{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23986641", "kind": "science-record", "revision": 1, "content_hash": "sha256:19cbb78b75aaad9b27ead715c91df850a07271620bb3a2dc5c22adba72e6c751", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T10:25:48Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Effect of transarterial chemoembolization with miriplatin plus epirubicin on local control of hepatocellular carcinoma: a retrospective comparison with miriplatin monotherapy", "doi": "10.2147/OTT.S49443", "pmid": "23986641", "authors": null, "journal": "OncoTargets and therapy", "year": 2013, "abstract": null, "claims": [{"id": "claim-1", "statement": "the 1-year local tumour control rate for transarterial chemoembolisation with miriplatin plus low-dose epirubicin, against miriplatin alone", "kind": "quantitative", "state": "complete", "target": {"value": 65.0, "unit": "percent", "tolerance": null, "source": "chars 953-1123 of source sha256 4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27"}, "evidence": [{"asset": "source:pmid:23986641", "locator": "chars 953-1123 of source sha256 4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27", "quote": "The local control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group, and 61% and 43% for the miriplatin group, respectively."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the 1-year local tumour control rate for transarterial chemoembolisation with miriplatin plus low-dose epirubicin, against miriplatin alone", "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:23986641"], "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:epidemiological_modelling_incidence_rate", "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:23986641"], "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:23986641", "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:epidemiological_modelling_incidence_rate"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:23986641", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/OTT.S49443", "sha256": "sha256:4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/OTT.S49443", "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:23986641", "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:23986641", "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"}}], "gaps": ["asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:23986641 not verified", "asset:source:pmid:23986641 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "log-rank", "label": "Survival analysis", "dsl_operations": ["glm_logit_fit", "logrank_test", "survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "We retrospectively analyzed the records of patients who underwent TACE using miriplatin plus low-dose epirubicin (30 patients, 61 nodules, August 2011–March 2012) and control patients who underwent TACE using miriplatin alone (36 patients, 70 nodules, June 2010–July 2011). The local control rate was compared between the two groups using the Kaplan–Meier estimator and the log-rank test. Factors affecting local tumor recurrence were analyzed using multivariate logistic regression analysis. Treatment-related toxicity was evaluated using the Common Terminology Criteria for Adverse Events."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 65.0, "unit": "percent", "tolerance": null, "state": "complete"}], "gaps": []}, "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:clinical_intervention", "label": "Clinical intervention and patient cohort access", "assay_families": ["clinical_trial", "clinical_cohort"], "availability_state": "unavailable", "tier_unlocked": "R4", "candidate": null}], "gaps": ["capability:capability:bench_workcell purchasable", "capability:capability:clinical_intervention unavailable"]}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "capability", "blocked_on": "capability:clinical_intervention", "axes": {"method": {"axis": "method", "tier": "R1", "blocker": null, "detail": {"outcome": "determined", "family": "survival_analysis", "specific_method": "kaplan_meier", "required_operations": ["glm_logit_fit", "logrank_test", "survival_km"], "basis": "Every DSL operation this method needs already exists."}}, "capability": {"axis": "capability", "tier": "R4", "blocker": "capability:clinical_intervention", "detail": {"families": ["clinical_cohort"], "capability_id": "capability:clinical_intervention", "availability_state": "unavailable", "considered": [{"family": "clinical_cohort", "capability_id": "capability:bench_workcell", "availability_state": "purchasable", "tier_unlocked": "R3"}, {"family": "clinical_cohort", "capability_id": "capability:clinical_intervention", "availability_state": "unavailable", "tier_unlocked": "R4"}], "basis": "The equipment register names no clinical capability at any gate. Patient data and clinical interventions need consent, ethics and a site, 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": ["glm_logit_fit", "logrank_test", "survival_km"], "assets": ["source:pmid:23986641"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": ["capability:bench_workcell", "capability:clinical_intervention"], "data_gaps": ["source:pmid:23986641", "materials:the source data behind the published result in pmid:23986641", "materials:the analysis programme that recomputes the published estimate"]}, "gaps": ["capability:clinical_intervention"]}, "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": "f62c8e2b36815966416c568d62c7c438b269400c141c233533f4dd9c84c976d5", "source_hash": "4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27", "raw_response_sha256": "sha256:5cafd9527f8f7680f599239d73f66d950af9b17dfa530894767a4f93ae831f4c", "raw_response_chars": 1599}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "b14ed901b6535c976329fbd9346c47c4269092673ca14dd90c0b560d664deb6d", "source_hash": "4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27", "raw_response_sha256": "sha256:a3c8a587b70498f8994b6c169cfdcb386447414d626be9c9cecbeee9d16f6625", "raw_response_chars": 3280}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "8310022d052d9f7cb10911ab674c501315fa7b6202df7134f9b09eeddb5881b9", "source_hash": "4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27", "raw_response": "{\"parent_value\":65,\"unit\":\"%\",\"evidence\":\"The local control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group, and 61% and 43% for the miriplatin group, respectively.\",\"target_result\":\"65%\",\"number_stated\":true}", "reading": {"parent_value": 65, "unit": "%", "evidence": "The local control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group, and 61% and 43% for the miriplatin group, respectively.", "target_result": "65%", "number_stated": true, "source_locator": "chars 953-1123 of source sha256 4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27"}, "recorded_at": "2026-10-31T14:30:31.250814+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "7cfcb1e963bef52213043816f80f2f12547d16eab706b77875c3afb1bcab03ef", "source_hash": "4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27", "raw_response": "{\n  \"parent_value\": 65,\n  \"unit\": \"%\",\n  \"evidence\": \"The local control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group, and 61% and 43% for the miriplatin group, respectively.\",\n  \"target_result\": \"The 1-year local tumour control rate for transarterial chemoembolisation with miriplatin plus low-dose epirubicin was 65%.\",\n  \"number_stated\": true\n}", "reading": {"parent_value": 65, "unit": "%", "evidence": "The local control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group, and 61% and 43% for the miriplatin group, respectively.", "target_result": "The 1-year local tumour control rate for transarterial chemoembolisation with miriplatin plus low-dose epirubicin was 65%.", "number_stated": true, "source_locator": "chars 953-1123 of source sha256 4fd3e39c33eda037be809b2256c55f605b7e06a55f62bba451fbe99ebc431d27"}, "recorded_at": "2026-10-31T14:30:45.798721+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax-m3-1-flash": "At 1 year, the local tumour control rate was 65% for transarterial chemoembolisation with miriplatin plus low-dose epirubicin, compared with 43% for miriplatin alone.", "minimax-m3": "At 1 year, the local tumor control rate was 65% for TACE with miriplatin plus low-dose epirubicin versus 43% for TACE with miriplatin alone. The reported overall comparison favored the combination group (P = 0.038).", "decisive": false}, "physical_methods": {"minimax-m3-1-flash": ["Transarterial chemoembolisation with miriplatin plus low-dose epirubicin or miriplatin alone", "Dynamic contrast-enhanced CT or MRI every 1–3 months after TACE to assess local recurrence"], "minimax-m3": [], "decisive": false}, "analysis_methods": {"minimax-m3-1-flash": ["Kaplan–Meier estimator", "Log-rank test", "Multivariate Cox proportional hazards model with backward stepwise selection"], "minimax-m3": ["Kaplan–Meier estimator", "log-rank test", "univariate and multivariate analyses of local tumor recurrence", "Cox proportional hazards model with backward stepwise selection"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["The local control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group, and 61% and 43% for the miriplatin group, respectively.", "Local tumor control rates were significantly better in the miriplatin plus low-dose epirubicin group than in the miriplatin group (P = 0.038).", "Multivariate analysis showed that the addition of epirubicin was an independent factor associated with better local tumor control (hazard ratio 0.2, P = 0.001)."], "minimax-m3": ["The study retrospectively compared 30 patients with 61 nodules treated with miriplatin plus low-dose epirubicin against 36 patients with 70 nodules treated with miriplatin alone during different calendar periods.", "The local tumor control rates at 6 months and 1 year were 87% and 65% for the miriplatin plus low-dose epirubicin group and 61% and 43% for the miriplatin group, respectively.", "Local tumor control was significantly better in the miriplatin plus low-dose epirubicin group than in the miriplatin group (P = 0.038).", "In multivariate analysis, addition of epirubicin was an independent factor associated with better local tumor control (hazard ratio 0.2, P = 0.001).", "Median follow-up was 279.5 days for the miriplatin group and 294 days for the miriplatin plus epirubicin group.", "The authors noted possible selection and information bias, lack of histological confirmation, small sample size, more distal chemoembolization in the combination group, and a relatively short observation period for the combination group."], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "physical_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:8deee153412223468a646ba5a794d50c9ce0eaa9a068a57080bd0b787173a811", "type": "sep_package", "label": "SEP v1 package for pmid:23986641"}], "activities": [{"id": "activity:conversion:pmid:23986641", "type": "conversion", "used": ["package:8deee153412223468a646ba5a794d50c9ce0eaa9a068a57080bd0b787173a811"], "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": "cc289864-6cdd-4e1d-8b96-1b2539189d7d", "parent_hash": "8deee153412223468a646ba5a794d50c9ce0eaa9a068a57080bd0b787173a811", "fork_of": null, "generation": 1}, "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:23986641 not verified", "asset:source:pmid:23986641 not verified", "authors", "capability:capability:bench_workcell purchasable", "capability:capability:clinical_intervention unavailable", "capability:clinical_intervention", "execution.not_run", "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:epidemiological_modelling_incidence_rate"]},"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":"2026-11-04T01:30:43+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}}}