{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40805273", "kind": "science-record", "revision": 2, "content_hash": "sha256:4fe46627049c8975055ce7355986f5826a2c1594b313c5ee1ffe1eb94e42fae6", "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": "Ribosome Biogenesis Underpins Tumor Progression: A Comprehensive Signature for Survival and Immunotherapy Response Prediction.", "doi": "10.3390/cancers17152576", "pmid": "40805273", "authors": null, "journal": "Cancers", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40805273"], "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:accession_absent", "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:40805273", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "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:40805273' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40805273", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers17152576", "sha256": "sha256:cb0ebb3294043f08ba791a2421f8e654889b7741cfe63a8c8669a035d7151774", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers17152576", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40805273:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:74cb459ce8da1d62493b57a7c77591b2a68488ffd336a4c5af5203a84f93b4e6", "bytes": 1123, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[28]/table-wrap[1]#array1", "version": null, "note": null, "structure": {"pmcid": "PMC12345896", "section_index": 28, "section_title": "Abbreviations", "row_count": 26, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["FDR", "False discovery rate"], ["GEO", "Gene Expression Omnibus"], ["HER2", "Human epidermal growth factor receptor 2"], ["HR", "Hazard ratio"], ["ICI", "Immune checkpoint inhibitor"], ["KEGG", "Kyoto Encyclopedia of Genes and Genomes"], ["KIRC", "Kidney renal clear cell carcinoma"], ["KM", "Kaplan–Meier"], ["LASSO", "Least absolute shrinkage and selection operator"], ["LIHC", "Liver hepatocellular carcinoma"], ["LUAD", "Lung adenocarcinoma"], ["mTOR", "mammalian target of rapamycin"], ["MSI", "Microsatellite instability"], ["OMIM", "Online Mendelian Inheritance in Man"], ["OS", "Overall survival"], ["TP53", "Tumor protein p53"], ["PD-1", "Programmed cell death protein 1"], ["PD-L1", "Programmed cell death-ligand 1"], ["PPI", "Protein–protein interaction"], ["RiBi", "RiBi"], ["R2", "Coefficient of determination"], ["RNAss", "RNA expression–based stemness"], ["TCGA", "The Cancer Genome Atlas"], ["T-cell", "T lymphocyte"], ["TIDE", "Tumor Immune Dysfunction and Exclusion"], ["Xena", "UCSC Xena browser"]], "row_count": 26, "column_count": 2, "numeric_cells": 6, "header_rows": 0, "locator": "section[28]/table-wrap[1]#array1"}}], "gaps": ["asset:source:pmid:40805273 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:40805273", "asset:table:pmid:40805273:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40805273"]}, "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": "83136ca3724100b9ed25f8d960fd9736971142d35e010bbb1ace5703c8f09e91", "source_hash": "cb0ebb3294043f08ba791a2421f8e654889b7741cfe63a8c8669a035d7151774", "raw_response_sha256": "sha256:c45b1533cb7dea9419f7824d36ccb41ccaa373c2dca2e079516364a84ec46740", "raw_response_chars": 3948}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "be500bbbba439d2edb9c8f358d754330e3cfd31e54ed662fd1e03c9928c8190b", "source_hash": "cb0ebb3294043f08ba791a2421f8e654889b7741cfe63a8c8669a035d7151774", "raw_response_sha256": "sha256:ccf32a81e0e8ccaaa92f69d9c8ad73d3ce7aa0d48531419661ba37c1148ea83a", "raw_response_chars": 64935}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "edb561c1f63449dd2280f7d19a10f7a759558fcdf8c5d44d08433dd72a472ca5", "source_hash": "cb0ebb3294043f08ba791a2421f8e654889b7741cfe63a8c8669a035d7151774", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that higher RiBi scores were linked to worse outcomes and that the OncoRibo-68 signature showed robust prognostic power across multiple cohorts, most notably in breast cancer, but it does not state a headline numerical result for the main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that higher RiBi scores were linked to worse outcomes and that the OncoRibo-68 signature showed robust prognostic power across multiple cohorts, most notably in breast cancer, but it does not state a headline numerical result for the main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:30:08.533594+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3ebe2d6b27631d9dc7b0389fbf50177a15b5ce2998f09abf32bfa0f67d92a835", "source_hash": "cb0ebb3294043f08ba791a2421f8e654889b7741cfe63a8c8669a035d7151774", "raw_response": "<think>We need answer JSON only. Need inspect source. Registered target headline numerical result paper states for main finding. Source includes scores PanRibo-515 and OncoRibo-68, but these are named signatures, numerical result? Need determine requested single numerical result replication registered target. The supplied excerpt has no performance metric/headline number, only 68/515 in score names, 2.5 section, cohorts/year citations perhaps. Need perhaps target is headline numerical result paper states for main finding. They say if no number for registered target, number_stated false, parent 0 unit/evidence empty, target_result say what text states instead. We must be careful: exact quote evidence only if number stated. Is OncoRibo-68 a numerical result? It's a gene-set size/name, perhaps headline number? The \"registered target: the headline numerical result the paper states for its main finding.\" Main finding is OncoRibo-68 signature and perhaps numbers 68, but not outcome value. Replication must reproduce headline numerical result. No AUC etc supplied. Thus false.\n\nNeed target_result concise what text states instead. Could say \"The text reports an OncoRibo-68 signature associated with prognostic and immunotherapy-response relevance, but it states no headline numerical result value.\" Since no evidence required? Empty. Need valid JSON. parent_value 0, unit \"\", evidence \"\", number_stated false. Ensure no unsupported wording perhaps it says higher scores linked worse outcomes, elevated often better survival ICI. \"The text describes higher RiBi scores as linked to worse outcomes and elevated OncoRibo-68 expression as often associated with better survival in immune-checkpoint inhibitor-treated cohorts, but it gives no numerical result for the main finding.\" This states accurately. But is target_result expected what text states instead, perhaps quote? They only demand exact quote evidence where number. Could quote full relevant clause. We can say \"The source states the qualitative findings but no headline numerical result for the registered target.\" Yet target_result should state what text does state instead. Let's craft.\n\nNeed determine whether unit should maybe \"genes\" and parent_value 68? Let's investigate task design. They want find single numerical result replication of registered target has to reproduce, value paper itself states. Registered target generic: headline numerical result paper states for main finding. Source likely abstract and excerpts. Could infer title main finding signature \"OncoRibo-68\"; perhaps headline numerical result might be 68? But \"replication of registered target\" likely benchmark asks extract reported main result metric. They distinguish parent_value. Source contains OncoRibo-68 repeatedly. Could be regarded as number attached directly to target (\"OncoRibo-68\"), and paper prints number 68. But is it a numerical result? Need deeply parse wording.\n\n\"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. ... 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.\"\n\nThis seems generated extraction task where target maybe specific claim but registered target here is \"the headline numerical result the paper states for its main finding.\" We need find one numeric result. Source provided perhaps only portions (abstract plus selected sections) and might have no main performance number. They intentionally test false due incomplete text. Number in title of signature may not be a \"result\" and no unit. Likely false.\n\nCould target be 68? OncoRibo-68 is main signature, and 68 presumably number of genes. The source does not explicitly say \"68 genes\" exactly? It says \"PanRibo-515 and OncoRibo-68\" and \"OncoRibo-68 gene set\". Could quote clause. Unit could \"genes\" perhaps inferred from \"gene set\" but not explicit that 68 is count. Yet replication of main finding could need reproduce AUC or HR, not number of signature genes. User says \"single numerical result\", \"headline number\" implies effect metric. So no.\n\nNeed perhaps evidence exact contiguous quote containing number. If false, evidence empty mandated. target_result can mention only qualitative. Let's answer JSON.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that higher RiBi scores were linked to worse outcomes and that elevated OncoRibo-68 expression often correlated with better survival in immune-checkpoint inhibitor-treated cohorts, but it provides no headline numerical result for the main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that higher RiBi scores were linked to worse outcomes and that elevated OncoRibo-68 expression often correlated with better survival in immune-checkpoint inhibitor-treated cohorts, but it provides no headline numerical result for the main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:30:17.427269+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "No headline numerical result is stated in the supplied text; the main finding is that higher RiBi scores, represented by PanRibo-515 and OncoRibo-68, were linked to worse outcomes.", "minimax_alt": "unclear—the source text states no headline numerical result. It reports qualitative associations: higher PanRibo-515/OncoRibo-68 scores were linked to worse outcomes, while elevated OncoRibo-68 expression was often associated with better survival in the named immune checkpoint inhibitor cohorts.", "decisive": false}, "analysis_methods": {"minimax": ["TIDE biomarker comparison using receiver operating characteristic (ROC) curves and area under the curve (AUC) values", "Kaplan–Meier analyses", "log-rank test comparisons"], "minimax_alt": ["LASSO regression", "TIDE (Tumor Immune Dysfunction and Exclusion) web-tool analysis", "receiver operating characteristic (ROC) curve analysis", "area under the curve (AUC) analysis", "Kaplan–Meier analysis", "log-rank test"], "decisive": false}, "statistical_method": {"minimax": "unclear", "minimax_alt": "Kaplan–Meier survival analysis with log-rank test comparisons for the ICI survival finding", "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:6f0b2e401e35fac775bb1a8b7db6d8d31357ba7100a94ae1c96f364b3f67d8f0", "type": "sep_package", "label": "SEP v1 package for pmid:40805273"}], "activities": [{"id": "activity:conversion:pmid:40805273", "type": "conversion", "used": ["package:6f0b2e401e35fac775bb1a8b7db6d8d31357ba7100a94ae1c96f364b3f67d8f0"], "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:40805273", "parent_hash": "sha256:e2a9e819c91627deafc55979519122eb219d34ee003592c1fa42f78c0fae64c0", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40805273 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:accession_absent", "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:40805273' 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":"2026-11-04T03:48:48+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}}}