{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27015167", "kind": "science-record", "revision": 2, "content_hash": "sha256:56ccc1c29f6e42a3a9d5e99f5b3341395b3775c072e22e1bbbf776bb731cf5ac", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:31Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Murine Double Minute 2 SNP T309G Polymorphism and Urinary Tract Cancer Risk", "doi": "10.1097/MD.0000000000002941", "pmid": "27015167", "authors": null, "journal": "Medicine", "year": 2016, "abstract": null, "claims": [{"id": "claim-1", "statement": "the pooled odds ratio for urinary tract cancer risk associated with the MDM2 T309G polymorphism", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the pooled odds ratio for urinary tract cancer risk associated with the MDM2 T309G polymorphism", "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:27015167"], "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": "method:fixed_effects_pool", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the source data behind the published result in pmid:27015167"], "outputs": ["the registered result"], "instruments": [], "reagents": []}, {"id": "provide_capability_bench_workcell", "order": 4, "name": "Provide General bench workcell (liquid transfer, plate handling, incubation)", "kind": "computational", "state": "blocked", "blocked_on": "instrument not yet purchased", "description": "Make this capability available to the experiment: amplicon_seq, animal_model, apoptosis_assay, cell_culture, cell_imaging, chip_seq, clinical_cohort, clinical_trial, elisa, flow_cytometry, ihc, image_quantification, mass_spectrometry, methylation_array, microarray, qpcr, rna_seq, transfection, western_blot", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": [], "instruments": [], "reagents": []}], "materials": ["the source data behind the published result in pmid:27015167", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:fixed_effects_pool"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27015167", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000002941", "sha256": "sha256:2d6a6e76143df64fdc57264c95ef08565d48a633299aadd76ab34ead579bedc2", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000002941", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind the published result in pmid:27015167", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind the published result in pmid:27015167", "structure": {"material_kind": "dataset", "access_state": "not_identified"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}, {"id": "asset:table:pmid:27015167:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aff0aaffd5e46fa9e5d7f773f68b65c67776db29ce9c3059e298f9aea256376c", "bytes": 191, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T1", "version": null, "note": "The Main Characteristics of Included Studies", "structure": {"pmcid": "PMC4998362", "section_index": 8, "section_title": "Study Characteristics", "row_count": 0, "column_count": 0}, "table": {"label": "TABLE 1", "caption": "The Main Characteristics of Included Studies", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[8]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:27015167:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8a61c1a7d4eb8f48be8314c6462afa743f4adcfdae4f4d226fadb2befe6dbf3e", "bytes": 199, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T2", "version": null, "note": "Distribution of MDM2 SNP T309G Genotypes and Alleles", "structure": {"pmcid": "PMC4998362", "section_index": 9, "section_title": "Quantitative Synthesis", "row_count": 0, "column_count": 0}, "table": {"label": "TABLE 2", "caption": "Distribution of MDM2 SNP T309G Genotypes and Alleles", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[9]/table-wrap[1]#T2"}}], "gaps": ["asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:27015167 not verified", "asset:source:pmid:27015167 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "meta_analysis", "specific": "meta-analysis", "label": "", "dsl_operations": [], "missing_operations": [], "expressible": false, "parameters": {}, "data_shapes": [], "evidence": {"score": 0.0, "band": "low", "quote": "The included studies met the following criteria: (1) research categories case-control study or a nested case-control study; (2) information evaluating the association between the MDM2 SNP309 and urinary tract cancers risk; (3) studies with sufficient data to perform a meta-analysis. The following studies were excluded: no control population, insufficient available data, duplicated articles, and the genotype distribution of the control population was departure from Hardy–Weinberg equilibrium."}}], "targets": [], "gaps": ["method.corpus_not_determined", "method.operations", "targets"]}, "capability": {"state": "partial", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}, {"capability_id": "capability:bench_workcell", "label": "General bench workcell (liquid transfer, plate handling, incubation)", "assay_families": ["amplicon_seq", "animal_model", "apoptosis_assay", "cell_culture", "cell_imaging", "chip_seq", "clinical_cohort", "clinical_trial", "elisa", "flow_cytometry", "ihc", "image_quantification", "mass_spectrometry", "methylation_array", "microarray", "qpcr", "rna_seq", "transfection", "western_blot"], "availability_state": "purchasable", "tier_unlocked": "R3", "candidate": "Supplier-neutral 96/384-well liquid handler"}, {"capability_id": "capability:animal_model", "label": "In-vivo animal model work", "assay_families": ["animal_model"], "availability_state": "unavailable", "tier_unlocked": "R4", "candidate": null}], "gaps": ["capability:capability:animal_model unavailable", "capability:capability:bench_workcell purchasable"]}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "capability", "blocked_on": "capability:animal_model", "axes": {"method": {"axis": "method", "tier": "R4", "blocker": "method:not_determinable", "detail": {"outcome": "not_determinable", "reason": "No specific statistical method is stated in recognised wording. Full methods review is required.", "basis": "The title, abstract and methods text do not carry the method, so a person has to read the paper before it can be programmed."}}, "capability": {"axis": "capability", "tier": "R4", "blocker": "capability:animal_model", "detail": {"families": ["animal_model"], "capability_id": "capability:animal_model", "availability_state": "unavailable", "considered": [{"family": "animal_model", "capability_id": "capability:bench_workcell", "availability_state": "purchasable", "tier_unlocked": "R3"}, {"family": "animal_model", "capability_id": "capability:animal_model", "availability_state": "unavailable", "tier_unlocked": "R4"}], "basis": "The equipment register names no animal-facility capability at any gate. In-vivo work needs a specialist facility and an ethical approval, which is a collaboration rather than a purchase."}}, "data": {"axis": "data", "tier": "R4", "blocker": "data:accession_absent", "detail": {"applies": true, "reachable": false, "basis": "The record names no repository accession and no data-availability statement, so the source data has to be requested from the authors."}}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:27015167", "asset:table:pmid:27015167:1", "asset:table:pmid:27015167:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": ["capability:bench_workcell", "capability:animal_model"], "data_gaps": ["source:pmid:27015167", "materials:the source data behind the published result in pmid:27015167", "materials:the analysis programme that recomputes the published estimate"]}, "gaps": ["capability:animal_model"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "de843c6399af29e5b4ab7e6a8c27ba3b222dda7d6a9e84fa548bc6bff1f0b2a6", "source_hash": "2d6a6e76143df64fdc57264c95ef08565d48a633299aadd76ab34ead579bedc2", "raw_response_sha256": "sha256:ea96d070ea933ad39ab1c6877284ea7798167a3d640a991c5121c8d0cd1f9a49", "raw_response_chars": 2634}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "8b160b1db727cfa41edadd3577760008052e9986197179613f620754cb76abde", "source_hash": "2d6a6e76143df64fdc57264c95ef08565d48a633299aadd76ab34ead579bedc2", "raw_response_sha256": "sha256:f7ff3f3bc1920970771d0b0ddf57ab93d0beb45c01fd79516932f4855a82a127", "raw_response_chars": 4640}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "aad3407e61e48ea7b91ceafa2e69b3c9f56343861d0e836fdd192bbfc5a4aa05", "source_hash": "2d6a6e76143df64fdc57264c95ef08565d48a633299aadd76ab34ead579bedc2", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The paper does not state a single pooled odds ratio for urinary tract cancer overall; it reports separate pooled odds ratios for prostate cancer, bladder cancer, and kidney cancer under allele, genotype, dominant, and recessive genetic models.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The paper does not state a single pooled odds ratio for urinary tract cancer overall; it reports separate pooled odds ratios for prostate cancer, bladder cancer, and kidney cancer under allele, genotype, dominant, and recessive genetic models.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T14:33:03.435477+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "7a1cdb78da9f4185ec18838e82cdef4a3abbf69865de9801d9c117201fb47ebb", "source_hash": "2d6a6e76143df64fdc57264c95ef08565d48a633299aadd76ab34ead579bedc2", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The paper reports separate pooled odds ratios for prostate, bladder, and kidney cancer under specified genetic contrasts, but it does not state a single pooled odds ratio for urinary tract cancer overall.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The paper reports separate pooled odds ratios for prostate, bladder, and kidney cancer under specified genetic contrasts, but it does not state a single pooled odds ratio for urinary tract cancer overall.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T14:33:49.517832+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax-m3-1-flash": "No single pooled odds ratio for urinary tract cancer overall is reported. The paper reports tumor-specific pooled ORs: for kidney cancer, allele contrast OR = 1.24 (95% CI 1.05–1.46), GG genotype OR = 1.57 (95% CI 1.11–2.20), dominant model OR = 1.30 (95% CI 1.00–1.68), and recessive model OR = 1.37 (95% CI 1.02–1.83); for prostate cancer and bladder cancer, the reported pooled ORs were not statistically significant.", "minimax-m3": "No single pooled OR for urinary tract cancer as one combined outcome is reported. The source reports subtype- and contrast-specific estimates. For kidney cancer, random-effects pooling of 3 studies gave an allele-contrast OR of 1.24 (95% CI 1.05–1.46; P = 0.01), a GG-genotype OR of 1.57 (95% CI 1.11–2.20; P = 0.01), a dominant-model OR of 1.30 (95% CI 1.00–1.68; P = 0.05), and a recessive-model OR of 1.37 (95% CI 1.02–1.83; P = 0.04). Prostate-cancer pooled ORs were 0.96, 0.93, 1.00, and 0.93 for the allele, GG, recessive, and dominant contrasts, respectively, and were nonsignificant. Bladder-cancer pooled ORs were 1.06, 1.12, 1.03, and 1.12 for the allele, GG, dominant, and recessive contrasts, respectively, and were nonsignificant.", "decisive": false}, "analysis_methods": {"minimax-m3-1-flash": ["Systematic review and meta-analysis of case-control and nested case-control studies", "Pooled odds ratios with 95% confidence intervals", "Random-effects pooling", "Mantel–Haenszel fixed-effects pooling", "DerSimonian–Laird random-effects pooling", "I²-test and chi-square test for heterogeneity", "Begg's funnel plot and Egger's test for publication bias", "Review Manager 5.0", "Stata 11.0"], "minimax-m3": ["Systematic review and meta-analysis of eligible case-control and nested case-control studies", "Pooled odds ratios with 95% confidence intervals under allele, homozygous, dominant, and recessive genetic-model contrasts", "Mantel–Haenszel fixed-effects model and DerSimonian–Laird random-effects model", "I²-test and chi-square test for between-study heterogeneity", "Subgroup analyses by ethnicity and study design", "Begg's funnel plots and Egger's linear regression test for publication bias", "Review Manager version 5.0 and Stata version 11.0"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["The meta-analysis included 18 studies examining the association between MDM2 T309G and urinary tract cancer risk.", "For kidney cancer, a random-effects model showed increased pooled odds ratios for the allele contrast, GG genotype, dominant genetic model, and recessive genetic model.", "The authors concluded that MDM2 T309G was associated with increased kidney cancer risk but was not associated with prostate cancer or bladder cancer risk.", "The paper does not provide a single pooled OR combining kidney, prostate, and bladder cancers into an overall urinary tract cancer estimate."], "minimax-m3": ["The meta-analysis included 18 eligible studies.", "The authors found no significant association between MDM2 SNP309 and prostate or bladder cancer risk.", "The authors reported positive associations between MDM2 SNP309 and kidney cancer risk under all four genetic contrasts.", "The kidney-cancer pooled estimates were obtained using a random-effects model.", "The kidney-cancer analysis included 3 studies with 567 cases and 663 controls.", "The authors concluded that the meta-analysis suggested increased MDM2 SNP T309G risk in renal cancer but no association with prostate or bladder cancer."], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "source_claims", "target_result"]}, "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": null, "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:d917632049b90514a05dd22eddf56e41f77b8d226125ff2326c1c1c1e7504600", "type": "sep_package", "label": "SEP v1 package for pmid:27015167"}], "activities": [{"id": "activity:conversion:pmid:27015167", "type": "conversion", "used": ["package:d917632049b90514a05dd22eddf56e41f77b8d226125ff2326c1c1c1e7504600"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"id": "agent:minimax-m3-1-flash", "type": "model", "label": "minimax-m3-1-flash"}, {"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:27015167", "parent_hash": "sha256:2b3a63d56306d721474fbf7286ca5eebb3ce42f2664eb79aaff0aea864c7d4e1", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:27015167 not verified", "asset:source:pmid:27015167 not verified", "authors", "capability:animal_model", "capability:capability:animal_model unavailable", "capability:capability:bench_workcell purchasable", "execution.not_run", "method.corpus_not_determined", "method.operations", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:accession_absent", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:fixed_effects_pool", "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":"2026-11-04T02:48:17+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}}}