{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32925795", "kind": "science-record", "revision": 8, "content_hash": "sha256:270c462ec66a616125cc190420ef507ba14d91e85178350374ecc44cb27aee44", "created_at": "2026-11-01T15:41:10Z", "updated_at": "2026-11-01T22:45:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Investigating potential molecular mechanisms of serum exosomal miRNAs in colorectal cancer based on bioinformatics analysis.", "doi": "10.1097/MD.0000000000022199", "pmid": "32925795", "authors": ["Haifeng Wang", "Xiliang Chen", "Lingling Bao", "Xuede Zhang"], "journal": "Medicine", "year": 2020, "abstract": "Colorectal cancer (CRC) is the most common malignant gastrointestinal tumor worldwide. Serum exosomal microRNAs (miRNAs) play a critical role in tumor progression and metastasis. However, the underlying molecular mechanisms are poorly understood.The miRNAs expression profile (GSE39833) was downloaded from Gene Expression Omnibus (GEO) database. GEO2R was applied to screen the differentially expressed miRNAs (DEmiRNAs) between healthy and CRC serum exosome samples. The target genes of DEmiRNAs were predicted by starBase v3.0 online tool. The gene ontology (GO) and Kyoto Encyclopedia of Genomes pathway (KEGG) enrichment analysis were performed using the Database for Annotation, Visualization and Integrated Discovery (DAVID) online tool. The protein-protein interaction (PPI) network was established by the Search Tool for the Retrieval of Interacting Genes (STRING) visualized using Cytoscape software. Molecular Complex Detection (MCODE) and cytohubba plug-in were used to screen hub genes and gene modules.In total, 102 DEmiRNAs were identified including 67 upregulated and 35 downregulated DEmiRNAs, and 1437 target genes were predicted. GO analysis showed target genes of upregulated DEmiRNAs were significantly enriched in transcription regulation, protein binding, and ubiquitin protein ligase activity. While the target genes of downregulated DEmiRNAs were mainly involved in transcription from RNA polymerase II promoter, SMAD binding, and DNA binding. The KEGG pathway enrichment analyses showed target genes of upregulated DEmiRNAs were significantly enriched in proteoglycans in cancer, microRNAs in cancer, and phosphatidylinositol-3 kinases/Akt (PI3K-Akt) signaling pathway, while target genes of downregulated DEmiRNAs were mainly enriched in transforming growth factor-beta (TGF-beta) signaling pathway and proteoglycans in cancer. The genes of the top 3 modules were mainly enriched in ubiquitin mediated proteolysis, spliceosome, and mRNA surveillance pathway. According to the cytohubba plugin, 37 hub genes were selected, and 4 hub genes including phosphoinositide-3-kinase regulatory subunit 1 (PIK3R1), SRC, cell division cycle 42 (CDC42), E1A binding protein p300 (EP300) were identified by combining 8 ranked methods of cytohubba.The study provides a comprehensive analysis of exosomal DEmiRNAs and target genes regulatory network in CRC, which can better understand the roles of exosomal miRNAs in the development of CRC. However, these findings require further experimental validation in future studies.", "claims": [{"id": "claim-method", "statement": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/) is an online analysis tool for comparing 2 groups of GEO datasets based on the GEO query and Limma R packages.[18]", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32925795", "locator": "sections[4] \"Identification of DEmiRNAs\" paragraph 2", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/) is an online analysis tool for comparing 2 groups of GEO datasets based on the GEO query and Limma R packages.[18]"}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32925795", "locator": "sections[19] \"Footnotes\" paragraph 2", "quote": "All data generated or analyzed during this study are included in this published article [and its supplementary information files]."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:32925795"], "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:GSE39833"], "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:GSE39833"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32925795", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000022199", "sha256": "sha256:d775ccb17b90900fdb43a4c9a58140b9b79748b3156aac9ffa60d1949f47088e", "bytes": 45401, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000022199", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7489663", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE39833", "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=GSE39833", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE39833", "version": null, "note": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM980024", "GSM980025", "GSM980026", "GSM980027", "GSM980028", "GSM980029", "GSM980030", "GSM980031", "GSM980032", "GSM980033", "GSM980034", "GSM980035", "GSM980036", "GSM980037", "GSM980038", "GSM980039", "GSM980040", "GSM980041", "GSM980042", "GSM980043", "GSM980044", "GSM980045", "GSM980046", "GSM980047", "GSM980048", "GSM980049", "GSM980050", "GSM980051", "GSM980052", "GSM980053", "GSM980054", "GSM980055", "GSM980056", "GSM980057", "GSM980058", "GSM980059", "GSM980060", "GSM980061", "GSM980062", "GSM980063", "GSM980064", "GSM980065", "GSM980066", "GSM980067", "GSM980068", "GSM980069", "GSM980070", "GSM980071", "GSM980072", "GSM980073", "GSM980074", "GSM980075", "GSM980076", "GSM980077", "GSM980078", "GSM980079", "GSM980080", "GSM980081", "GSM980082", "GSM980083", "GSM980084", "GSM980085", "GSM980086", "GSM980087", "GSM980088", "GSM980089", "GSM980090", "GSM980091", "GSM980092", "GSM980093", "GSM980094", "GSM980095", "GSM980096", "GSM980097", "GSM980098", "GSM980099", "GSM980100", "GSM980101", "GSM980102", "GSM980103", "GSM980104", "GSM980105", "GSM980106", "GSM980107", "GSM980108", "GSM980109", "GSM980110", "GSM980111", "GSM980112", "GSM980113", "GSM980114", "GSM980115", "GSM980116", "GSM980117", "GSM980118", "GSM980119", "GSM980120", "GSM980121", "GSM980122"], "sample_count": 99, "group_sizes": null, "group_sizes_basis": null, "platform": "14767", "taxon": "Homo sapiens", "title": "microRNA profiles of serum exosomes in healthy controls and colorectal cancer patients-1", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32925795:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7a5b5ed19e0e0e8978cf6c1a8573fa866de04aaa6c5eb06f6a6f1af83177c1ec", "bytes": 220, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "Top 10 most significantly up or downregulated DEmiRNAs in serum exosome.", "structure": {"pmcid": "PMC7489663", "section_index": 4, "section_title": "Identification of DEmiRNAs", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Top 10 most significantly up or downregulated DEmiRNAs in serum exosome.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32925795:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7a5b5ed19e0e0e8978cf6c1a8573fa866de04aaa6c5eb06f6a6f1af83177c1ec", "bytes": 220, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "Top 10 most significantly up or downregulated DEmiRNAs in serum exosome.", "structure": {"pmcid": "PMC7489663", "section_index": 10, "section_title": "Identification of DEmiRNAs", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Top 10 most significantly up or downregulated DEmiRNAs in serum exosome.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32925795:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1321a5bfdcd46e70082780152e0cef03d8cf48474008dfc9d233bd16efef05f8", "bytes": 204, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Gene ontology analysis of DEmiRNAs target genes (Top 5).", "structure": {"pmcid": "PMC7489663", "section_index": 12, "section_title": "GO analysis of target genes", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Gene ontology analysis of DEmiRNAs target genes (Top 5).", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32925795:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6129048716cea00188ea36f4517a124b3691647b43b9ebc5f458c3a14bdf46da", "bytes": 203, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T3", "version": null, "note": "KEGG pathway analysis of DEmiRNAs target genes (Top 5).", "structure": {"pmcid": "PMC7489663", "section_index": 13, "section_title": "KEGG pathway enrichment analysis of target genes of DEmiRNAs", "row_count": 0, "column_count": 0}, "table": {"label": "Table 3", "caption": "KEGG pathway analysis of DEmiRNAs target genes (Top 5).", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[13]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:32925795:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4040d0a349d890f1da316d00efefc455e3e269affdf1b61eb1c5a2cfe79146cf", "bytes": 218, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T4", "version": null, "note": "Functional and pathway enrichment analysis of the genes in the module.", "structure": {"pmcid": "PMC7489663", "section_index": 14, "section_title": "PPI network and modules analysis", "row_count": 0, "column_count": 0}, "table": {"label": "Table 4", "caption": "Functional and pathway enrichment analysis of the genes in the module.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[14]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:32925795:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8621093118f676787c676e394fb5f502fc84ec3656fa503f0804419bd839d103", "bytes": 178, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T5", "version": null, "note": "Hub genes ranked in cytoHubba.", "structure": {"pmcid": "PMC7489663", "section_index": 15, "section_title": "Identification of hub genes and construction miRNA-mRNA network", "row_count": 0, "column_count": 0}, "table": {"label": "Table 5", "caption": "Hub genes ranked in cytoHubba.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[15]/table-wrap[1]#T5"}}], "gaps": ["asset:data:geo:GSE39833 not downloaded", "asset:data:geo:GSE39833 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/) is an online analysis tool for comparing 2 groups of GEO datasets based on the GEO query and Limma R packages.[18]"}}, {"id": "method-2", "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-3", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE39833"], "resolved_accessions": ["GSE39833"], "statements": ["All data generated or analyzed during this study are included in this published article [and its supplementary information files]."], "basis": "The paper names GSE39833 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32925795", "data:geo:GSE39833", "asset:table:pmid:32925795:1", "asset:table:pmid:32925795:2", "asset:table:pmid:32925795:3", "asset:table:pmid:32925795:4", "asset:table:pmid:32925795:5", "asset:table:pmid:32925795:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE39833"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 35173, "completion_tokens": 1374, "cached_tokens": 792}}, "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:32925795", "type": "paper", "label": "pmid:32925795"}, {"id": "source:pmid:32925795", "type": "manuscript", "label": "PMID 32925795 full text"}, {"id": "data:geo:GSE39833", "type": "dataset", "label": "GEO GSE39833"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32925795", "type": "paper", "label": "pmid:32925795"}, {"id": "source:pmid:32925795", "type": "manuscript", "label": "PMID 32925795 full text"}, {"id": "data:geo:GSE39833", "type": "dataset", "label": "GEO GSE39833"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32925795", "type": "extraction", "used": ["source:pmid:32925795"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE39833", "type": "accession_resolution", "used": ["data:geo:GSE39833"], "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:32925795", "parent_hash": "sha256:c85d13017a91328fed3d6f0ba5ce342a70e3e752f735c4f91e0864197cb7f9ab", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE39833 licence not read", "asset:data:geo:GSE39833 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/) is an online analysis tool for comparing 2 groups of GEO datasets based on the GEO query and Limma R packages.[18]"], "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":"2026-11-04T03:34:21+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}}}