{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33046027", "kind": "science-record", "revision": 8, "content_hash": "sha256:4372d93728e58425c994bfa3adf266ddfb795ab66f994f98ee5cdd59de324711", "created_at": "2026-11-01T15:41:12Z", "updated_at": "2026-11-01T22:45:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Diagnostic biomarker candidates for pulpitis revealed by bioinformatics analysis of merged microarray gene expression datasets.", "doi": "10.1186/s12903-020-01266-5", "pmid": "33046027", "authors": ["Ming Chen", "Junkai Zeng", "Yeqing Yang", "Buling Wu"], "journal": "BMC oral health", "year": 2020, "abstract": "BACKGROUND: Pulpitis is an inflammatory disease, the grade of which is classified according to the level of inflammation. Traditional methods of evaluating the status of dental pulp tissue in clinical practice have limitations. The rapid and accurate diagnosis of pulpitis is essential for determining the appropriate treatment. By integrating different datasets from the Gene Expression Omnibus (GEO) database, we analysed a merged expression matrix of pulpitis, aiming to identify biological pathways and diagnostic biomarkers of pulpitis.\nMETHODS: By integrating two datasets (GSE77459 and GSE92681) in the GEO database using the sva and limma packages of R, differentially expressed genes (DEGs) of pulpitis were identified. Then, the DEGs were analysed to identify biological pathways of dental pulp inflammation with Gene Ontology (GO) analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis and Gene Set Enrichment Analysis (GSEA). Protein-protein interaction (PPI) networks and modules were constructed to identify hub genes with the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) and Cytoscape.\nRESULTS: A total of 470 DEGs comprising 394 upregulated and 76 downregulated genes were found in pulpitis tissue. GO analysis revealed that the DEGs were enriched in biological processes related to inflammation, and the enriched pathways in the KEGG pathway analysis were cytokine-cytokine receptor interaction, chemokine signalling pathway and NF-κB signalling pathway. The GSEA results provided further functional annotations, including complement system, IL6/JAK/STAT3 signalling pathway and inflammatory response pathways. According to the degrees of nodes in the PPI network, 10 hub genes were identified, and 8 diagnostic biomarker candidates were screened: PTPRC, CD86, CCL2, IL6, TLR8, MMP9, CXCL8 and ICAM1.\nCONCLUSIONS: With bioinformatics analysis of merged datasets, biomarker candidates of pulpitis were screened and the findings may be as reference to develop a new method of pulpitis diagnosis.", "claims": [{"id": "claim-method", "statement": "Then, the raw data was converted into the form of an expression matrix and handled with the Linear Models for Microarray data (limma, https://bioconductor.org/packages/limma/) package in Bioconductor.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33046027", "locator": "sections[3] \"Data processing\" paragraph 2", "quote": "Then, the raw data was converted into the form of an expression matrix and handled with the Linear Models for Microarray data (limma, https://bioconductor.org/packages/limma/) package in Bioconductor."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33046027", "locator": "sections[20] \"Availability of data and materials\" paragraph 2", "quote": "The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds."}], "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:33046027"], "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:GSE77459"], "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:GSE77459"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33046027", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12903-020-01266-5", "sha256": "sha256:127f951d79c96ed9a0362b0c1819a512ac13d30f775df9d0e1c89bc7ec48e8d6", "bytes": 38087, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12903-020-01266-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7552454", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE77459", "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=GSE77459", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE77459", "version": null, "note": "The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2052371", "GSM2052372", "GSM2052373", "GSM2052374", "GSM2052375", "GSM2052376", "GSM2052377", "GSM2052378", "GSM2052379", "GSM2052380", "GSM2052381", "GSM2052382"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "17692", "taxon": "Homo sapiens", "title": "Gene Expression Profile of Pulpitis", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE92681", "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=GSE92681", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE92681", "version": null, "note": "The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2434473", "GSM2434474", "GSM2434475", "GSM2434476", "GSM2434477", "GSM2434478", "GSM2434479", "GSM2434480", "GSM2434481", "GSM2434482", "GSM2434483", "GSM2434484"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "16956", "taxon": "Homo sapiens", "title": "Differential Expression of LncRNAs and mRNAs in normal and inflamed human pulp", "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:33046027:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bf043104e8099321f80fc5b9d6deeea9413e76956c7c80e6b34df66a9125596e", "bytes": 971, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#Tab1", "version": null, "note": "Summary of two individual datasets of pulpitis", "structure": {"pmcid": "PMC7552454", "section_index": 2, "section_title": "Methods", "row_count": 9, "column_count": 3}, "table": {"label": "Table 1", "caption": "Summary of two individual datasets of pulpitis", "rows": [["GEO gene set ID", "GSE77459", "GSE92681"], ["Title", "Gene Expression Profile of Pulpitis", "Differential Expression of LncRNAs and mRNAs in normal and inflamed human pulp"], ["Platform", "GPL17692: Affymetrix Human Gene 2.1 ST Array [transcript (gene) version]", "GPL16956: Agilent 045997 Arraystar human lncRNA microarray V3 (Probe Name Version)"], ["Diagnostic criteria", "AAE", "AAE"], ["Number of normal samples vs. pulpitis sample", "6 vs. 6", "5 vs. 7"], ["Clinical data"], ["Normal tissues", "Picked from healthy teeth extracted for various reasons", "Picked from healthy teeth extracted for various reasons"], ["Pulpitis tissues", "Picked from teeth diagnosed with irreversible pulpitis", "Picked from teeth diagnosed with irreversible pulpitis"], ["PubMed ID", "27,052,691", "29,079,059"]], "row_count": 9, "column_count": 3, "numeric_cells": 8, "header_rows": 1, "locator": "section[2]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33046027:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c0a12abcdd95b44fc50e97273fb85a5b3007bef0f92589e13b2c69a0cd44af28", "bytes": 2024, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab2", "version": null, "note": "Supplementary information of GO analysis", "structure": {"pmcid": "PMC7552454", "section_index": 4, "section_title": "Functional analysis of DEGs", "row_count": 31, "column_count": 4}, "table": {"label": "Table 2", "caption": "Supplementary information of GO analysis", "rows": [["Category", "ID", "Term", "adj. P. val"], ["BP", "GO:0006954", "inflammatory response", "7.13E-24"], ["BP", "GO:0007165", "signal transduction", "3.73E-05"], ["BP", "GO:0006955", "immune response", "3.36E-20"], ["BP", "GO:0007155", "cell adhesion", "7.95E-12"], ["BP", "GO:0045944", "positive regulation of transcription from RNA polymerase II promoter", "0.005548688"], ["BP", "GO:0007186", "G-protein coupled receptor signalling pathway", "0.002323744"], ["BP", "GO:0006915", "apoptotic process", "0.000255676"], ["BP", "GO:0043066", "negative regulation of apoptotic process", "3.66E-05"], ["BP", "GO:0007166", "cell surface receptor signalling pathway", "7.13E-09"], ["BP", "GO:0045087", "innate immune response", "3.69E-05"], ["CC", "GO:0016021", "integral component of membrane", "7.35E-06"], ["CC", "GO:0005886", "plasma membrane", "1.69E-12"], ["CC", "GO:0070062", "extracellular exosome", "0.00028413"], ["CC", "GO:0005576", "extracellular region", "8.34E-13"], ["CC", "GO:0016020", "membrane", "2.96E-05"], ["CC", "GO:0005887", "integral component of plasma membrane", "1.08E-13"], ["CC", "GO:0005615", "extracellular space", "1.57E-08"], ["CC", "GO:0009986", "cell surface", "1.72E-07"], ["CC", "GO:0009897", "external side of plasma membrane", "2.35E-12"], ["CC", "GO:0005578", "proteinaceous extracellular matrix", "0.000108122"], ["MF", "GO:0005515", "protein binding", "0.002283082"], ["MF", "GO:0005509", "calcium ion binding", "0.003507755"], ["MF", "GO:0042803", "protein homodimerization activity", "0.014495214"], ["MF", "GO:0005102", "receptor binding", "0.000515236"], ["MF", "GO:0004872", "receptor activity", "1.96E-06"], ["MF", "GO:0030246", "carbohydrate binding", "0.00011033"], ["MF", "GO:0008201", "heparin binding", "0.000173777"], ["MF", "GO:0004888", "transmembrane signalling receptor activity", "0.002616585"], ["MF", "GO:0003779", "actin binding", "0.043764465"], ["MF", "GO:0005125", "cytokine activity", "0.004406936"]], "row_count": 31, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:33046027:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c0a12abcdd95b44fc50e97273fb85a5b3007bef0f92589e13b2c69a0cd44af28", "bytes": 2024, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab2", "version": null, "note": "Supplementary information of GO analysis", "structure": {"pmcid": "PMC7552454", "section_index": 9, "section_title": "Functional analysis of DEGs", "row_count": 31, "column_count": 4}, "table": {"label": "Table 2", "caption": "Supplementary information of GO analysis", "rows": [["Category", "ID", "Term", "adj. P. val"], ["BP", "GO:0006954", "inflammatory response", "7.13E-24"], ["BP", "GO:0007165", "signal transduction", "3.73E-05"], ["BP", "GO:0006955", "immune response", "3.36E-20"], ["BP", "GO:0007155", "cell adhesion", "7.95E-12"], ["BP", "GO:0045944", "positive regulation of transcription from RNA polymerase II promoter", "0.005548688"], ["BP", "GO:0007186", "G-protein coupled receptor signalling pathway", "0.002323744"], ["BP", "GO:0006915", "apoptotic process", "0.000255676"], ["BP", "GO:0043066", "negative regulation of apoptotic process", "3.66E-05"], ["BP", "GO:0007166", "cell surface receptor signalling pathway", "7.13E-09"], ["BP", "GO:0045087", "innate immune response", "3.69E-05"], ["CC", "GO:0016021", "integral component of membrane", "7.35E-06"], ["CC", "GO:0005886", "plasma membrane", "1.69E-12"], ["CC", "GO:0070062", "extracellular exosome", "0.00028413"], ["CC", "GO:0005576", "extracellular region", "8.34E-13"], ["CC", "GO:0016020", "membrane", "2.96E-05"], ["CC", "GO:0005887", "integral component of plasma membrane", "1.08E-13"], ["CC", "GO:0005615", "extracellular space", "1.57E-08"], ["CC", "GO:0009986", "cell surface", "1.72E-07"], ["CC", "GO:0009897", "external side of plasma membrane", "2.35E-12"], ["CC", "GO:0005578", "proteinaceous extracellular matrix", "0.000108122"], ["MF", "GO:0005515", "protein binding", "0.002283082"], ["MF", "GO:0005509", "calcium ion binding", "0.003507755"], ["MF", "GO:0042803", "protein homodimerization activity", "0.014495214"], ["MF", "GO:0005102", "receptor binding", "0.000515236"], ["MF", "GO:0004872", "receptor activity", "1.96E-06"], ["MF", "GO:0030246", "carbohydrate binding", "0.00011033"], ["MF", "GO:0008201", "heparin binding", "0.000173777"], ["MF", "GO:0004888", "transmembrane signalling receptor activity", "0.002616585"], ["MF", "GO:0003779", "actin binding", "0.043764465"], ["MF", "GO:0005125", "cytokine activity", "0.004406936"]], "row_count": 31, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:33046027:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e450b85e919a23e66bfc9103c6416d4f343e27fcbe4ec4932e560d17bae5570a", "bytes": 1864, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab3", "version": null, "note": "Top 10 hub genes with higher degrees of PPI network of pulpitis", "structure": {"pmcid": "PMC7552454", "section_index": 11, "section_title": "PPI network and hub genes", "row_count": 11, "column_count": 4}, "table": {"label": "Table 3", "caption": "Top 10 hub genes with higher degrees of PPI network of pulpitis", "rows": [["Gene symbol", "Description", "Function", "Degree"], ["PTPRC", "Receptor-type tyrosine-protein phosphatase C", "Protein tyrosine-protein phosphatase required for T-cell activation through the antigen receptor. Acts as a positive regulator of T-cell coactivation upon binding to DPP4.", "126"], ["TLR8", "Toll-like receptor 8", "Key component of innate and adaptive immunity", "100"], ["CD86", "T-lymphocyte activation antigen CD86", "Receptor involved in the costimulatory signal essential for T-lymphocyte proliferation and interleukin-2 production, by binding CD28 or CTLA-4.", "100"], ["IL6", "Interleukin-6", "Cytokine with a wide variety of biological functions. Plays an essential role in the final differentiation of B-cells into Ig-secreting cells involved in lymphocyte and monocyte differentiation.", "135"], ["CCL2", "C-C motif chemokine 2", "Chemotactic factor that attracts monocytes and basophils", "80"], ["MMP9", "Matrix metalloproteinase-9", "May play an essential role in local proteolysis of the extracellular matrix and in leukocyte migration", "83"], ["IL8", "Interleukin-8", "A chemotactic factor that attracts neutrophils, basophils, and T-cells, major mediator of the inflammatory response", "101"], ["SPI1", "Spi-1 Proto-Oncogene", "This protein is a transcriptional activator that may be specifically involved in the differentiation or activation of macrophages or B- cells.", "76"], ["ICAM1", "Intercellular adhesion molecule 1", "Encodes a cell surface glycoprotein which is typically expressed on endothelial cells and cells of the immune system", "83"], ["LCP2", "Lymphocyte cytosolic protein 2", "Involved in T-cell antigen receptor mediated signalling", "77"]], "row_count": 11, "column_count": 4, "numeric_cells": 21, "header_rows": 1, "locator": "section[11]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE77459 not downloaded", "asset:data:geo:GSE77459 licence not read", "asset:data:geo:GSE92681 not downloaded", "asset:data:geo:GSE92681 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": "Then, the raw data was converted into the form of an expression matrix and handled with the Linear Models for Microarray data (limma, https://bioconductor.org/packages/limma/) package in Bioconductor."}}, {"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": ["GSE77459", "GSE92681"], "resolved_accessions": ["GSE77459", "GSE92681"], "statements": ["The datasets generated and analysed during the current study are available in GEO DataSets repository, https://www.ncbi.nlm.nih.gov/gds."], "basis": "The paper names GSE77459, GSE92681 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:33046027", "data:geo:GSE77459", "asset:table:pmid:33046027:1", "asset:table:pmid:33046027:2", "asset:table:pmid:33046027:3", "asset:table:pmid:33046027:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE77459"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 30671, "completion_tokens": 1568, "cached_tokens": 784}}, "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:33046027", "type": "paper", "label": "pmid:33046027"}, {"id": "source:pmid:33046027", "type": "manuscript", "label": "PMID 33046027 full text"}, {"id": "data:geo:GSE77459", "type": "dataset", "label": "GEO GSE77459"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33046027", "type": "paper", "label": "pmid:33046027"}, {"id": "source:pmid:33046027", "type": "manuscript", "label": "PMID 33046027 full text"}, {"id": "data:geo:GSE77459", "type": "dataset", "label": "GEO GSE77459"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33046027", "type": "extraction", "used": ["source:pmid:33046027"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE77459", "type": "accession_resolution", "used": ["data:geo:GSE77459"], "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:33046027", "parent_hash": "sha256:e904ba4680c2e901ebcc4c3dfa11a8d37fdd2262a2b931b6d13581de5243879a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE77459 licence not read", "asset:data:geo:GSE77459 not downloaded", "asset:data:geo:GSE92681 licence not read", "asset:data:geo:GSE92681 not downloaded", "execution.not_run", "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": ["evealed by bioinformatics analysis of merged microarray gene expression datasets.", "Methods Two microarray datasets of pulpitis from GEO database were", "ples of normal pulps, respectively using the microarray platform GPL17692 and GPL16956. The details", "atrix and handled with the Linear Models for Microarray data (limma, https://bioconductor.org/packag"], "order_basis": "paper_text_order:46", "id": "assay:1"}, {"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": ["Then, the raw data was converted into the form of an expression matrix and handled with the Linear Models for Microarray data (limma, https://bioconductor.org/packages/limma/) package in Bioconductor."], "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":"2026-11-04T03:34:20+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}}}