{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32575108", "kind": "science-record", "revision": 8, "content_hash": "sha256:93742babfb02f859097c77ba801834d69addd6e6780e4a84a66a67529042940a", "created_at": "2026-11-01T15:41:04Z", "updated_at": "2026-11-01T22:01:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics-Based Study to Investigate Potential Differentially Expressed Genes and miRNAs in Pediatric Sepsis.", "doi": "10.12659/MSM.923881", "pmid": "32575108", "authors": ["Kexin Xie", "Shan Kong", "Fuxing Li", "Yulin Zhang", "Jing Wang", "Weidong Zhao"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2020, "abstract": "BACKGROUND Sepsis is an extremely common health issue with a considerable mortality rate in children. Our understanding about the pathogenic mechanisms of sepsis is limited. The aim of this study was to identify the differential expression genes (DEGs) in pediatric sepsis through comprehensive analysis, and to provide specific insights for the clinical sepsis therapies in children. MATERIAL AND METHODS Three pediatric gene expression profiles (GSE25504, GSE26378, GSE26440) were downloaded from the Gene Expression Omnibus (GEO) database. The difference expression genes (DEGs) between pediatric sepsis and normal control group were screened with the GEO2R online tool. The Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses of the DEGs were performed. Cytoscape with CytoHubba were used to identify the hub genes. Finally, NetworkAnalyst was used to construct the targeted microRNAs (miRNAs) of the hub genes. RESULTS Totally, 160 overlapping upward genes and 61 downward genes were identified. In addition, 5 KEGG pathways, including hematopoietic cell lineage, Staphylococcus aureus infection, starch and sucrose metabolism, osteoclast differentiation, and tumor necrosis factor (TNF) signaling pathway, were significantly enriched using a database for labeling, visualization, and synthetic discovery. In combination with the results of the protein-protein interaction (PPI) network and CytoHubba, 9 hub genes including ITGAM, TLR8, IL1ß, MMP9, MPO, FPR2, ELANE, SPI1, and C3AR1 were selected. Combined with DEG-miRNAs visualization, 5 miRNAs, including has-miR-204-5p, has-miR-211-5p, has-miR-590-5p, and has-miR-21-5p, were predicted as possibly the key miRNAs. CONCLUSIONS Our findings will contribute to identification of potential biomarkers and novel strategies for pediatric sepsis treatment.", "claims": [{"id": "claim-method", "statement": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was applied to perform DEGs analysis between serum samples from pediatric sepsis and control groups, and corrected P-value calculations to obtain |logFC|.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32575108", "locator": "sections[4] \"Differentially expressed genes (DEGs) selection\" paragraph 2", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was applied to perform DEGs analysis between serum samples from pediatric sepsis and control groups, and corrected P-value calculations to obtain |logFC|."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32575108", "locator": "sections[3] \"Microarray data processing\" paragraph 2", "quote": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review."}], "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:32575108"], "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:GSE25504"], "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:GSE25504"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32575108", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.923881", "sha256": "sha256:9a578356b035cfd37e09d17aedcecabaea6285b4bccf6ae184be724fe0c69cb1", "bytes": 40858, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.923881", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7331480", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE25504", "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=GSE25504", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25504", "version": null, "note": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1404208", "GSM1404209", "GSM1404210", "GSM1404211", "GSM1404212", "GSM1404213", "GSM1404214", "GSM1404215", "GSM1404216", "GSM1404217", "GSM1404218", "GSM1404219", "GSM1404220", "GSM1404221", "GSM1404222", "GSM1404223", "GSM1404224", "GSM1404225", "GSM1404226", "GSM1404227", "GSM1404228", "GSM1404229", "GSM1404230", "GSM1404231", "GSM1404232", "GSM1404233", "GSM1404234", "GSM1404235", "GSM1404236", "GSM1404237", "GSM1404238", "GSM1404239", "GSM1404240", "GSM1404241", "GSM1404242", "GSM1404243", "GSM1404244", "GSM1404245", "GSM1404246", "GSM1404247", "GSM1404248", "GSM1404249", "GSM1404250", "GSM1404251", "GSM1404252", "GSM1404253", "GSM1404254", "GSM1404255", "GSM1404256", "GSM1404257", "GSM1404258", "GSM1404259", "GSM1404260", "GSM1404261", "GSM1404262", "GSM1404263", "GSM1404264", "GSM1404265", "GSM1404266", "GSM1404267", "GSM1404268", "GSM1404269", "GSM1404270", "GSM1404271", "GSM1404272", "GSM1404273", "GSM1404274", "GSM1404275", "GSM1404276", "GSM1404277", "GSM1404278", "GSM1404279", "GSM1404280", "GSM1404281", "GSM1404282", "GSM1404283", "GSM1404284", "GSM1404285", "GSM1404286", "GSM1404287", "GSM1404288", "GSM1404289", "GSM1404290", "GSM1404291", "GSM1404292", "GSM1404293", "GSM1404294", "GSM1404295", "GSM1404296", "GSM1404297", "GSM1404298", "GSM1404299", "GSM1404300", "GSM1404301", "GSM1404302", "GSM1404303", "GSM1404304", "GSM1404305", "GSM1404306", "GSM1404307", "GSM1404308", "GSM1404309", "GSM1404310", "GSM1404311", "GSM1404312", "GSM1404313", "GSM1404314", "GSM627008", "GSM627009", "GSM627010", "GSM627011", "GSM627012", "GSM627013", "GSM627014", "GSM627015", "GSM627016", "GSM627017", "GSM627018", "GSM627019", "GSM627020", "GSM627021", "GSM627022", "GSM627023", "GSM627024", "GSM627025", "GSM627026", "GSM627027", "GSM627028", "GSM627029", "GSM627030", "GSM627031", "GSM627032", "GSM627033", "GSM627034", "GSM627035", "GSM627036", "GSM627037", "GSM627038", "GSM627039", "GSM627040", "GSM627041", "GSM627042", "GSM627043", "GSM627044", "GSM627045", "GSM627046", "GSM627047", "GSM627048", "GSM627049", "GSM627050", "GSM627051", "GSM627052", "GSM627053", "GSM627054", "GSM627055", "GSM627056", "GSM627057", "GSM627058", "GSM627059", "GSM627060", "GSM627061", "GSM627062", "GSM627063", "GSM627064", "GSM627065", "GSM627066", "GSM627067", "GSM627068", "GSM627069", "GSM627070"], "sample_count": 170, "group_sizes": null, "group_sizes_basis": null, "platform": "15158;570;6947;13667", "taxon": "Homo sapiens", "title": "Whole blood mRNA expression profiling of host molecular networks in neonatal sepsis", "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:GSE26378", "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=GSE26378", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26378", "version": null, "note": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM647527", "GSM647528", "GSM647529", "GSM647530", "GSM647531", "GSM647532", "GSM647533", "GSM647534", "GSM647535", "GSM647536", "GSM647537", "GSM647538", "GSM647539", "GSM647540", "GSM647541", "GSM647542", "GSM647543", "GSM647544", "GSM647545", "GSM647546", "GSM647547", "GSM647548", "GSM647549", "GSM647550", "GSM647551", "GSM647552", "GSM647553", "GSM647554", "GSM647555", "GSM647556", "GSM647557", "GSM647558", "GSM647559", "GSM647560", "GSM647561", "GSM647562", "GSM647563", "GSM647564", "GSM647565", "GSM647566", "GSM647567", "GSM647568", "GSM647569", "GSM647570", "GSM647571", "GSM647572", "GSM647573", "GSM647574", "GSM647575", "GSM647576", "GSM647577", "GSM647578", "GSM647579", "GSM647580", "GSM647581", "GSM647582", "GSM647583", "GSM647584", "GSM647585", "GSM647586", "GSM647587", "GSM647588", "GSM647589", "GSM647590", "GSM647591", "GSM647592", "GSM647593", "GSM647594", "GSM647595", "GSM647596", "GSM647597", "GSM647598", "GSM647599", "GSM647600", "GSM647601", "GSM647602", "GSM647603", "GSM647604", "GSM647605", "GSM647606", "GSM647607", "GSM647608", "GSM647609", "GSM647610", "GSM647611", "GSM647612", "GSM647613", "GSM647614", "GSM647615", "GSM647616", "GSM647617", "GSM647618", "GSM647619", "GSM647620", "GSM647621", "GSM647622", "GSM647623", "GSM647624", "GSM647625", "GSM647626", "GSM647627", "GSM647628", "GSM647629"], "sample_count": 103, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from validation cohort of children with septic shock", "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:GSE26440", "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=GSE26440", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26440", "version": null, "note": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM648590", "GSM648591", "GSM648592", "GSM648593", "GSM648594", "GSM648595", "GSM648596", "GSM648597", "GSM648598", "GSM648599", "GSM648600", "GSM648601", "GSM648602", "GSM648603", "GSM648604", "GSM648605", "GSM648606", "GSM648607", "GSM648608", "GSM648609", "GSM648610", "GSM648611", "GSM648612", "GSM648613", "GSM648614", "GSM648615", "GSM648616", "GSM648617", "GSM648618", "GSM648619", "GSM648620", "GSM648621", "GSM648622", "GSM648623", "GSM648624", "GSM648625", "GSM648626", "GSM648627", "GSM648628", "GSM648629", "GSM648630", "GSM648631", "GSM648632", "GSM648633", "GSM648634", "GSM648635", "GSM648636", "GSM648637", "GSM648638", "GSM648639", "GSM648640", "GSM648641", "GSM648642", "GSM648643", "GSM648644", "GSM648645", "GSM648646", "GSM648647", "GSM648648", "GSM648649", "GSM648650", "GSM648651", "GSM648652", "GSM648653", "GSM648654", "GSM648655", "GSM648656", "GSM648657", "GSM648658", "GSM648659", "GSM648660", "GSM648661", "GSM648662", "GSM648663", "GSM648664", "GSM648665", "GSM648666", "GSM648667", "GSM648668", "GSM648669", "GSM648670", "GSM648671", "GSM648672", "GSM648673", "GSM648674", "GSM648675", "GSM648676", "GSM648677", "GSM648678", "GSM648679", "GSM648680", "GSM648681", "GSM648682", "GSM648683", "GSM648684", "GSM648685", "GSM648686", "GSM648687", "GSM648688", "GSM648689", "GSM648690", "GSM648691", "GSM648692", "GSM648693", "GSM648694", "GSM648695", "GSM648696", "GSM648697", "GSM648698", "GSM648699", "GSM648700", "GSM648701", "GSM648702", "GSM648703", "GSM648704", "GSM648705", "GSM648706", "GSM648707", "GSM648708", "GSM648709", "GSM648710", "GSM648711", "GSM648712", "GSM648713", "GSM648714", "GSM648715", "GSM648716", "GSM648717", "GSM648718", "GSM648719"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for derivation of septic shock subgroups", "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:32575108:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:37ed0924e1acad8d70560e4bb371bf31dbb50f18ff3c106744d2472c3e8dff58", "bytes": 410, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t1-medscimonit-26-e923881", "version": null, "note": "Details for GEO pediatric sepsis data.", "structure": {"pmcid": "PMC7331480", "section_index": 3, "section_title": "Microarray data processing", "row_count": 4, "column_count": 5}, "table": {"label": "Table 1", "caption": "Details for GEO pediatric sepsis data.", "rows": [["Reference", "GEO", "Platform", "Control", "Sepsis"], ["Dickinson P (2014)", "GSE25504", "GPL6947", "35", "27"], ["Wong HR (2011)", "GSE26378", "GPL570", "21", "82"], ["Wong HR (2011)", "GSE26440", "GPL570", "32", "78"]], "row_count": 4, "column_count": 5, "numeric_cells": 15, "header_rows": 1, "locator": "section[3]/table-wrap[1]#t1-medscimonit-26-e923881"}}, {"id": "asset:table:pmid:32575108:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:de772e843433633b6bf563c554db990a98c62c24969af10dc8ac86678b1ce685", "bytes": 1613, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t2-medscimonit-26-e923881", "version": null, "note": "Screening DEGs in pediatric sepsis patients by integrated microarray.", "structure": {"pmcid": "PMC7331480", "section_index": 9, "section_title": "Sepsis DEGs identification", "row_count": 3, "column_count": 2}, "table": {"label": "Table 2", "caption": "Screening DEGs in pediatric sepsis patients by integrated microarray.", "rows": [["DEGs", "Gene terms"], ["Upregulated", "MMP8 CD177 OLFM4 ARG1 MCEMP1 ANXA3 HP RETN LTF ANKRD22 MMP9 LCN2 VNN1 GPR84 CEACAM1 S100A12 CA4 CYSTM1 CLEC4D SOCS3 TCN1 RGL4 GYG1 PFKFB3 FCGR1B S100P IRAK3 MGAM LILRA5 IL18R1 LRG1 ADGRG3 DYSF ALPL PFKFB2 HK3 CKAP4 PGLYRP1 CD163 ZDHHC19 PADI4 TLR5 PGD NLRC4 SERPINB1 SLC2A3 GADD45A KIF1B ACSL1 ADM BCL6 SORT1 PROK2 STOM SAMSN1 PSTPIP2 PYGL B4GALT5 FCER1G ACER3 C3AR1 CST7 MKNK1 RNASE2 TNFAIP6 IL1RN SIPA1L2 THBS1 FKBP5 IL18RAP SLC22A4 OSCAR PLBD1 CDA FLOT1 SIGLEC5 FAR2 UGCG PGS1 SERPINA1 FAM129A ELANE DEFA4 TSPO ITGAM LILRA3 NCF4 CD55 BASP1 ORM1 ETS2 SIRPA FLOT2 ATP9A MARCKS TLR8 RAB31 FFAR2 CEBPD CCR1 PLIN3 AQP9 CEACAM6 C5AR1 FPR2 CTSD MPO SLC25A37 SEMA4A AGTRAP STXBP2 MSRB1 TRIB1 ALOX5AP HCK TIMP1 GK FGR SPI1 RHAG ADGRE1 MMP25 CD14 CSF3R LILRB3 CREB5 GCA ALPK1 GRN KCNJ2 FPR1 NBEAL2 NAMPT PRKCD CLEC1B STX3 MTF1 NFE2 CEBPB P2RX1 UBE2H ZYX IDI1 FES DENND3 RNF24 G6PD VPS9D1 RALB VNN2 ASAP1 MS4A3 CTSA GRINA GNA15 STX11 BAZ1A SHKBP1 RHOG IL1B"], ["Downregulated", "CD6 GIMAP1 FCRLA KDM2B PIK3IP1 CD8A SKAP1 PCED1B BCAS4 RPL22 PKIA LEF1 DYRK2 SPOCK2 NMT2 ETS1 LDHB CLEC2D PRKCQ-AS1 CD96 ATM FAM102A ITM2A MAL CD3G CD27 CCR7 C12orf57 AUTS2 HLA-DMB PAQR8 RFTN1 EVL PLEKHA1 CLC IL7R PRKCH PASK CD3D FCMR FAM117B CCL5 TRAF5 THEMIS RNF125 ABLIM1 CD2 BCL11B GPR183 RASGRP1 SAMD3 GZMK CD247 NELL2 GZMA TRAT1 GPR18 SH2D1A LRRN3 KLRB1 KLRF1"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t2-medscimonit-26-e923881"}}, {"id": "asset:table:pmid:32575108:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c3ab6650a8c4200f693cca7a1d3dd1f3b95f1696199685515fc1f157f7a38237", "bytes": 1382, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#t3-medscimonit-26-e923881", "version": null, "note": "GO biological process terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 15, "section_title": "Supplementary Data", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 1", "caption": "GO biological process terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Neutrophil degranulation (GO: 0043312)", "3.277e-51", "1.672e-47", "12.09", "1405.58"], ["2", "Neutrophil activation involved in immune response (GO: 0002283)", "5.617e-51", "1.433e-47", "11.99", "1387.48"], ["3", "Neutrophil mediated immunity (GO: 0002446)", "9.578e-51", "1.629e-47", "11.89", "1369.74"], ["4", "Membrane raft assembly (GO: 0001765)", "0.00002597", "0.004734", "45.25", "477.76"], ["5", "Complement receptor mediated signaling pathway (GO: 0002430)", "0.000002892", "0.001342", "36.20", "461.67"], ["6", "Positive regulation of superoxide anion generation (GO: 0032930)", "0.000004505", "0.001642", "32.91", "405.11"], ["7", "Immunoglobulin mediated immune response (GO: 0016064)", "0.00007155", "0.01074", "33.94", "323.93"], ["8", "B cell mediated immunity (GO: 0019724)", "0.00007155", "0.01106", "33.94", "323.93"], ["9", "Regulation of superoxide anion generation (GO: 0032928)", "0.000009593", "0.002577", "27.85", "321.74"], ["10", "Immune response-activating cell surface receptor signaling pathway (GO: 0002429)", "0.000002132", "0.001209", "22.62", "295.44"]], "row_count": 11, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[15]/table-wrap[1]#t3-medscimonit-26-e923881"}}, {"id": "asset:table:pmid:32575108:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e6189e36478595ff5cb2647341c057407d6fee69327392f081e1c805de0e350f", "bytes": 1364, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[2]#t4-medscimonit-26-e923881", "version": null, "note": "GO molecular function terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 15, "section_title": "Supplementary Data", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 2", "caption": "GO molecular function terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Complement receptor activity (GO: 0004875)", "0.000004505", "0.005186", "32.91", "405.11"], ["2", "Phosphofructokinase activity (GO: 0008443)", "0.002461", "0.3147", "25.86", "155.33"], ["3", "Interleukin-1 receptor binding (GO: 0005149)", "0.0005490", "0.1580", "18.10", "135.88"], ["4", "C-C chemokine binding (GO: 0019957)", "0.003257", "0.3124", "22.62", "129.57"], ["5", "UDP-glucosyltransferase activity (GO: 0035251)", "0.004158", "0.3190", "20.11", "110.26"], ["6", "Hydrolase activity, acting on carbon-nitrogen (but not peptide) bonds, in linear amidines (GO: 0016813)", "0.005159", "0.3493", "18.10", "95.33"], ["7", "Protein kinase C activity (GO: 0004697)", "0.005159", "0.3712", "18.10", "95.33"], ["8", "Metalloendopeptidase inhibitor activity (GO: 0008191)", "0.007458", "0.4518", "15.08", "73.88"], ["9", "Cysteine-type endopeptidase inhibitor activity (GO: 0004869)", "0.0002446", "0.09383", "8.87", "73.78"], ["10", "Cysteine-type endopeptidase inhibitor activity involved in apoptotic process (GO: 0043027)", "0.002270", "0.3265", "11.31", "68.87"]], "row_count": 11, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[15]/table-wrap[2]#t4-medscimonit-26-e923881"}}, {"id": "asset:table:pmid:32575108:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:12960f8fe8aed5af1735af52f117b9048e69a6b59950b3455cb9ae6dd7c6de60", "bytes": 1209, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[3]#t5-medscimonit-26-e923881", "version": null, "note": "GO cellular component terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 15, "section_title": "Supplementary Data", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 3", "caption": "GO cellular component terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Specific granule (GO: 0042581)", "1.250e-32", "5.575e-30", "18.67", "1371.13"], ["2", "Tertiary granule (GO: 0070820)", "1.939e-29", "4.324e-27", "17.11", "1130.94"], ["3", "T cell receptor complex (GO: 0042101)", "1.923e-10", "7.795e-9", "39.59", "885.78"], ["4", "Tertiary granule membrane (GO: 0070821)", "8.636e-17", "9.629e-15", "19.84", "733.66"], ["5", "Specific granule lumen (GO: 0035580)", "4.868e-15", "3.618e-13", "20.43", "673.46"], ["6", "Tertiary granule lumen (GO: 1904724)", "7.091e-13", "3.514e-11", "19.74", "552.36"], ["7", "Specific granule membrane (GO: 0035579)", "3.583e-15", "3.196e-13", "15.91", "529.26"], ["8", "Primary lysosome (GO: 0005766)", "0.000002892", "0.00009213", "36.20", "461.67"], ["9", "Secretory granule lumen (GO: 0034774)", "1.576e-20", "2.343e-18", "8.85", "403.53"], ["10", "Ficolin-1-rich granule membrane (GO: 0101003)", "6.019e-11", "2.684e-9", "16.32", "384.05"]], "row_count": 11, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[15]/table-wrap[3]#t5-medscimonit-26-e923881"}}, {"id": "asset:table:pmid:32575108:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1c1a2d6f496f78adae9b3392322e5d465776af9849664c4e168aea94084e63d6", "bytes": 1111, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[4]#t6-medscimonit-26-e923881", "version": null, "note": "KEGG pathway enrichment terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 15, "section_title": "Supplementary Data", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 4", "caption": "KEGG pathway enrichment terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Hematopoietic cell lineage", "1.011e-8", "0.000003115", "10.26", "188.93"], ["2", "Staphylococcus aureus infection", "0.00001001", "0.001028", "9.32", "107.25"], ["3", "Starch and sucrose metabolism", "0.0006476", "0.02849", "10.06", "73.83"], ["4", "Osteoclast differentiation", "0.00001197", "0.0009217", "6.41", "72.68"], ["5", "TNF signaling pathway", "0.00003052", "0.001880", "6.58", "68.43"], ["6", "Legionellosis", "0.0003494", "0.01794", "8.23", "65.48"], ["7", "Transcriptional misregulation in cancer", "0.000007366", "0.001134", "5.35", "63.25"], ["8", "Neomycin, kanamycin and gentamicin biosynthesis", "0.05405", "0.3542", "18.10", "52.81"], ["9", "Inflammatory bowel disease (IBD)", "0.0007588", "0.02597", "6.96", "50.01"], ["10", "Acute myeloid leukemia", "0.0008138", "0.02279", "6.86", "48.77"]], "row_count": 11, "column_count": 6, "numeric_cells": 50, "header_rows": 1, "locator": "section[15]/table-wrap[4]#t6-medscimonit-26-e923881"}}, {"id": "asset:table:pmid:32575108:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5617f5e44564d4aeceba1a3a4fbf21afe2705488e1f2bb686edda09338ff3434", "bytes": 1381, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#db_ds_table-wrap1_reqid_", "version": null, "note": "GO biological process terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 20, "section_title": "Supplementary Materials", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 1", "caption": "GO biological process terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Neutrophil degranulation (GO: 0043312)", "3.277e-51", "1.672e-47", "12.09", "1405.58"], ["2", "Neutrophil activation involved in immune response (GO: 0002283)", "5.617e-51", "1.433e-47", "11.99", "1387.48"], ["3", "Neutrophil mediated immunity (GO: 0002446)", "9.578e-51", "1.629e-47", "11.89", "1369.74"], ["4", "Membrane raft assembly (GO: 0001765)", "0.00002597", "0.004734", "45.25", "477.76"], ["5", "Complement receptor mediated signaling pathway (GO: 0002430)", "0.000002892", "0.001342", "36.20", "461.67"], ["6", "Positive regulation of superoxide anion generation (GO: 0032930)", "0.000004505", "0.001642", "32.91", "405.11"], ["7", "Immunoglobulin mediated immune response (GO: 0016064)", "0.00007155", "0.01074", "33.94", "323.93"], ["8", "B cell mediated immunity (GO: 0019724)", "0.00007155", "0.01106", "33.94", "323.93"], ["9", "Regulation of superoxide anion generation (GO: 0032928)", "0.000009593", "0.002577", "27.85", "321.74"], ["10", "Immune response-activating cell surface receptor signaling pathway (GO: 0002429)", "0.000002132", "0.001209", "22.62", "295.44"]], "row_count": 11, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[20]/table-wrap[1]#db_ds_table-wrap1_reqid_"}}, {"id": "asset:table:pmid:32575108:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:686ef8c9170cf4f2bf13fae3961a0cf8faec1f00e63db958864b95b258d499da", "bytes": 1363, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[2]#db_ds_table-wrap2_reqid_", "version": null, "note": "GO molecular function terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 20, "section_title": "Supplementary Materials", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 2", "caption": "GO molecular function terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Complement receptor activity (GO: 0004875)", "0.000004505", "0.005186", "32.91", "405.11"], ["2", "Phosphofructokinase activity (GO: 0008443)", "0.002461", "0.3147", "25.86", "155.33"], ["3", "Interleukin-1 receptor binding (GO: 0005149)", "0.0005490", "0.1580", "18.10", "135.88"], ["4", "C-C chemokine binding (GO: 0019957)", "0.003257", "0.3124", "22.62", "129.57"], ["5", "UDP-glucosyltransferase activity (GO: 0035251)", "0.004158", "0.3190", "20.11", "110.26"], ["6", "Hydrolase activity, acting on carbon-nitrogen (but not peptide) bonds, in linear amidines (GO: 0016813)", "0.005159", "0.3493", "18.10", "95.33"], ["7", "Protein kinase C activity (GO: 0004697)", "0.005159", "0.3712", "18.10", "95.33"], ["8", "Metalloendopeptidase inhibitor activity (GO: 0008191)", "0.007458", "0.4518", "15.08", "73.88"], ["9", "Cysteine-type endopeptidase inhibitor activity (GO: 0004869)", "0.0002446", "0.09383", "8.87", "73.78"], ["10", "Cysteine-type endopeptidase inhibitor activity involved in apoptotic process (GO: 0043027)", "0.002270", "0.3265", "11.31", "68.87"]], "row_count": 11, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[20]/table-wrap[2]#db_ds_table-wrap2_reqid_"}}, {"id": "asset:table:pmid:32575108:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b54956308d954fd4958ba117dd62937ccc5551536cab3a9ba589160342e1b51a", "bytes": 1208, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[3]#db_ds_table-wrap3_reqid_", "version": null, "note": "GO cellular component terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 20, "section_title": "Supplementary Materials", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 3", "caption": "GO cellular component terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Specific granule (GO: 0042581)", "1.250e-32", "5.575e-30", "18.67", "1371.13"], ["2", "Tertiary granule (GO: 0070820)", "1.939e-29", "4.324e-27", "17.11", "1130.94"], ["3", "T cell receptor complex (GO: 0042101)", "1.923e-10", "7.795e-9", "39.59", "885.78"], ["4", "Tertiary granule membrane (GO: 0070821)", "8.636e-17", "9.629e-15", "19.84", "733.66"], ["5", "Specific granule lumen (GO: 0035580)", "4.868e-15", "3.618e-13", "20.43", "673.46"], ["6", "Tertiary granule lumen (GO: 1904724)", "7.091e-13", "3.514e-11", "19.74", "552.36"], ["7", "Specific granule membrane (GO: 0035579)", "3.583e-15", "3.196e-13", "15.91", "529.26"], ["8", "Primary lysosome (GO: 0005766)", "0.000002892", "0.00009213", "36.20", "461.67"], ["9", "Secretory granule lumen (GO: 0034774)", "1.576e-20", "2.343e-18", "8.85", "403.53"], ["10", "Ficolin-1-rich granule membrane (GO: 0101003)", "6.019e-11", "2.684e-9", "16.32", "384.05"]], "row_count": 11, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[20]/table-wrap[3]#db_ds_table-wrap3_reqid_"}}, {"id": "asset:table:pmid:32575108:10", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1af9dfce210d5e07cbbcf15a1b4c6d39e4bb14da02cc6ed65c9e6af6512a663e", "bytes": 1110, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[4]#db_ds_table-wrap4_reqid_", "version": null, "note": "KEGG pathway enrichment terms for DEGs between the control and pediatric sepsis groups.", "structure": {"pmcid": "PMC7331480", "section_index": 20, "section_title": "Supplementary Materials", "row_count": 11, "column_count": 6}, "table": {"label": "Supplementary Table 4", "caption": "KEGG pathway enrichment terms for DEGs between the control and pediatric sepsis groups.", "rows": [["Index", "Name", "P-value", "Adjusted P-value", "Odds ratio", "Combined score"], ["1", "Hematopoietic cell lineage", "1.011e-8", "0.000003115", "10.26", "188.93"], ["2", "Staphylococcus aureus infection", "0.00001001", "0.001028", "9.32", "107.25"], ["3", "Starch and sucrose metabolism", "0.0006476", "0.02849", "10.06", "73.83"], ["4", "Osteoclast differentiation", "0.00001197", "0.0009217", "6.41", "72.68"], ["5", "TNF signaling pathway", "0.00003052", "0.001880", "6.58", "68.43"], ["6", "Legionellosis", "0.0003494", "0.01794", "8.23", "65.48"], ["7", "Transcriptional misregulation in cancer", "0.000007366", "0.001134", "5.35", "63.25"], ["8", "Neomycin, kanamycin and gentamicin biosynthesis", "0.05405", "0.3542", "18.10", "52.81"], ["9", "Inflammatory bowel disease (IBD)", "0.0007588", "0.02597", "6.96", "50.01"], ["10", "Acute myeloid leukemia", "0.0008138", "0.02279", "6.86", "48.77"]], "row_count": 11, "column_count": 6, "numeric_cells": 50, "header_rows": 1, "locator": "section[20]/table-wrap[4]#db_ds_table-wrap4_reqid_"}}], "gaps": ["asset:data:geo:GSE25504 not downloaded", "asset:data:geo:GSE25504 licence not read", "asset:data:geo:GSE26378 not downloaded", "asset:data:geo:GSE26378 licence not read", "asset:data:geo:GSE26440 not downloaded", "asset:data:geo:GSE26440 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": "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"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R differential expression analysis with corrected P-values and absolute log fold change thresholds", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was applied to perform DEGs analysis between serum samples from pediatric sepsis and control groups, and corrected P-value calculations to obtain |logFC|."}}], "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": ["GSE25504", "GSE26378", "GSE26440"], "resolved_accessions": ["GSE25504", "GSE26378", "GSE26440"], "statements": ["Three microarray datasets (GSE25504, GSE26378, GSE26440) of pediatric sepsis and control samples were collected from the GEO database (https://www.ncbi.nlm.nih.gov/geo/) after a careful review."], "basis": "The paper names GSE25504, GSE26378, GSE26440 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:32575108", "data:geo:GSE25504", "asset:table:pmid:32575108:1", "asset:table:pmid:32575108:2", "asset:table:pmid:32575108:3", "asset:table:pmid:32575108:4", "asset:table:pmid:32575108:5", "asset:table:pmid:32575108:6", "asset:table:pmid:32575108:7", "asset:table:pmid:32575108:8", "asset:table:pmid:32575108:9", "asset:table:pmid:32575108:10"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE25504"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:32Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 35261, "completion_tokens": 1156, "cached_tokens": 528}}, "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:32575108", "type": "paper", "label": "pmid:32575108"}, {"id": "source:pmid:32575108", "type": "manuscript", "label": "PMID 32575108 full text"}, {"id": "data:geo:GSE25504", "type": "dataset", "label": "GEO GSE25504"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32575108", "type": "paper", "label": "pmid:32575108"}, {"id": "source:pmid:32575108", "type": "manuscript", "label": "PMID 32575108 full text"}, {"id": "data:geo:GSE25504", "type": "dataset", "label": "GEO GSE25504"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32575108", "type": "extraction", "used": ["source:pmid:32575108"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE25504", "type": "accession_resolution", "used": ["data:geo:GSE25504"], "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:32575108", "parent_hash": "sha256:1e688f415833ba999a582cf6d43bb7dbe140f3e77892be9297508d389bb02c39", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE25504 licence not read", "asset:data:geo:GSE25504 not downloaded", "asset:data:geo:GSE26378 licence not read", "asset:data:geo:GSE26378 not downloaded", "asset:data:geo:GSE26440 licence not read", "asset:data:geo:GSE26440 not downloaded", "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": ["Material and Methods Microarray data processing Three microarray datasets (G", "and Methods Microarray data processing Three microarray datasets (GSE25504, GSE26378, GSE26440) of p", "lated and downregulated DEGs combined sepsis microarray data were analyzed using an online software", "on Agilent GPL570 platform ([HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array). Details f"], "order_basis": "paper_text_order:1970", "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":"2026-11-04T00:42:28+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}}}