{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25680115", "kind": "science-record", "revision": 2, "content_hash": "sha256:b16b0ccacf6a739c4a817cb1c1d09a479b5e18ec39b2529ce3e96a0d6c5d0cb2", "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": "Association between Glu504Lys Polymorphism of ALDH2 Gene and Cancer Risk: A Meta-Analysis", "doi": "10.1371/journal.pone.0117173", "pmid": "25680115", "authors": null, "journal": "PLoS ONE", "year": 2015, "abstract": null, "claims": [{"id": "claim-1", "statement": "the pooled odds ratio for overall cancer risk in carriers of the ALDH2 Glu504Lys (Lys+) genotype compared with Glu/Glu", "kind": "quantitative", "state": "complete", "target": {"value": 1.2, "unit": "odds ratio", "tolerance": null, "source": "chars 702-868 of source sha256 c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59"}, "evidence": [{"asset": "source:pmid:25680115", "locator": "chars 702-868 of source sha256 c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59", "quote": "The comparison of genotypes Lys+ (Lys/Lys and Lys/Glu) with Glu/Glu yielded a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%)."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the pooled odds ratio for overall cancer risk in carriers of the ALDH2 Glu504Lys (Lys+) genotype compared with Glu/Glu", "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:25680115"], "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 analysis programme that recomputes the published estimate"], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": ["the source data behind pmid:25680115, which the paper says are within the paper and its supporting information", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:fixed_effects_pool"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:25680115", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0117173", "sha256": "sha256:c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0117173", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind pmid:25680115, which the paper says are within the paper and its supporting information", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind pmid:25680115, which the paper says are within the paper and its supporting information", "structure": {"material_kind": "dataset", "access_state": "named_not_verified"}}, {"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": "data:availability", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "All relevant data are within the paper and its Supporting Information files.", "structure": {"access_route": "within_paper_only", "location": "custom-meta: Data Availability"}}, {"id": "asset:table:pmid:25680115:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2aa84f7f9a597e9e16032976171057f6c78ee47230189d26752f76fa954225e8", "bytes": 246, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#pone.0117173.t001", "version": null, "note": "Characteristics of studies included in ALDH2 Glu504Lys polymorphism and cancer risk.", "structure": {"pmcid": "PMC4334541", "section_index": 8, "section_title": "Studies and population", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Characteristics of studies included in ALDH2 Glu504Lys polymorphism and cancer risk.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[8]/table-wrap[1]#pone.0117173.t001"}}, {"id": "asset:table:pmid:25680115:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:17508a5fdeb36e5a8643d107f2262e8084497caf77db902c8a7fc86fc2eaae7f", "bytes": 237, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#pone.0117173.t002", "version": null, "note": "Stratification analyses of the ALDH2 Glu504Lys polymorphism on cancer risk.", "structure": {"pmcid": "PMC4334541", "section_index": 9, "section_title": "Pooled analysis", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Stratification analyses of the ALDH2 Glu504Lys polymorphism on cancer risk.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[9]/table-wrap[1]#pone.0117173.t002"}}], "gaps": ["asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:25680115, which the paper says are within the paper and its supporting information not verified", "asset:source:pmid:25680115 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "meta_analysis", "specific": "random-effects", "label": "", "dsl_operations": [], "missing_operations": [], "expressible": false, "parameters": {}, "data_shapes": [], "evidence": {"score": 0.0, "band": "low", "quote": "The strength of the association between the ALDH2 Glu504Lys polymorphism and cancer risk was measured by odds ratios (ORs) with their 95% confidence intervals (95%CI). The statistical significance of pooled ORs was assessed by the Z-test. Heterogeneity was assessed by the I 2 statistic, which was documented for the percentage of the observed between-study variability due to heterogeneity rather than chance with the ranges of 0 to 100% [I 2 = 0–25%, no heterogeneity; I 2 = 25–50%, moderate heterogeneity; I 2 = 50–75%, large heterogeneity; I 2 = 75–100%, extreme heterogeneity] [12]. When the Q test was significant (P<0.05) or I 2>50%, indicating the presence of heterogeneity, a random-effects model (the DerSimonian & Laird method) was used [13]; otherwise, the fixed-effects model (the Mantel-Haenszel method) was used [14]. Sensitivity analysis was performed by excluding the studies that the genotype distribution in controls was not in HWE or which did not provide the three genotypes in controls to evaluate the stability of the results. Statistical analysis was conducted using the software Review Manager (V5.2) for Mac Os X."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 1.2, "unit": "odds ratio", "tolerance": null, "state": "complete"}], "gaps": ["method.corpus_not_determined", "method.operations"]}, "capability": {"state": "complete", "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"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "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": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "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:25680115", "asset:table:pmid:25680115:1", "asset:table:pmid:25680115:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": [], "data_gaps": ["source:pmid:25680115", "materials:the source data behind pmid:25680115, which the paper says are within the paper and its supporting information", "materials:the analysis programme that recomputes the published estimate", "data:availability"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "99c3c5a14e9a3b348db2e5f82739df9a92f2116b3a0196d8a886a517e3ebadd4", "source_hash": "c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59", "raw_response_sha256": "sha256:8f29c5f56dbb1b5ca9f84b770dec1925209141121b0a6f45151aab9cbe1e3e60", "raw_response_chars": 3166}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "811e386b062477552627d4aed6242514beb61f9ff4cbc5f7eb1b9aa397d709c0", "source_hash": "c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59", "raw_response_sha256": "sha256:c1372a82a77123a45ceb807f739e4b1a8d176b10dc9b851e2c7749fdcd35e797", "raw_response_chars": 4662}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "6b387a2aa45aaecf7b153fe6daa42a932c5ef1c1349af96aa5c9fd597827df3e", "source_hash": "c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59", "raw_response": "{\"parent_value\":1.2,\"unit\":\"OR\",\"evidence\":\"The comparison of genotypes Lys+ (Lys/Lys and Lys/Glu) with Glu/Glu yielded a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%).\",\"target_result\":\"Pooled odds ratio for overall cancer risk in carriers of the ALDH2 Glu504Lys (Lys+) genotype compared with Glu/Glu: OR = 1.20.\",\"number_stated\":true}", "reading": {"parent_value": 1.2, "unit": "OR", "evidence": "The comparison of genotypes Lys+ (Lys/Lys and Lys/Glu) with Glu/Glu yielded a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%).", "target_result": "Pooled odds ratio for overall cancer risk in carriers of the ALDH2 Glu504Lys (Lys+) genotype compared with Glu/Glu: OR = 1.20.", "number_stated": true, "source_locator": "chars 702-868 of source sha256 c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59"}, "recorded_at": "2026-10-31T14:31:41.689692+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "c94c401d8de9fdf2457117069be3f60707f22958df1371adb41b754ee3b1baa6", "source_hash": "c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59", "raw_response": "{\"parent_value\":1.20,\"unit\":\"odds ratio (OR)\",\"evidence\":\"In the genotypic model, the comparison of Lys+ with Glu/Glu genotype generated a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%; Table 2, Fig. 2).\",\"target_result\":\"Pooled odds ratio for overall cancer risk in ALDH2 Glu504Lys Lys+ carriers compared with Glu/Glu: 1.20.\",\"number_stated\":true}", "reading": {"parent_value": 1.2, "unit": "odds ratio (OR)", "evidence": "In the genotypic model, the comparison of Lys+ with Glu/Glu genotype generated a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%; Table 2, Fig. 2).", "target_result": "Pooled odds ratio for overall cancer risk in ALDH2 Glu504Lys Lys+ carriers compared with Glu/Glu: 1.20.", "number_stated": true, "source_locator": "chars 8565-8751 of source sha256 c2b64448683f34433c2505eda2cffad9aa23458a842ccb1c2097a16701c86a59"}, "recorded_at": "2026-10-31T14:31:46.507330+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax-m3-1-flash": "Pooled odds ratio for overall cancer risk in carriers of the ALDH2 Glu504Lys (Lys+) genotype compared with Glu/Glu: OR = 1.20 (95% CI 1.03–1.39), P = 0.02, I² = 92%.", "minimax-m3": "Pooled odds ratio for overall cancer risk in ALDH2 Glu504Lys Lys+ carriers (Lys/Lys or Lys/Glu) versus Glu/Glu: OR = 1.20 (95% CI 1.03–1.39, P = 0.02, I² = 92%), indicating a significant 20% increased risk.", "decisive": false}, "work_type": {"minimax-m3-1-flash": "review_or_method_without_reexecutible_result", "minimax-m3": "analysis_only_for_target", "decisive": true}, "analysis_methods": {"minimax-m3-1-flash": ["Meta-analysis of 53 case-control studies from 51 publications", "Genotypic comparison of Lys+ (Lys/Lys and Lys/Glu) with Glu/Glu", "Random-effects model using the DerSimonian–Laird method", "Hardy-Weinberg equilibrium testing using a chi-square test", "Heterogeneity assessment using the I² statistic", "Subgroup analyses by cancer type, country, study design, and sample size", "Sensitivity analysis", "Fail-safe number analysis for publication bias"], "minimax-m3": ["Meta-analysis of published case-control genotype data using the genotypic comparison of Lys+ (Lys/Lys and Lys/Glu) with Glu/Glu.", "Random-effects pooling with the DerSimonian–Laird method for the overall genotypic comparison because heterogeneity was present.", "Calculation of pooled odds ratios with 95% confidence intervals and assessment of pooled-OR significance using the Z-test.", "Assessment of between-study heterogeneity using the I² statistic and Q test.", "Testing of control genotype frequencies for Hardy-Weinberg equilibrium using a chi-square test.", "Subgroup analyses by cancer type, country, study design, and sample size.", "Sensitivity analyses excluding studies without Hardy-Weinberg equilibrium or with unavailable PHWE values.", "Publication-bias assessment using the fail-safe number (Nfs) at a significance level of 0.05.", "Statistical analysis using Review Manager (V5.2)."], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["The comparison of genotypes Lys+ (Lys/Lys and Lys/Glu) with Glu/Glu yielded a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%).", "In the genotypic model, the comparison of Lys+ with Glu/Glu genotype generated a significant 20% increased cancer risk (OR = 1.20, 95%CI: 1.03–1.39, P = 0.02, I2 = 92%; Table 2, Fig. 2).", "The pooled analysis was based on 51 case-control studies consisting of 16,774 cases and 32,060 controls.", "A random-effects model was used for the Lys+ versus Glu/Glu comparison because the pooled analysis showed significant heterogeneity.", "The overall pooled estimate was statistically significant at P = 0.02, but it had substantial heterogeneity (I² = 92%)."], "minimax-m3": ["The overall pooled genotypic comparison of Lys+ with Glu/Glu found a significant 20% increase in cancer risk, with OR = 1.20 (95% CI 1.03–1.39, P = 0.02, I² = 92%).", "The overall genotypic pooled comparison showed substantial heterogeneity (I² = 92%, P heterogeneity <0.00001), and a random-effects model was used.", "The reported pooled odds ratio was unchanged in sensitivity analyses excluding studies that were not in Hardy-Weinberg equilibrium or had unavailable PHWE values.", "The estimates were based on unadjusted odds ratios, leaving possible confounding by age and other factors.", "The authors could not perform a subgroup analysis by drinking status because sufficient original data were unavailable."], "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": "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:36199c26e8ac5a35d2f83da7debb0fb46977373a4d205849fc9818c29d416515", "type": "sep_package", "label": "SEP v1 package for pmid:25680115"}], "activities": [{"id": "activity:conversion:pmid:25680115", "type": "conversion", "used": ["package:36199c26e8ac5a35d2f83da7debb0fb46977373a4d205849fc9818c29d416515"], "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:25680115", "parent_hash": "sha256:a716cc201e4fd21426a3849e154a10bae9d8d5ffac64ffc7f84a4843d553038f", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:25680115, which the paper says are within the paper and its supporting information not verified", "asset:source:pmid:25680115 not verified", "authors", "execution.not_run", "method.corpus_not_determined", "method.operations", "method:not_determinable", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:fixed_effects_pool"]},"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":"2026-11-04T03:51:30+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}}}