{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30013745", "kind": "science-record", "revision": 8, "content_hash": "sha256:75f40a7af1d437ad33e604aff1ab5bece375201055945398bcddc46b09ed1a00", "created_at": "2026-11-01T15:40:35Z", "updated_at": "2026-11-01T21:59:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Celiac disease microarray analysis based on System Biology Approach.", "doi": null, "pmid": "30013745", "authors": ["Mostafa Rezaei Tavirani", "Davood Bashash", "Fatemeh Tajik Rostami", "Sina Rezaei Tavirani", "Abdolrahim Nikzamir", "Majid Rezaei Tavirani", "Mohammad Hossain Haidary"], "journal": "Gastroenterology and hepatology from bed to bench", "year": 2018, "abstract": "AIM: Aim of this study is screen of the large numbers of related genes of CD to find the key ones.\nBACKGROUND: Celiac disease (CD) is known as a gluten sensitive and immune system dependent disease. There are several high throughput investigations about CD but it is necessary to clarify new molecular aspects mechanism of celiac.\nMETHODS: Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) as Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database. The significant genes were selected and analyzed via protein-protein interaction (PPI) network by Cytoscape software. The key genes were introduced and enriched via ClueGO to find the related biochemical pathways.\nRESULTS: Among 250 significant genes 47 genes with expressed change above 2 fold change (FC) were interacted and the constructed network were analyzed. The network characterized by poor connections so it was promoted by addition 50 related nodes and 18 crucial nodes were introduced. Two clusters of biochemical pathways were identified and discussed.\nCONCLUSION: There is an obvious conflict between microarray finding and the well-known related genes of CD. This problem can be solve by more attention to the interpretation of PPI ntwork analysis results.", "claims": [{"id": "claim-method", "statement": "Numbers of 250 top score genes were selected and differences between control and celiac samples were calculated using the Student’s t test statistical p-values less than 0.05 and adjusted p-values via GEO2R analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30013745", "locator": "sections[2] \"Methods\" paragraph 2", "quote": "Numbers of 250 top score genes were selected and differences between control and celiac samples were calculated using the Student’s t test statistical p-values less than 0.05 and adjusted p-values via GEO2R analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database. The profile was provided based on the GPL10558 Illumina HumanHT-12 V4.0 expression bead chip. Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) of celiac patients on gluten free diet (GFD) vs. controls is investigated.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30013745", "locator": "sections[2] \"Methods\" paragraph 2", "quote": "Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database. The profile was provided based on the GPL10558 Illumina HumanHT-12 V4.0 expression bead chip. Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) of celiac patients on gluten free diet (GFD) vs. controls is investigated."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using Student’s t test and GEO2R-adjusted p-values on GSE113469 RNA-expression data retrieved from GEO, the study identified 47 differentially expressed genes distinguishing gluten-free-diet celiac patients from controls at FC≥2.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:30013745", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) as Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database."}, {"asset": "source:pmid:30013745", "locator": "sections[3] \"Results\" paragraph 2", "quote": "Among 250 top score genes 47 up and down-regulated genes based on statistic method (as described in methods) and considering FC≥2 were identified as the significant DEGs (see figure 2)."}, {"asset": "source:pmid:30013745", "locator": "sections[3] \"Results\" paragraph 2", "quote": "Therefor 47 DEGs differentiate the GFD patients from control samples."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "Using Student’s t test and GEO2R-adjusted p-values on GSE113469 RNA-expression data retrieved from GEO, the study identified 47 differentially expressed genes distinguishing gluten-free-diet celiac patients from controls at FC≥2.", "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:30013745"], "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:GSE113469"], "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:GSE113469"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30013745", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:22dd9930710738f0ee0590912a6134bfb595893f258f04ba6967dd7a6449d54b", "bytes": 15283, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "30013745", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6040039", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE113469", "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=GSE113469", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE113469", "version": null, "note": "Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database. The profile was provided based on the GPL10558 Illumina HumanHT-12 V4.0 expression bead chip. Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) of celiac patients on gluten free diet (GFD) vs. controls is investigated.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database. The profile was provided based on the GPL10558 Illumina HumanHT-12 V4.0 expression bead chip. Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) of celiac patients on gluten free diet (GFD) vs. controls is investigated.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3106457", "GSM3106458", "GSM3106459", "GSM3106460", "GSM3106461", "GSM3106462", "GSM3106463", "GSM3106464", "GSM3106465", "GSM3106466", "GSM3106467", "GSM3106468", "GSM3106469", "GSM3106470", "GSM3106471", "GSM3106472", "GSM3106473", "GSM3106474", "GSM3106475", "GSM3106476", "GSM3106477", "GSM3106478", "GSM3106479", "GSM3106480", "GSM3106481", "GSM3106482", "GSM3106483", "GSM3106484", "GSM3106485", "GSM3106486", "GSM3106487", "GSM3106488", "GSM3106489", "GSM3106490", "GSM3106491", "GSM3106492", "GSM3106493"], "sample_count": 37, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Identification of peculiar gene expression profile in peripheral blood mononuclear cells (PBMC) of celiac patients on gluten free diet", "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:30013745:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4dc010f6635747cf6fe3d6a367eb9ef5c4514c3f456afbf8a7120ed16b8ca489", "bytes": 1693, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#T1", "version": null, "note": "Rows 1-10 are the hub-nodes and The 1, 3, and 11-18 rows are bottleneck genes of celiac network. The rend color refers to hub-bottleneck nodes and green color is corresponded to bottleneck genes. The query genes are presented as yellow highlighted nodes. The normalized betweenness centrality (NBC) is shown in the last column of table.", "structure": {"pmcid": "PMC6040039", "section_index": 2, "section_title": "Methods", "row_count": 19, "column_count": 5}, "table": {"label": "Table 1", "caption": "Rows 1-10 are the hub-nodes and The 1, 3, and 11-18 rows are bottleneck genes of celiac network. The rend color refers to hub-bottleneck nodes and green color is corresponded to bottleneck genes. The query genes are presented as yellow highlighted nodes. The normalized betweenness centrality (NBC) is shown in the last column of table.", "rows": [["R", "Gene name", "description", "Degree", "N BC"], ["1", "GAPDH", "glyceraldehyde-3-phosphate dehydrogenase", "60", "0.625"], ["2", "AKT1", "v-akt murine thymoma viral oncogene homolog 1", "56", "0.375"], ["3", "TP53", "tumor protein p53", "54", "0.813"], ["4", "PRDM10", "PR domain containing 10", "54", "0.313"], ["5", "SRC", "v-src sarcoma (Schmidt-Ruppin A-2) viral oncogene homolog (avian)", "53", "0.188"], ["6", "NFKB1", "nuclear factor of kappa light polypeptide gene enhancer in B-cells 1", "53", "0.156"], ["7", "IL6", "interleukin 6 (interferon, beta 2)", "52", "0.281"], ["8", "PIK3CG", "phosphatidylinositol-4,5-bisphosphate 3-kinase, catalytic subunit gamma", "51", "0.063"], ["9", "INS", "Insulin", "50", "0.313"], ["10", "TNF", "tumor necrosis factor", "50", "0.000"], ["11", "IL1B", "interleukin 1, beta", "44", "1.000"], ["12", "NOTCH1", "notch 1", "44", "0.719"], ["13", "HSPA5", "heat shock 70kDa protein 5 (glucose-regulated protein, 78kDa)", "42", "0.563"], ["14", "PTPRC", "protein tyrosine phosphatase, receptor type, C", "38", "0.594"], ["15", "UBC", "ubiquitin C", "34", "0.469"], ["16", "TOP2A", "topoisomerase (DNA) II alpha 170kDa", "32", "0.531"], ["17", "ACLY", "ATP citrate lyase", "29", "0.844"], ["18", "PELI1", "pellino E3 ubiquitin protein ligase 1", "3", "0.500"]], "row_count": 19, "column_count": 5, "numeric_cells": 69, "header_rows": 1, "locator": "section[2]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30013745:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:51bd9be6605eeef120b9e4ab4ab2dd33068c61896834d1e6c9e76a0dba075ff9", "bytes": 1844, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#T2", "version": null, "note": "The enriched pathways from KEGG related to the 18 central nodes of celiac disease network are shown. The 22 terms are grouped in 2 clusters (blue and green color terms) which the names of groups are highlighted with yellow color. At least presence of 4 genes in a term and 2%genes/term were considered for term determination. P-value for all identified terms was less than 0.01. The repeated termsare marked by (-1).", "structure": {"pmcid": "PMC6040039", "section_index": 2, "section_title": "Methods", "row_count": 30, "column_count": 4}, "table": {"label": "Table 2", "caption": "The enriched pathways from KEGG related to the 18 central nodes of celiac disease network are shown. The 22 terms are grouped in 2 clusters (blue and green color terms) which the names of groups are highlighted with yellow color. At least presence of 4 genes in a term and 2%genes/term were considered for term determination. P-value for all identified terms was less than 0.01. The repeated termsare marked by (-1).", "rows": [["R", "Term", "%Genes/Term", "No. of Genes"], ["1", "Sphingolipid signaling pathway", "3.4", "4"], ["2", "Apoptosis", "2.9", "4"], ["3", "Longevity regulating pathway", "4.5", "4"], ["4", "Cellular senescence", "2.5", "4"], ["5", "Prolactin signaling pathway", "5.7", "4"], ["6", "Hepatitis C", "3.1", "4"], ["7", "Measles", "3.0", "4"], ["8", "Prostate cancer", "4.2", "4"], ["9", "HIF-1signaling pathway", "5.0", "5"], ["10", "Sphingolipid signaling pathway-1", "3.4", "4"], ["11", "Apoptosis-1", "2.9", "4"], ["12", "Longevity regulating pathway-1", "4.5", "4"], ["13", "Cellular senescence-1", "2.5", "4"], ["14", "Toll-like receptor signaling pathway", "3.8", "4"], ["15", "TNF signaling pathway", "3.6", "4"], ["16", "Insulin resistance", "4.7", "5"], ["17", "Non-alcoholic fatty liver diseases (NAFLD)", "3.3", "5"], ["18", "AGE-RAGE signaling pathway in diabetic complications", "4.1", "4"], ["19", "Chagas disease (American trypanosomiasis", "3.8", "4"], ["20", "Toxoplasmosis", "3.5", "4"], ["21", "Tuberculosis", "2.7", "5"], ["22", "Hepatitis C-1", "3.1", "4"], ["23", "Hepatitis B", "4.2", "6"], ["24", "Measles-1", "3.0", "4"], ["25", "Influenza A", "2.3", "4"], ["26", "Kaposis sarcoma-associated herpesvirus infection", "3.3", "6"], ["27", "Herpes simplex infection", "2.1", "4"], ["28", "Prostate cancer-1", "4.2", "4"], ["29", "Fluid shear stress and atherosclerosis", "3.6", "5"]], "row_count": 30, "column_count": 4, "numeric_cells": 95, "header_rows": 1, "locator": "section[2]/table-wrap[2]#T2"}}], "gaps": ["asset:data:geo:GSE113469 not downloaded", "asset:data:geo:GSE113469 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "centrality"}}, {"id": "method-3", "family": null, "specific": null, "label": "Student’s t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Numbers of 250 top score genes were selected and differences between control and celiac samples were calculated using the Student’s t test statistical p-values less than 0.05 and adjusted p-values via GEO2R analysis."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE113469"], "resolved_accessions": ["GSE113469"], "statements": ["Gene expression profile GSE113469 was retrieved Gene Expression Omnibus (GEO) database. The profile was provided based on the GPL10558 Illumina HumanHT-12 V4.0 expression bead chip. Whole-genome profile (RNA) of the human peripheral blood mononuclear cells (PBMCs) of celiac patients on gluten free diet (GFD) vs. controls is investigated."], "basis": "The paper names GSE113469 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:30013745", "data:geo:GSE113469", "asset:table:pmid:30013745:1", "asset:table:pmid:30013745:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE113469"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:35:03Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 30715, "completion_tokens": 2762, "cached_tokens": 1584}}, "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:30013745", "type": "paper", "label": "pmid:30013745"}, {"id": "source:pmid:30013745", "type": "manuscript", "label": "PMID 30013745 full text"}, {"id": "data:geo:GSE113469", "type": "dataset", "label": "GEO GSE113469"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30013745", "type": "paper", "label": "pmid:30013745"}, {"id": "source:pmid:30013745", "type": "manuscript", "label": "PMID 30013745 full text"}, {"id": "data:geo:GSE113469", "type": "dataset", "label": "GEO GSE113469"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30013745", "type": "extraction", "used": ["source:pmid:30013745"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE113469", "type": "accession_resolution", "used": ["data:geo:GSE113469"], "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:30013745", "parent_hash": "sha256:b4c74cf4c4a6adc9d5d08ba51f06ac9180792901ef69621b9951348dfe703d3a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE113469 licence not read", "asset:data:geo:GSE113469 not downloaded", "doi", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Celiac disease microarray analysis based on System Biology Approach.", "LUSION: There is an obvious conflict between microarray finding and the well-known related genes of"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "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":"2026-11-04T03:05:41+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}}}