molecular pattern and a risk index for predicting prognosis and antitumor drug sensitivity in breast cancer.", "doi": "10.1007/s12672-025-02044-x", "pmid": "40085377", "authors": null, "journal": "Discover oncology", "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": 682.0, "unit": "clmgs", "tolerance": null, "source": "chars 14932-15074 of source sha256 29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff"}, "evidence": [{"asset": "source:pmid:40085377", "locator": "chars 14932-15074 of source sha256 29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff", "quote": "In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer."}]}], "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:40085377"], "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:40085377", "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:40085377' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40085377", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-02044-x", "sha256": "sha256:29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-02044-x", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40085377 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:40085377"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40085377"]}, "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": "dd2642cb495a0b7325c206cad2e99f4fdc9a93766fdef16b3edad6828a2e06ac", "source_hash": "29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff", "raw_response_sha256": "sha256:c9b8888ce5846f3791636bb86fc65a505ffb4e3b5dd80a3d0375a677784417d4", "raw_response_chars": 3225}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "9c50db2246633de6b2f68e2858bdd7f242a023c0ce490954ec5facc2cbb1cdd2", "source_hash": "29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff", "raw_response_sha256": "sha256:4e7e5d80913f98deb26b80b4e0ec08c848eaa9a0ac5bb0220b1cb2d1c14bed44", "raw_response_chars": 60102}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "c0fb62da9c22947814443cbb3fe413f59e35f08cd9cbf8ebdb8e6d913b78ab60", "source_hash": "29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff", "raw_response": "{\"parent_value\":682,\"unit\":\"CLMGs\",\"evidence\":\"In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer.\",\"target_result\":\"The study identified 682 cuproptosis-related lipid metabolism genes (CLMGs).\",\"number_stated\":true}", "reading": {"parent_value": 682, "unit": "CLMGs", "evidence": "In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer.", "target_result": "The study identified 682 cuproptosis-related lipid metabolism genes (CLMGs).", "number_stated": true, "source_locator": "chars 14932-15074 of source sha256 29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff"}, "recorded_at": "2026-10-31T15:34:46.224860+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3bbb77f749757f86037331ebe0802cc4f90a2fe0d040e60124e68bd2f1b937f2", "source_hash": "29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff", "raw_response": "<think>We need answer JSON only, extract single numerical result headline main finding. Need infer target registered is headline numerical result paper states for main finding. Need identify likely number. Source abstract/model: identified 682 CLMGs, risk model 8 genes. \"headline numerical result\" perhaps AUC values? Need determine what counts as registered target. We need find single numerical result replication must reproduce, value paper states for registered target, not calculated. Registered target vague: \"the headline numerical result the paper states for its main finding\". Need pick perhaps 682 CLMGs. They emphasize numerical result, headline number. Source starts abstract, states \"we identified 682 CLMGs\" repeatedly conclusion. Main finding may be 682 CLMGs. Yet there are multiple AUCs. They ask \"single numerical result that a replication ... has to reproduce.\" Need report headline number only. Target likely asks extraction from paper where main result might be number of genes identified. The title no numerical result. Abstract's only prominent number is 682 CLMGs; four clusters and 8 genes, but latter model genes. \"headline numerical result the paper states for its main finding\" likely 682.\n\nCould be headline number is AUC 0.868? But that's performance for one-year survival, while paper main finding is integrated bulk/single-cell transcriptomic analysis and risk index. Registered target phrasing deliberately generic maybe benchmark framework has targets like \"headline numerical result\". Need select one result. The source conclusion says \"we identified 682 CLMGs\". This is singular and repeated, likely target. Unit could be \"CLMGs\" or perhaps \"cuproptosis-related lipid metabolism genes\". Exact contiguous evidence containing number. Need quote whole clause for attribution. Could use: \"In conclusion, the results of this study provide new insights and strategies for assessing prognosis and implementing precision treatment for breast cancer through the lens of CLMGs.\" No number. Better exact: \"In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer.\" Contains direct target. Parent_value 682, unit perhaps \"CLMGs\". User says unit must be unit paper prints. \"682 CLMGs\" printed, so unit \"CLMGs\". target_result should say \"The study identified 682 cuproptosis-related lipid metabolism genes.\" Evidence exact quote.\n\nBut let's ensure perhaps headline numerical result means AUC values and no single because three values. Their instructions mention attribution by parenthetical list / respectively likely target extraction sometimes numbers attached to labels. Here source has AUCs 0.868, .773, .739, respectively. Registered target broad could mean headline numerical result main finding perhaps \"AUC values for predicting 1-year, 3-year, 5-year survival\" but asks single numerical result, so likely select one target? Registered target wording singular may be interpreted as target itself broad category, but asks \"single numerical result\". Could identify main headline number from abstract, likely 682.\n\nLet's parse wording: \"Read the supplied paper text and find the 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. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\nREGISTERED TARGET: the headline numerical result the paper states for its main finding\"\n\nThis looks generated task with registered target perhaps a description. We need identify \"headline numerical result\" from paper. Could be challenge to choose primary numeric finding. The abstract highlights:\n- 682 CLMGs\n- four clusters\n- risk model 8 genes.\nConclusion repeats 682.\nAUC 0.868 etc in results.\nWhat is \"main finding\"? \"novel ... molecular pattern and a risk index.\" Number 682 supports novel gene identification. Headline likely 682.\n\nCould they expect \"8\" genes in risk model? Replication of registered target main finding needs reproduce gene model perhaps eight model genes. But numerical headline maybe \"identified 682 CLMGs\". Let's assess wording singular numerical result. If target is \"the headline numerical result the paper states for its main finding\", main finding is perhaps \"682 CLMGs\" because explicit count, whereas 8 genes are enumerated and could count but source doesn't say \"8\" there except single-cell paragraph says 8 CLMG-related risk model genes. Abstract says model incorporates eight names without number. The 682 appears twice. Thus strongest.\n\nUnit must be paper's printed unit. Could \"CLMGs\" be unit? Counts aren't often units but source prints \"682 CLMGs\". They may expect \"CLMGs\". target_result concise.\n\nNeed output exact JSON, no markdown. Ensure quote exact contiguous. \"In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer.\" Exact. Could use abstract clause \"By utilizing transcriptomic data from The Cancer Genome Atlas (TCGA) for breast cancer, we identified 682 CLMGs and applied the nonnegative matrix factorization (NMF) method to categorize breast cancer patients into four distinct clusters: cluster 1, ‘‘immune-cold and stroma-poor’’; cluster 2, ‘‘immune-infiltrated’’; cluster 3, ‘‘stroma-rich’’; and cluster 4, ‘‘moderate infiltration’’.\" Longer but exact. Conclusion clause is enough and directly says finding. Use unit \"CLMGs\". parent_value number 682. target_result maybe \"682 cuproptosis-related lipid metabolism genes were identified.\" But asks report headline number only perhaps target_result should only say number? Schema asks target_result string. Maybe \"The study identified 682 CLMGs.\" Evidence has number. Number only in parent_value. Fine.\n\nCould unit be \"genes\" rather than CLMGs? The paper prints \"682 CLMGs\", so unit \"CLMGs.\" They explicitly say unit must be unit paper prints. Yes.\n\nNeed not include extra keys.</think>\n\n{\"parent_value\":682,\"unit\":\"CLMGs\",\"evidence\":\"In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer.\",\"target_result\":\"The study identified 682 cuproptosis-related lipid metabolism genes.\",\"number_stated\":true}", "reading": {"parent_value": 682, "unit": "CLMGs", "evidence": "In summary, in this study, we identified 682 CLMGs, providing insights into the expression patterns and roles of these genes in breast cancer.", "target_result": "The study identified 682 cuproptosis-related lipid metabolism genes.", "number_stated": true, "source_locator": "chars 14932-15074 of source sha256 29fa246c656953dd22094b666a8487f1be03bf7b3e5994df0442745eef8ae6ff"}, "recorded_at": "2026-10-31T15:34:51.269406+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "682 cuproptosis-related lipid metabolism genes (CLMGs)", "minimax_alt": "682 cuproptosis-related lipid metabolism genes (CLMGs) were identified.", "decisive": false}, "analysis_methods": {"minimax": ["Pearson correlation analysis", "nonnegative matrix factorization (NMF)"], "minimax_alt": ["Pearson correlation analysis", "Consistent clustering analysis using nonnegative matrix factorization (NMF)", "Kaplan–Meier survival analysis", "Univariate and multivariate Cox regression", "Limma differential gene expression analysis", "Gene Ontology (GO) enrichment analysis", "Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis", "Gene set enrichment analysis (GSEA)", "Spearman correlation analysis", "ESTIMATE analysis", "CIBERSORT", "Single-sample GSEA (ssGSEA)", "Maftools somatic-mutation annotation analysis", "Uniform manifold approximation and projection (UMAP)", "Wilcoxon test", "ROC curve analysis", "Nomogram and calibration curve analysis"], "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:2c7e682401b4c36e5cacdb0fa7e9c284995d0a45ceba9c9a07e1215a80d7f65b", "type": "sep_package", "label": "SEP v1 package for pmid:40085377"}], "activities": [{"id": "activity:conversion:pmid:40085377", "type": "conversion", "used": ["package:2c7e682401b4c36e5cacdb0fa7e9c284995d0a45ceba9c9a07e1215a80d7f65b"], "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": "0c5ea9c9-7a79-48ff-acec-ac39b10183fa", "parent_hash": "2c7e682401b4c36e5cacdb0fa7e9c284995d0a45ceba9c9a07e1215a80d7f65b", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40085377 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:40085377' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:24:47+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}}}