{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33888009", "kind": "science-record", "revision": 7, "content_hash": "sha256:7e943d28ef7cf564b06ec296739b938a930ca17f918083ce85eacecb17ed2d5b", "created_at": "2026-11-01T15:41:33Z", "updated_at": "2026-11-01T21:25:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Expression Profiles Reveal Involvement of VEGF, IGF1, BIRC5, and MMP1 in Vulvar Carcinogenesis.", "doi": "10.1177/15330338211004922", "pmid": "33888009", "authors": ["Tao Zhang", "Qin Liu", "Minghua Yu", "Yibing Lan", "Jianghong Zhou"], "journal": "Technology in cancer research & treatment", "year": 2021, "abstract": "OBJECTIVE: The objective of this study was to identify key genes and shed light on the underlying molecular mechanisms of vulvar squamous cell carcinoma (VSCC).\nMETHODS: Bioinformatic software was utilized for the identification and characterization of key differentially expressed genes (DEGs) from microarrays GSE63678 and GSE38228, which contain VSCC and normal vulvar tissue data. These microarrays were obtained from Gene Expression Omnibus (GEO). Immunohistochemical assays (55 VSCC and 50 normal vulvar tissues) were utilized to validate the expression of VEGF, IGF1, BIRC5, and MMP1 screened from the identified DEGs. SPSS 18.0 software was used for statistical analyses of the relationships between IGF1, BIRC5, VEGF, MMP1 expression levels and patient clinicopathological characteristics.\nRESULTS: A total of 141 DEGs were identified, among which 18 genes were closely correlated with the biological characteristics of VSCC. Four of the 18 genes (VEGF, IGF1, BIRC5, and MMP1) screened from the GEO database were markedly enriched in pathways in cancer (P < 0.05), and could be considered key genes in VSCC based on KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway analysis in DAVID (Database for Annotation, Visualization and Integrated Discovery).The expression levels of these 4 hub genes, determined by immunohistochemical assays, were consistent with the bioinformatics results. Higher expression of IGF1 showed significant association with well-differentiated carcinomas (P = 0.017).BIRC5 expression levels showed a positive correlation with clinical stage (P = 0.039); compared with those in menopause for over 10 years, patients in menopause for less than 10 years at the time of diagnosis tended to have significantly higher expression of BIRC5 (P = 0.003). VEGF and MMP1 expression levels were not correlated with any of the tested clinicopathological characteristics.\nCONCLUSION: VEGF, IGF1, BIRC5, and MMP1 were identified as being associated with VSCC using integrated bioinformatic methods, which may provide important insights into the pathogenesis of this disease and help to identify new biomarkers.", "claims": [{"id": "claim-method", "statement": "DEGs between the 2 groups were identified by using the GEO2R online tool8 with statistical significance reached at |logFC| > 1 and adjusted P value < 0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33888009", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "DEGs between the 2 groups were identified by using the GEO2R online tool8 with statistical significance reached at |logFC| > 1 and adjusted P value < 0.05."}], "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:33888009"], "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:GSE38228"], "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:GSE38228"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33888009", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1177/15330338211004922", "sha256": "sha256:a1d99994da3d143b1235af92740fea6a8e30c1ef6663fc63b24a7b48a5729ec6", "bytes": 26527, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1177/15330338211004922", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8071978", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE38228", "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=GSE38228", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38228", "version": null, "note": "Microarray data of GSE63678 comprise 6 VSCC tumor and 13 normal vulvar tissue samples, while the GSE38228 profile consists of 7 VSCC tumor and 5 normal vulvar tissues samples. The VSCC-associated gene expression datasets GSE63678 and GSE38228 were downloaded from Gene Expression Omnibus (GEO) (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray data of GSE63678 comprise 6 VSCC tumor and 13 normal vulvar tissue samples, while the GSE38228 profile consists of 7 VSCC tumor and 5 normal vulvar tissues samples. The VSCC-associated gene expression datasets GSE63678 and GSE38228 were downloaded from Gene Expression Omnibus (GEO) (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM937042", "GSM937043", "GSM937044", "GSM937045", "GSM937046", "GSM937047", "GSM937048", "GSM937049", "GSM937050", "GSM937051", "GSM937052", "GSM937053", "GSM937054", "GSM937055", "GSM937056", "GSM937057", "GSM937058", "GSM937059"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Expression analysis of 13 squamous cell carcinomas arising in the vulva", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE63678", "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=GSE63678", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63678", "version": null, "note": "Microarray data of GSE63678 comprise 6 VSCC tumor and 13 normal vulvar tissue samples, while the GSE38228 profile consists of 7 VSCC tumor and 5 normal vulvar tissues samples. The VSCC-associated gene expression datasets GSE63678 and GSE38228 were downloaded from Gene Expression Omnibus (GEO) (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray data of GSE63678 comprise 6 VSCC tumor and 13 normal vulvar tissue samples, while the GSE38228 profile consists of 7 VSCC tumor and 5 normal vulvar tissues samples. The VSCC-associated gene expression datasets GSE63678 and GSE38228 were downloaded from Gene Expression Omnibus (GEO) (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1555075", "GSM1555076", "GSM1555077", "GSM1555078", "GSM1555079", "GSM1555080", "GSM1555081", "GSM1555082", "GSM1555083", "GSM1555084", "GSM1555085", "GSM1555086", "GSM1555087", "GSM1555088", "GSM1555089", "GSM1555090", "GSM1555091", "GSM1555092", "GSM1555093", "GSM1555094", "GSM1555095", "GSM1555096", "GSM1555097", "GSM1555098", "GSM1555099", "GSM1555100", "GSM1555101", "GSM1555102", "GSM1555103", "GSM1555104", "GSM1555105", "GSM1555106", "GSM1555107", "GSM1555108", "GSM1555109"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Expression data from Vulvar, Cervical, Endometrial Carcinoma tissue", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33888009:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b68db7bf44393e5b080344ed015404465a554e773685f6058dc3d9b934be0d48", "bytes": 359, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table1-15330338211004922", "version": null, "note": "Entire 141 Common DEGs Were Identified From 2 Profile Datasets, Including 39 Up-Regulated Genes and 102 Down-Regulated Genes in the Vulvar Cancer Tissues Compared to Normal Vulvar Tissues.", "structure": {"pmcid": "PMC8071978", "section_index": 10, "section_title": "Identification of DEGs in VSCC", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1.", "caption": "Entire 141 Common DEGs Were Identified From 2 Profile Datasets, Including 39 Up-Regulated Genes and 102 Down-Regulated Genes in the Vulvar Cancer Tissues Compared to Normal Vulvar Tissues.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[10]/table-wrap[1]#table1-15330338211004922"}}, {"id": "asset:table:pmid:33888009:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f7f48658c7fd9a6d42a1bcb090423251ce589c59a6b177fb32566f721a64341a", "bytes": 218, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table2-15330338211004922", "version": null, "note": "KEGG Pathway Analysis of 18 Core Genes in VSCC.", "structure": {"pmcid": "PMC8071978", "section_index": 12, "section_title": "Analysis of 18 Core Genes for KEGG Pathway Enrichment", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2.", "caption": "KEGG Pathway Analysis of 18 Core Genes in VSCC.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#table2-15330338211004922"}}, {"id": "asset:table:pmid:33888009:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aaf4712154f48e089538651f6caeeef350a1bac2b4009d0e164ada9720fcb8e4", "bytes": 218, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#table3-15330338211004922", "version": null, "note": "Protein Expression in Different Vulvar Tissue.a", "structure": {"pmcid": "PMC8071978", "section_index": 13, "section_title": "Validation of VEGF, IGF1, BIRC5, and MMP1 Expression With Immunohistochemical Assay in Normal Vulvar Tissues Versus Vulvar Cancer Samples", "row_count": 0, "column_count": 0}, "table": {"label": "Table 3.", "caption": "Protein Expression in Different Vulvar Tissue.a", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[13]/table-wrap[1]#table3-15330338211004922"}}, {"id": "asset:table:pmid:33888009:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6c6f11469bd54e768ce18f794cc6b93edad562e739bfeb2c87c04f9f122c3a3a", "bytes": 278, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#table4-15330338211004922", "version": null, "note": "Association Between the Expression of IGF1, BIRC5, VEGF, and MMP1 and Clinicopathological Characteristics.a", "structure": {"pmcid": "PMC8071978", "section_index": 14, "section_title": "Relationships Between IGF1, BIRC5, VEGF, MMP1 Expression Levels and Patients’ Clinicopathological Characteristics", "row_count": 0, "column_count": 0}, "table": {"label": "Table 4.", "caption": "Association Between the Expression of IGF1, BIRC5, VEGF, and MMP1 and Clinicopathological Characteristics.a", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[14]/table-wrap[1]#table4-15330338211004922"}}], "gaps": ["asset:data:geo:GSE38228 not downloaded", "asset:data:geo:GSE38228 licence not read", "asset:data:geo:GSE63678 not downloaded", "asset:data:geo:GSE63678 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "family": null, "specific": null, "label": "GEO2R online tool", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "DEGs between the 2 groups were identified by using the GEO2R online tool8 with statistical significance reached at |logFC| > 1 and adjusted P value < 0.05."}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["GSE63678", "GSE38228"], "resolved_accessions": ["GSE63678", "GSE38228"], "statements": ["Microarray data of GSE63678 comprise 6 VSCC tumor and 13 normal vulvar tissue samples, while the GSE38228 profile consists of 7 VSCC tumor and 5 normal vulvar tissues samples. The VSCC-associated gene expression datasets GSE63678 and GSE38228 were downloaded from Gene Expression Omnibus (GEO) (http://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE63678, GSE38228 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": ["pathway_enrich"], "assets": ["source:pmid:33888009", "data:geo:GSE38228", "asset:table:pmid:33888009:1", "asset:table:pmid:33888009:2", "asset:table:pmid:33888009:3", "asset:table:pmid:33888009:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE38228"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 20049, "completion_tokens": 1848, "cached_tokens": 12800}}, "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:33888009", "type": "paper", "label": "pmid:33888009"}, {"id": "source:pmid:33888009", "type": "manuscript", "label": "PMID 33888009 full text"}, {"id": "data:geo:GSE38228", "type": "dataset", "label": "GEO GSE38228"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33888009", "type": "paper", "label": "pmid:33888009"}, {"id": "source:pmid:33888009", "type": "manuscript", "label": "PMID 33888009 full text"}, {"id": "data:geo:GSE38228", "type": "dataset", "label": "GEO GSE38228"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33888009", "type": "extraction", "used": ["source:pmid:33888009"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE38228", "type": "accession_resolution", "used": ["data:geo:GSE38228"], "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:33888009", "parent_hash": "sha256:f0bdc7965838175c70ca13053a07b96270935639ee3d0d8addeb45488caff31d", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE38228 licence not read", "asset:data:geo:GSE38228 not downloaded", "asset:data:geo:GSE63678 licence not read", "asset:data:geo:GSE63678 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["obtained from Gene Expression Omnibus (GEO). Immunohistochemical assays (55 VSCC and 50 normal vulvar tissues", "n levels of these 4 hub genes, determined by immunohistochemical assays, were consistent with the bioinformat", "VEGF, IGF1, BIRC5, and MMP1 Expression With Immunohistochemical Assay in Normal Vulvar Tissues Versus Vulvar", "lidation of VEGF, IGF1, BIRC5, and MMP1 with immunohistochemical assay of normal vulvar tissues versus vulvar"], "order_basis": "paper_text_order:504", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Pathway Enrichment"], "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":"2026-11-04T02:52:06+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}}}