{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40078640", "kind": "science-record", "revision": 3, "content_hash": "sha256:2ed86cdd7a796892d73b8a0d617735515ee7726286b972deff7b793d45046f77", "created_at": "2026-11-01T20:30:17Z", "updated_at": "2026-11-01T22:13:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Parkin characteristics and blood biomarkers of Parkinson's disease in WPBLC study.", "doi": "10.3389/fnagi.2025.1511272", "pmid": "40078640", "authors": ["Haijun He", "Xi Xiong", "Yi Zheng", "Jialong Hou", "Tao Jiang", "Weiwei Quan", "Jiani Huang", "Jiaxue Xu", "Keke Chen", "Jingjing Qian", "Jinlai Cai", "Yao Lu", "Mengjia Lian", "Chenglong Xie", "Ji Luo"], "journal": "Frontiers in aging neuroscience", "year": 2025, "abstract": "Background: The exact mechanisms of PD are unclear, but Parkin-mediated mitophagy dysfunction is believed to play a key role. We investigated whether blood levels of Parkin and other biomarkers are linked to the risk of developing PD.\nMethods: Baseline blood measures of Parkin and other biomarkers, including Homocysteine, carcinoembryonic antigen, Urea, total proteins, total cholesterol, creatine kinase, and albumin, were collected from 197 clinically diagnosed Parkinson's disease participants and 107 age-matched healthy controls in Wenzhou Parkinson's Biomarkers and Living Characteristics study. We conducted bioinformatics analysis using three datasets from the GEO database: GSE90514 (Cohort 1: PD = 4, HC = 4), GSE7621 (Cohort 2: PD = 16, HC = 9), and GSE205450 (Cohort 3: PD = 69, HC = 81).\nResults: Using a bioinformatic approach, we identified dysregulated biological processes in PD patients with PRKN mutations. Compared to controls, significant abnormalities were observed in blood levels of Parkin, Hcy, total proteins, urea, albumin, and CEA in PD patients. A model incorporating Parkin, Hcy, total proteins, and urea effectively distinguished PD from healthy controls, achieving a higher accuracy (AUC 0.841) than other biomarker combinations. Gene set enrichment analysis suggested that pathways such as PINK1-Parkin-mediated mitophagy, urea cycle, cysteine degradation, and riboflavin metabolism may be involved in PRKN mutation. Additionally, the link between Parkin and PD was partially mediated by CEA and albumin, not by Hcy, total proteins, or urea.\nConclusion: Our findings indicate that blood Parkin levels may be a minimally invasive biomarker for PD diagnosis. The model, which included Parkin, Hcy, total proteins, and urea, effectively distinguished PD from HC with greater accuracy.", "claims": [{"id": "claim-method", "statement": "The Random Forest (RF) classifier and Least Absolute Shrinkage And Selection Operator (LASSO) regression were employed to identify effective blood biomarkers for distinguishing PD from HC participants.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40078640", "locator": "sections[6] \"Statistical analyses\" paragraph 2", "quote": "The Random Forest (RF) classifier and Least Absolute Shrinkage And Selection Operator (LASSO) regression were employed to identify effective blood biomarkers for distinguishing PD from HC participants."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40078640", "locator": "sections[25] \"Data availability statement\" paragraph 2", "quote": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The model, which included Parkin, Hcy, total proteins, and urea, effectively distinguished PD from HC with greater accuracy.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40078640", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "The model, which included Parkin, Hcy, total proteins, and urea, effectively distinguished PD from HC with greater accuracy."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The model, which included Parkin, Hcy, total proteins, and urea, effectively distinguished PD from HC with greater accuracy.", "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:40078640"], "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:GSE205450"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:GSE205450"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40078640", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fnagi.2025.1511272", "sha256": "sha256:18ad336724b05de958ca63ab44007ea7d1302c2c748929ca5c88250334fb0765", "bytes": 48115, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fnagi.2025.1511272", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11897490", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE205450", "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=GSE205450", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE205450", "version": null, "note": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6212891", "GSM6212892", "GSM6212893", "GSM6212894", "GSM6212895", "GSM6212896", "GSM6212897", "GSM6212898", "GSM6212899", "GSM6212900", "GSM6212901", "GSM6212902", "GSM6212903", "GSM6212904", "GSM6212905", "GSM6212906", "GSM6212907", "GSM6212908", "GSM6212909", "GSM6212910", "GSM6212911", "GSM6212912", "GSM6212913", "GSM6212914", "GSM6212915", "GSM6212916", "GSM6212917", "GSM6212918", "GSM6212919", "GSM6212920", "GSM6212921", "GSM6212922", "GSM6212923", "GSM6212924", "GSM6212925", "GSM6212926", "GSM6212927", "GSM6212928", "GSM6212929", "GSM6212930", "GSM6212931", "GSM6212932", "GSM6212933", "GSM6212934", "GSM6212935", "GSM6212936", "GSM6212937", "GSM6212938", "GSM6212939", "GSM6212940", "GSM6212941", "GSM6212942", "GSM6212943", "GSM6212944", "GSM6212945", "GSM6212946", "GSM6212947", "GSM6212948", "GSM6212949", "GSM6212950", "GSM6212951", "GSM6212952", "GSM6212953", "GSM6212954", "GSM6212955", "GSM6212956", "GSM6212957", "GSM6212958", "GSM6212959", "GSM6212960", "GSM6212961", "GSM6212962", "GSM6212963", "GSM6212964", "GSM6212965", "GSM6212966", "GSM6212967", "GSM6212968", "GSM6212969", "GSM6212970", "GSM6212971", "GSM6212972", "GSM6212973", "GSM6212974", "GSM6212975", "GSM6212976", "GSM6212977", "GSM6212978", "GSM6212979", "GSM6212980", "GSM6212981", "GSM6212982", "GSM6212983", "GSM6212984", "GSM6212985", "GSM6212986", "GSM6212987", "GSM6212988", "GSM6212989", "GSM6212990", "GSM6212991", "GSM6212992", "GSM6212993", "GSM6212994", "GSM6212995", "GSM6212996", "GSM6212997", "GSM6212998", "GSM6212999", "GSM6213000", "GSM6213001", "GSM6213002", "GSM6213003", "GSM6213004", "GSM6213005", "GSM6213006", "GSM6213007", "GSM6213008", "GSM6213009", "GSM6213010", "GSM6213011", "GSM6213012", "GSM6213013", "GSM6213014", "GSM6213015", "GSM6213016", "GSM6213017", "GSM6213018", "GSM6213019", "GSM6213020", "GSM6213021", "GSM6213022", "GSM6213023", "GSM6213024", "GSM6213025", "GSM6213026", "GSM6213027", "GSM6213028", "GSM6213029", "GSM6213030", "GSM6213031", "GSM6213032", "GSM6213033", "GSM6213034", "GSM6213035", "GSM6213036", "GSM6213037", "GSM6213038", "GSM6213039", "GSM6213040"], "sample_count": 150, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Transcriptome changes in human post-mortem PD striatum", "resolution_checked_at": "2026-11-01T20:16:08Z", "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": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "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}}, {"id": "data:geo:GSE90514", "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=GSE90514", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE90514", "version": null, "note": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2405870", "GSM2405871", "GSM2405872", "GSM2405873", "GSM2405874", "GSM2405875", "GSM2405876", "GSM2405877"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Transcriptomic alterations in fibroblasts from Parkinson's disease patients carrying Parkin mutations", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE205450 not downloaded", "asset:data:geo:GSE205450 licence not read", "asset:data:geo:GSE7621 not downloaded", "asset:data:geo:GSE7621 licence not read", "asset:data:geo:GSE90514 not downloaded", "asset:data:geo:GSE90514 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Random Forest (RF) classifier and Least Absolute Shrinkage And Selection Operator (LASSO) regression were employed to identify effective blood biomarkers for distinguishing PD from HC participants."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-3", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor", "method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["GSE90514", "GSE7621", "GSE205450"], "resolved_accessions": ["GSE90514", "GSE7621", "GSE205450"], "statements": ["The data that support the findings of this study are available from the corresponding author upon reasonable request. Transcriptomic RNAseq datasets analysed in this study are available on NCBI GEO (Accession number: GSE90514, GSE7621 and GSE205450)."], "basis": "The paper names GSE90514, GSE7621, GSE205450 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40078640", "data:geo:GSE205450"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE205450"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:48:20Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13187, "completion_tokens": 1601, "cached_tokens": 0}}, "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:40078640", "type": "paper", "label": "pmid:40078640"}, {"id": "source:pmid:40078640", "type": "manuscript", "label": "PMID 40078640 full text"}, {"id": "data:geo:GSE205450", "type": "dataset", "label": "GEO GSE205450"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40078640", "type": "paper", "label": "pmid:40078640"}, {"id": "source:pmid:40078640", "type": "manuscript", "label": "PMID 40078640 full text"}, {"id": "data:geo:GSE205450", "type": "dataset", "label": "GEO GSE205450"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40078640", "type": "extraction", "used": ["source:pmid:40078640"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE205450", "type": "accession_resolution", "used": ["data:geo:GSE205450"], "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:40078640", "parent_hash": "sha256:8a7bcb3eada7452bbf848fdef15ab56cbadb1f54a8008a5877a2017d03bc8bfc", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE205450 licence not read", "asset:data:geo:GSE205450 not downloaded", "asset:data:geo:GSE7621 licence not read", "asset:data:geo:GSE7621 not downloaded", "asset:data:geo:GSE90514 licence not read", "asset:data:geo:GSE90514 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["DEGs using high-quality bulk RNA sequencing (RNA-seq) data from the GSE90514. Heat map showing ex", "3 (Figures 2H,I). Importantly, based on the RNA-seq analysis, the transcriptional levels of thes", "lar analysis of DEGs using high-quality bulk RNA sequencing (RNA-seq) data from the GSE90514. Heat map s"], "order_basis": "paper_text_order:6321", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The Random Forest (RF) classifier and Least Absolute Shrinkage And Selection Operator (LASSO) regression were employed to identify effective blood biomarkers for distinguishing PD from HC participants."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:23:11+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}}}