{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40133591", "kind": "science-record", "revision": 2, "content_hash": "sha256:317c3481b8c38ced3769b02b73907f5886e36c20a4771b5172fde76f7066afba", "created_at": "2026-11-01T10:25:50Z", "updated_at": "2026-11-01T14:01:38Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Prognostic impact of a senescence gene signature in multiple myeloma.", "doi": "10.1007/s11357-025-01622-9", "pmid": "40133591", "authors": null, "journal": "GeroScience", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40133591"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40133591", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40133591' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40133591", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s11357-025-01622-9", "sha256": "sha256:6e8bc084c799f8e7349cf6511dee4f45e7cc5d2e944a6575c186b5246e4262a7", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s11357-025-01622-9", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40133591:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6c8503c0cfd7232e411221e496397bbbdd91821790d5cdbc04f417c308b598f1", "bytes": 1945, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab1", "version": null, "note": "Demographic and clinical characteristics of multiple myeloma patients in the integrated database. All percentages were calculated as the portion of the total number of patients (n = 1416). Not all data were available for all patients. Molecular subtypes: CD1 — cases with IgH translocations activating CCND1 or CCND3; CD2 — IgH translocations activating CCND1 or CCND3, and the expression of the early B-cell markers CD20 and PAX5; HY, hyperdiploid subgroup; LB, low bone disease subgroup; MF — increased expression of c-MAF or MAFB; MS — upregulation of FGFR3 and/or MMSET; MY, myeloid-like subgroup; PR, proliferation subgroup [32]. Abbreviations: Isotypes: FLC, Free Light Chain; IGA, Immunoglobulin A; IGG, Immunoglobulin G; Light Chain, monoclonal light chains without accompanying heavy chains", "structure": {"pmcid": "PMC12181611", "section_index": 9, "section_title": "Database setup", "row_count": 36, "column_count": 3}, "table": {"label": "Table 1", "caption": "Demographic and clinical characteristics of multiple myeloma patients in the integrated database. All percentages were calculated as the portion of the total number of patients (n = 1416). Not all data were available for all patients. Molecular subtypes: CD1 — cases with IgH translocations activating CCND1 or CCND3; CD2 — IgH translocations activating CCND1 or CCND3, and the expression of the early B-cell markers CD20 and PAX5; HY, hyperdiploid subgroup; LB, low bone disease subgroup; MF — increased expression of c-MAF or MAFB; MS — upregulation of FGFR3 and/or MMSET; MY, myeloid-like subgroup; PR, proliferation subgroup [32]. Abbreviations: Isotypes: FLC, Free Light Chain; IGA, Immunoglobulin A; IGG, Immunoglobulin G; Light Chain, monoclonal light chains without accompanying heavy chains", "rows": [["Feature", "", "n (%)"], ["Included datasets", "", "4"], ["Total number of patients", "", "1416"], ["Survival"], ["", "Median follow up", "30 months"], ["", "Number of patients with an event", "433 (30.6%)"], ["Age (years)", "", "58.2 (± 9.8)"], ["Sex"], ["", "Male", "496 (35%)"], ["", "Female", "327 (23%)"], ["", "No data", "593 (42%)"], ["Race"], ["", "White", "726 (51.2%)"], ["", "African American", "22 (1.6%)"], ["", "No data", "668 (47.2%)"], ["Isotype"], ["", "FLC", "84 (5.9%)"], ["", "IGA", "187 (13.2%)"], ["", "IGG", "463 (32.7%)"], ["", "Light Chain", "51 (3.6%)"], ["Molecular subtypes"], ["", "CD1", "33 (2.3%)"], ["", "CD2", "73 (5.2%)"], ["", "HY", "127 (9%)"], ["", "LB", "64 (4.5%)"], ["", "MF", "39 (2.8%)"], ["", "MS", "70 (4.9%)"], ["", "MY", "127 9%)"], ["", "PR", "60 (4.2%)"], ["Treatment type"], ["", "Dexamethasone", "76 (5.3%)"], ["", "Total Therapy 2 (TT2)", "345 (24.4%)"], ["", "Total Therapy 3 (TT3)", "214 (15.1%)"], ["", "PS341 (bortezomib)", "188 (13.3%)"], ["", "Total Therapy 6 (TT6)", "55 (3.9%)"], ["", "Previously untreated", "538 (38%)"]], "row_count": 36, "column_count": 3, "numeric_cells": 33, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab1"}}], "gaps": ["asset:source:pmid:40133591 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40133591", "asset:table:pmid:40133591:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40133591"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "2b359075f68fb0a1096851fee634c9582ef3d26f3989c4fca08a1f13c09eaf4e", "source_hash": "6e8bc084c799f8e7349cf6511dee4f45e7cc5d2e944a6575c186b5246e4262a7", "raw_response_sha256": "sha256:cde851ff1deb3ba9f7b89e1fcf42bb9dd27030574747303c7c01f11c2b713283", "raw_response_chars": 35885}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "87fbcf0bce1a2622eaf59a6206643a0ac346a04a3f759b1b5724a78e7cd4131c", "source_hash": "6e8bc084c799f8e7349cf6511dee4f45e7cc5d2e944a6575c186b5246e4262a7", "raw_response": "{\"parent_value\":0.6,\"unit\":\"hazard ratio (HR)\",\"evidence\":\"The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).\",\"target_result\":\"The weighted SenMayo gene signature correlated with overall survival in multiple myeloma patients with an HR of 0.6.\",\"number_stated\":true}", "reading": {"parent_value": 0.6, "unit": "hazard ratio (HR)", "evidence": "The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).", "target_result": "The weighted SenMayo gene signature correlated with overall survival in multiple myeloma patients with an HR of 0.6.", "number_stated": true, "source_locator": "chars 1462-1599 of source sha256 6e8bc084c799f8e7349cf6511dee4f45e7cc5d2e944a6575c186b5246e4262a7"}, "recorded_at": "2026-10-31T15:35:33.824308+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "84ef77074f1e902c07326416fea8043afed511b78c8335a46703d96723dc10c9", "source_hash": "6e8bc084c799f8e7349cf6511dee4f45e7cc5d2e944a6575c186b5246e4262a7", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for main finding. Likely HR = 0.6. Unit? Paper prints HR dimensionless perhaps unit \"hazard ratio (HR)\"? Required parent_value number, unit string, evidence exact contiguous quote containing number, whole clause sufficient attribution. Need headline number only in target_result perhaps \"HR = 0.6\" or \"0.6\". Registered target \"headline numerical result paper states for main finding\". Abstract explicit: \"The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).\" Need quote whole clause attribution. parent_value 0.6. unit likely \"hazard ratio\" or \"HR\" as printed. User says unit must be unit paper prints. HR is a metric, perhaps unit \"HR\" or \"hazard ratio\". Evidence exact contiguous quote. Could quote full sentence. target_result perhaps \"HR = 0.6\". number_stated true.\n\nQuestion asks \"Report headline number only\" but schema has target_result. Maybe target_result string \"0.6\" only, while unit \"hazard ratio\". Evidence quote full clause. Need not calculate. Let's formulate valid JSON. Exact quote including en dashes etc. \"The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).\" Contiguous exact. Unit paper prints? It prints HR, not \"hazard ratio\" in result, though elsewhere \"univariate hazard ratios\". Better unit \"HR\". parent_value 0.6. target_result \"0.6\" to meet headline number only.</think>\n\n{\"parent_value\":0.6,\"unit\":\"HR\",\"evidence\":\"The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).\",\"target_result\":\"0.6\",\"number_stated\":true}", "reading": {"parent_value": 0.6, "unit": "HR", "evidence": "The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).", "target_result": "0.6", "number_stated": true, "source_locator": "chars 1462-1599 of source sha256 6e8bc084c799f8e7349cf6511dee4f45e7cc5d2e944a6575c186b5246e4262a7"}, "recorded_at": "2026-10-31T15:35:33.658939+00:00"}], "agreement": false, "disagreements": {"unit": {"minimax": "hazard ratio (HR)", "minimax_alt": "HR", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "reason": "a quoted statement is absent from the supplied text", "raw_response": "{\n  \"target_result\": \"The weighted SenMayo gene signature was associated with overall survival in multiple myeloma patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05), with the 75th percentile of survival reached at 36.1 months in the low-expression group and 57 months in the high-expression group.\",\n  \"work_type\": \"analysis_only_for_target\",\n  \"physical_methods\": [],\n  \"analysis_methods\": [\n    \"Univariate Cox regression\",\n    \"Kaplan–Meier survival analysis\",\n    \"Multivariate Cox regression\",\n    \"Benjamini–Hochberg false discovery rate correction\"\n  ],\n  \"statistical_method\": \"Univariate Cox regression\",\n  \"method_evidence\": \"Univariate Cox regression analysis was conducted to assess the prognostic significance of the SenMayo gene signature on overall survival (OS).\",\n  \"repositories\": [\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE24080\",\n      \"data_description\": \"Gene expression and clinical data from 1416 multiple myeloma patients obtained from four GEO datasets and integrated into a unified database.\",\n      \"evidence\": \"Gene expression and clinical data from 1416 MM patients were obtained from four GEO datasets (GSE24080, GSE4204, GSE57317, and GSE9782) and integrated into a unified database.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE4204\",\n      \"data_description\": \"Gene expression and clinical data from 1416 multiple myeloma patients obtained from four GEO datasets and integrated into a unified database.\",\n      \"evidence\": \"Gene expression and clinical data from 1416 MM patients were obtained from four GEO datasets (GSE24080, GSE4204, GSE57317, and GSE9782) and integrated into a unified database.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE57317\",\n      \"data_description\": \"Gene expression and clinical data from 1416 multiple myeloma patients obtained from four GEO datasets and integrated into a unified database.\",\n      \"evidence\": \"Gene expression and clinical data from 1416 MM patients were obtained from four GEO datasets (GSE24080, GSE4204, GSE57317, and GSE9782) and integrated into a unified database.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE9782\",\n      \"data_description\": \"Gene expression and clinical data from 1416 multiple myeloma patients obtained from four GEO datasets and integrated into a unified database.\",\n      \"evidence\": \"Gene expression and clinical data from 1416 MM patients were obtained from four GEO datasets (GSE24080, GSE4204, GSE57317, and GSE9782) and integrated into a unified database.\",\n      \"publicly_downloadable\": false\n    }\n  ],\n  \"availability_statement\": \"The paper states that the gene expression and clinical data were obtained from four GEO datasets, but it does not explicitly state that these data can be downloaded without an application, embargo, or request and does not state that they are available on request.\",\n  \"data_on_request\": false,\n  \"source_claims\": [\n    \"The weighted SenMayo gene signature was associated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).\",\n    \"The 75th percentile probability of survival was 36.1 months in the low-expression group and 57 months in the high-expression group.\",\n    \"Independent validation was reported for GSE4204, GSE24080, and GSE57317.\",\n    \"The senescence signature retained prognostic value in multivariate analyses paired with isotype and sex.\",\n    \"Neither molecular subtype nor the senescence signature achieved statistical significance in the multivariate model pairing them.\"\n  ],\n  \"missing_information\": [\n    \"The source does not explicitly describe the download or access conditions for the four GEO datasets.\",\n    \"The source does not state that the underlying data are available on request.\",\n    \"The source does not provide a separate repository or accession for the integrated unified database.\"\n  ],\n  \"evidence_spans\": [\n    \"The weighted SenMayo gene signature strongly correlated with overall survival in MM patients (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05).\",\n    \"The 75th percent probability of survival was reached at 36.1 months in the low-expression patient group, compared to 57 months in the high-expression group.\",\n    \"Independent validation in datasets with sufficient patient numbers confirmed the prognostic value of the SenMayo signature (GSE4204: HR = 0.58, 95% CI = 0.39–0.88, p = 0.0089; GSE24080: HR = 0.61, 95% CI = 0.45–0.83, p = 0.0012; GSE57317: HR = 0.25, 95% CI = 0.08–0.77, p = 0.0095).\",\n    \"Gene expression and clinical data from 1416 MM patients were obtained from four GEO datasets (GSE24080, GSE4204, GSE57317, and GSE9782) and integrated into a unified database.\",\n    \"The raw data were processed using MAS5 normalization, scaling adjustments, and JetSet probe selection to ensure cross-platform comparability.\",\n    \"The final gene signature was computed as a weighted mean expression of 122 senescence-associated genes, with weights derived from univariate hazard ratios.\",\n    \"Univariate Cox regression analysis was conducted to assess the prognostic significance of the SenMayo gene signature on overall survival (OS).\",\n    \"The Kaplan–Meier plotter was utilized to analyze the association between gene expression and survival [28, 29].\",\n    \"Then, false discovery rate (FDR) was controlled using the Benjamini–Hochberg method to account for multiple hypothesis testing [30, 31].\",\n    \"A multivariate Cox regression analysis was conducted to evaluate the combined effect of the senescence signature and key clinical parameters, including gender, isotypes, and molecular subgroups.\",\n    \"We identified a strong association with overall survival (HR = 0.6, 95% CI = 0.47–0.76, p = 1.7e-05; depicted in Fig. 1A), with a false discovery rate under 1%.\",\n    \"In the low-expression patient group, the 75th percent probability of survival was 36.1 months. In contrast, it was 57 months in the high-expression group, demonstrating a significantly prolonged survival.\",\n    \"The senescence signature demonstrated significant prognostic value when paired with isotype (p = 5.3e-13), which was also independently significant (p for isotype = 2.1e-04).\",\n    \"Of note, neither the molecular subtype nor the senescence signature achieves statistical significance when paired in a multivariate analysis.\"\n  ]\n}"}]}}, {"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:f4b83b8aa95c77cbd4e3ed0811b8dc1489b87036726aabe79b8cb0e276da195b", "type": "sep_package", "label": "SEP v1 package for pmid:40133591"}], "activities": [{"id": "activity:conversion:pmid:40133591", "type": "conversion", "used": ["package:f4b83b8aa95c77cbd4e3ed0811b8dc1489b87036726aabe79b8cb0e276da195b"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40133591", "parent_hash": "sha256:a0b4ed452fb686c4241efe1518600401f59a35e8b9c00c6d5a8a3c9f596a2bc9", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40133591 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40133591' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:06:44+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}}}