{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38894850", "kind": "science-record", "revision": 3, "content_hash": "sha256:1f2407ca3caa22749850349e09279b4a10c434ac4572f6c7ca567039d4a219cc", "created_at": "2026-11-01T20:28:58Z", "updated_at": "2026-11-01T22:12:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics analysis of the potential receptor and therapeutic drugs for Alzheimer's disease with comorbid Parkinson's disease.", "doi": "10.3389/fnagi.2024.1411320", "pmid": "38894850", "authors": ["Xuerong Zhou", "Zhifan Liu", "Guiqin Bai", "Bai Dazhang", "Peilin Zhao", "Xiaoming Wang", "Guohui Jiang"], "journal": "Frontiers in aging neuroscience", "year": 2024, "abstract": "Background: Now, there are no sensitive biomarkers for improving Alzheimer's disease (AD) and comorbid Parkinson's disease (PD). The aim of the present study was to analyze differentially expressed genes (DEGs) in brain tissue from AD and PD patients via bioinformatics analysis, as well as to explore precise diagnostic and therapeutic targets for AD and comorbid PD.\nMethods: GFE122063 and GSE7621 data sets from GEO in NCBI, were used to screen differentially expressed genes (DEGs) for AD and PD, and identify the intersected genes, respectively. Intersected genes were analyzed by Gene Ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis. Then, STRING site and Cytoscape were used to construct a protein-protein interaction (PPI) network, CytoNCA algorithm to analyze and evaluate centrality, Mcode plug-in to analyze module, and Cytohubba to screen key genes. Combined GO-KEGG enrichment analysis with Cytoscape algorithm to screen the key gene in AD complicated with PD. Then, the DEGs for AD and PD were imported into the Association Map (CMap) online platform to screen out the top 10 small molecule drugs, and using molecular docking techniques to evaluate the interactions between small molecule drugs and key genes receptors.\nResults: In total, 231 upregulated genes and 300 downregulated genes were identified. GO analysis revealed that the DEGs were highly enriched in signal transduction, and KEGG analysis revealed that the DEGs were associated with the MAPK and PI3K-Akt signaling pathways. Epidermal growth factor receptor (EGFR) was identified as a potential receptor gene in AD and comorbid PD. EGFR was upregulated in both AD and PD, and the proteins that interact with EGFR were enriched in the Ras/Raf/MAPK and PI3K/Akt signaling pathways. Semagacestat was identified as a drug with therapeutic potential for treating AD complicated with PD. There was a high binding affinity between semagacestat and EGFRNTD, with seven hydrogen bonds and one hydrophobic bond.\nDiscussion: Semagacestat may improve the health of patients with AD complicated with PD through the regulation of the Ras/Raf/MAPK and PI3K/Akt signaling pathways by EGFR, providing evidence supporting the structural modification of semagacestat to develop a more effective drug for treating AD complicated with PD.", "claims": [{"id": "claim-method", "statement": "The differences in gene expression profiles between AD patient and PD patient samples were analyzed using the GEO2R online platform (http://ncbi.nlm.nih.gov/geo/geo2r).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38894850", "locator": "sections[4] \"Data sources, quality and variance analysis\" paragraph 2", "quote": "The differences in gene expression profiles between AD patient and PD patient samples were analyzed using the GEO2R online platform (http://ncbi.nlm.nih.gov/geo/geo2r)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38894850", "locator": "sections[21] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In total, 231 upregulated genes and 300 downregulated genes were identified.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38894850", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "GFE122063 and GSE7621 data sets from GEO in NCBI, were used to screen differentially expressed genes (DEGs) for AD and PD, and identify the intersected genes, respectively."}, {"asset": "source:pmid:38894850", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "In total, 231 upregulated genes and 300 downregulated genes were identified."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "In total, 231 upregulated genes and 300 downregulated genes were identified.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:38894850"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE122063"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE122063"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38894850", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fnagi.2024.1411320", "sha256": "sha256:a7947b5e148303b5eaff6c65ee49598c7fc0bce2f46e2d64aae4c34389f89710", "bytes": 31450, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fnagi.2024.1411320", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11185263", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE122063", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE122063", "version": null, "note": "Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3454053", "GSM3454054", "GSM3454055", "GSM3454056", "GSM3454057", "GSM3454058", "GSM3454059", "GSM3454060", "GSM3454061", "GSM3454062", "GSM3454063", "GSM3454064", "GSM3454065", "GSM3454066", "GSM3454067", "GSM3454068", "GSM3454069", "GSM3454070", "GSM3454071", "GSM3454072", "GSM3454073", "GSM3454074", "GSM3454075", "GSM3454076", "GSM3454077", "GSM3454078", "GSM3454079", "GSM3454080", "GSM3454081", "GSM3454082", "GSM3454083", "GSM3454084", "GSM3454085", "GSM3454086", "GSM3454087", "GSM3454088", "GSM3454089", "GSM3454090", "GSM3454091", "GSM3454092", "GSM3454093", "GSM3454094", "GSM3454095", "GSM3454096", "GSM3454097", "GSM3454098", "GSM3454099", "GSM3454100", "GSM3454101", "GSM3454102", "GSM3454103", "GSM3454104", "GSM3454105", "GSM3454106", "GSM3454107", "GSM3454108", "GSM3454109", "GSM3454110", "GSM3454111", "GSM3454112", "GSM3454113", "GSM3454114", "GSM3454115", "GSM3454116", "GSM3454117", "GSM3454118", "GSM3454119", "GSM3454120", "GSM3454121", "GSM3454122", "GSM3454123", "GSM3454124", "GSM3454125", "GSM3454126", "GSM3454127", "GSM3454128", "GSM3454129", "GSM3454130", "GSM3454131", "GSM3454132", "GSM3454133", "GSM3454134", "GSM3454135", "GSM3454136", "GSM3454137", "GSM3454138", "GSM3454139", "GSM3454140", "GSM3454141", "GSM3454142", "GSM3454143", "GSM3454144", "GSM3454145", "GSM3454146", "GSM3454147", "GSM3454148", "GSM3454149", "GSM3454150", "GSM3454151", "GSM3454152", "GSM3454153", "GSM3454154", "GSM3454155", "GSM3454156", "GSM3454157", "GSM3454158", "GSM3454159", "GSM3454160", "GSM3454161", "GSM3454162", "GSM3454163", "GSM3454164", "GSM3454165", "GSM3454166", "GSM3454167", "GSM3454168", "GSM3454169", "GSM3454170", "GSM3454171", "GSM3454172", "GSM3454173", "GSM3454174", "GSM3454175", "GSM3454176", "GSM3454177", "GSM3454178", "GSM3454179", "GSM3454180", "GSM3454181", "GSM3454182", "GSM3454183", "GSM3454184", "GSM3454185", "GSM3454186", "GSM3454187", "GSM3454188"], "sample_count": 136, "group_sizes": null, "group_sizes_basis": null, "platform": "16699", "taxon": "Homo sapiens", "title": "Dementia Comparison: VaD vs. AD vs. Controls", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE7621", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7621", "version": null, "note": "Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM184354", "GSM184355", "GSM184356", "GSM184357", "GSM184358", "GSM184359", "GSM184360", "GSM184361", "GSM184362", "GSM184363", "GSM184364", "GSM184365", "GSM184366", "GSM184367", "GSM184368", "GSM184369", "GSM184370", "GSM184371", "GSM184372", "GSM184373", "GSM184374", "GSM184375", "GSM184376", "GSM184377", "GSM184378"], "sample_count": 25, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of substantia nigra from postmortem human brain of Parkinson's disease patients (PD)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE122063 not downloaded", "asset:data:geo:GSE122063 licence not read", "asset:data:geo:GSE7621 not downloaded", "asset:data:geo:GSE7621 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-3", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "centrality"}}, {"id": "method-4", "family": null, "specific": null, "label": "GEO2R online platform", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The differences in gene expression profiles between AD patient and PD patient samples were analyzed using the GEO2R online platform (http://ncbi.nlm.nih.gov/geo/geo2r)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE122063", "GSE7621"], "resolved_accessions": ["GSE122063", "GSE7621"], "statements": ["Publicly available datasets were analyzed in this study. These data may be found in the GSE122063 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE122063) and GSE7621 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7621) datasets."], "basis": "The paper names GSE122063, GSE7621 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:38894850", "data:geo:GSE122063"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE122063"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:21:39Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9112, "completion_tokens": 1532, "cached_tokens": 128}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:38894850", "type": "paper", "label": "pmid:38894850"}, {"id": "source:pmid:38894850", "type": "manuscript", "label": "PMID 38894850 full text"}, {"id": "data:geo:GSE122063", "type": "dataset", "label": "GEO GSE122063"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38894850", "type": "paper", "label": "pmid:38894850"}, {"id": "source:pmid:38894850", "type": "manuscript", "label": "PMID 38894850 full text"}, {"id": "data:geo:GSE122063", "type": "dataset", "label": "GEO GSE122063"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38894850", "type": "extraction", "used": ["source:pmid:38894850"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE122063", "type": "accession_resolution", "used": ["data:geo:GSE122063"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:38894850", "parent_hash": "sha256:3a4f8132cc87c6fc59d1c34d14cd0581e892699773dac71cbb7e7f530f63130f", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE122063 licence not read", "asset:data:geo:GSE122063 not downloaded", "asset:data:geo:GSE7621 licence not read", "asset:data:geo:GSE7621 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T03:16:05+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}}}