{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33603773", "kind": "science-record", "revision": 8, "content_hash": "sha256:9ca19f2722bd1304afab1914c0b3eb0936badac8b47ac65b29e3a591e35d4a15", "created_at": "2026-11-01T15:41:25Z", "updated_at": "2026-11-01T22:46:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptomic Signatures and Functional Network Analysis of Chronic Rhinosinusitis With Nasal Polyps.", "doi": "10.3389/fgene.2021.609754", "pmid": "33603773", "authors": ["Yun Hao", "Yan Zhao", "Ping Wang", "Kun Du", "Ying Li", "Zhen Yang", "Xiangdong Wang", "Luo Zhang"], "journal": "Frontiers in genetics", "year": 2021, "abstract": "Chronic rhinosinusitis with nasal polyps (CRSwNP) is a chronic sinonasal inflammatory disease with limited treatment options of corticosteroids, sinus surgery, or both. CRSwNP is frequently associated with allergic rhinitis and asthma, but the molecular mechanisms underlying CRSwNP inflammation are not completely understood. We obtained four gene expression profiles (GSE136825, GSE36830, GSE23552, and GSE72713) from four Gene Expression Omnibus (GEO), which collectively included 65 nasal polyp samples from CRSwNP patients and 54 nasal mucosal samples from healthy controls. Using an integrated analysis approach, we identified 76 co-differentially expressed genes (co-DEGs, including 45 upregulated and 31 downregulated) in CRSwNP patients compared with the healthy controls. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses identified the terms including immune effector process, leukocyte migration, regulation of the inflammatory response, Staphylococcus aureus infection, and cytokine-cytokine receptor interaction. protein-protein interaction (PPI) network analysis and real-time quantitative PCR (RT-qPCR) showed that 7 genes might be crucial in CRSwNP pathogenesis. Repurposing drug candidates (Alfadolone, Hydralazine, SC-560, Iopamidol, Iloprost, etc) for CRSwNP treatment were identified from the Connectivity Map (CMap) database. Our results suggest multiple molecular mechanisms, diagnostic biomarkers, potential therapeutic targets, and new repurposing drug candidates for CRSwNP treatment.", "claims": [{"id": "claim-method", "statement": "Differences between groups were assessed by ANOVA.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33603773", "locator": "sections[12] \"Statistical Analysis\" paragraph 2", "quote": "Differences between groups were assessed by ANOVA."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33603773", "locator": "sections[21] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."}], "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:33603773"], "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:GSE136825"], "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:GSE136825"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33603773", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2021.609754", "sha256": "sha256:66eb300ec9f9fc6dd809fd4746682062ddc2c4f49cc06e7d7436857f6486cc84", "bytes": 48094, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2021.609754", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7884819", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE136825", "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=GSE136825", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE136825", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4058752", "GSM4058753", "GSM4058754", "GSM4058755", "GSM4058756", "GSM4058757", "GSM4058758", "GSM4058759", "GSM4058760", "GSM4058761", "GSM4058762", "GSM4058763", "GSM4058764", "GSM4058765", "GSM4058766", "GSM4058767", "GSM4058768", "GSM4058769", "GSM4058770", "GSM4058771", "GSM4058772", "GSM4058773", "GSM4058774", "GSM4058775", "GSM4058776", "GSM4058777", "GSM4058778", "GSM4058779", "GSM4058780", "GSM4058781", "GSM4058782", "GSM4058783", "GSM4058784", "GSM4058785", "GSM4058786", "GSM4058787", "GSM4058788", "GSM4058789", "GSM4058790", "GSM4058791", "GSM4058792", "GSM4058793", "GSM4058794", "GSM4058795", "GSM4058796", "GSM4058797", "GSM4058798", "GSM4058799", "GSM4058800", "GSM4058801", "GSM4058802", "GSM4058803", "GSM4058804", "GSM4058805", "GSM4058806", "GSM4058807", "GSM4058808", "GSM4058809", "GSM4058810", "GSM4058811", "GSM4058812", "GSM4058813", "GSM4058814", "GSM4058815", "GSM4058816", "GSM4058817", "GSM4058818", "GSM4058819", "GSM4058820", "GSM4058821", "GSM4058822", "GSM4058823", "GSM4058824", "GSM4058825", "GSM4058826", "GSM4058827", "GSM4058828", "GSM4058829", "GSM4058830", "GSM4058831", "GSM4058832", "GSM4058833", "GSM4058834", "GSM4058835", "GSM4058836", "GSM4058837", "GSM4058838", "GSM4058839", "GSM4058840", "GSM4058841", "GSM4058842", "GSM4058843", "GSM4058844", "GSM4058845", "GSM4058846", "GSM4058847", "GSM4058848", "GSM4058849", "GSM4058850", "GSM4058851", "GSM4058852", "GSM4058853", "GSM4058854"], "sample_count": 103, "group_sizes": null, "group_sizes_basis": null, "platform": "20301", "taxon": "Homo sapiens", "title": "Whole-transcriptome sequencing reveals heightened inflammation and defective host-defense responses in inflammation and defective host-defense responses in chronic rhinosinusitis with nasal polyps", "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:GSE23552", "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=GSE23552", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE23552", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM577728", "GSM577729", "GSM577730", "GSM577731", "GSM577732", "GSM577733", "GSM577734", "GSM577735", "GSM577736", "GSM577737", "GSM577738", "GSM577739", "GSM577740", "GSM577741", "GSM577742", "GSM577743", "GSM577744", "GSM577745", "GSM577746", "GSM577747", "GSM577748", "GSM577749", "GSM577750", "GSM577751", "GSM577752", "GSM577753", "GSM577754", "GSM577755", "GSM577756", "GSM577757", "GSM577758", "GSM577759", "GSM577760", "GSM577761", "GSM577762", "GSM577763", "GSM577764", "GSM577765", "GSM577766"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Exon Array Analysis of Asthmatic Chronic Rhinosinusitis with Nasal Polyps", "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:GSE36830", "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=GSE36830", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36830", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM902680", "GSM902681", "GSM902682", "GSM902683", "GSM902684", "GSM902685", "GSM902686", "GSM902687", "GSM902688", "GSM902689", "GSM902690", "GSM902691", "GSM902692", "GSM902693", "GSM902694", "GSM902695", "GSM902696", "GSM902697", "GSM902698", "GSM902699", "GSM902700", "GSM902701", "GSM902702", "GSM902703"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of Chronic rhinosinusitis", "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:GSE72713", "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=GSE72713", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE72713", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1868853", "GSM1868854", "GSM1868855", "GSM1868856", "GSM1868857", "GSM1868858", "GSM1868859", "GSM1868860", "GSM1868861"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Transcriptome analysis of eosinophilic and noneosinophilic chronic rhinosinusitis with nasal polyps reveals distinct lncRNA expression profiles", "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:33603773:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:68bbeb4a64c5b493863cd1174e2119d3dd932c2278ace8dfeae2c05158d8f46b", "bytes": 1226, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "The details of GEO datasets for CRSwNP.", "structure": {"pmcid": "PMC7884819", "section_index": 3, "section_title": "Microarray Studies, Datasets and Characteristics of Clinical Samples From the GEO Data Repository", "row_count": 6, "column_count": 11}, "table": {"label": "Table 1", "caption": "The details of GEO datasets for CRSwNP.", "rows": [["GSE", "PMID", "Sample size (n)", "Technology", "Platform", "Instrument", "Age (y)", "Sex, male (n%)", "Number of DEGs", "mRNA"], ["", "", "", "", "", "", "", "", "", "Up", "Down"], ["GSE136825", "PMID: 31439685", "CRSwNP: 42 Control: 28", "High-Throughput sequencing", "GPL20301", "Illumina HiSeq 4000", "NA", "NA", "851", "507", "344"], ["GSE36830", "PMID: 26067893", "CRSwNP: 6 Control: 6", "In situ oligonucleotide", "GPL570", "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "CRSwNP: 38 ± 5 Control: 36 ± 6", "CRSwNP: 4 (67%) Control: 2 (33%)", "286", "149", "137"], ["GSE23522", "PMID: 20625511", "CRSwNP: 11 Control: 17", "In situ oligonucleotide", "GPL5175", "[HuEx-1_0-st] Affymetrix Human Exon 1.0 ST Array [transcript (gene) version]", "CRSwNP: 40 ± 2.788 Control: 31.22 ± 2.913", "CRSwNP: 5 (45%) Control: 9 (53%)", "459", "271", "188"], ["GSE72713", "PMID: 27216292", "CRSwNP: 6 Control: 3", "High-Throughput sequencing", "GPL11154", "Illumina HiSeq 2000 (Homo sapiens)", "CRSwNP: 46.8 ± 4.8 Control: 48.7 ± 7.6", "CRSwNP: 4 (67%) Control: 1 (67%)", "85", "21", "64"]], "row_count": 6, "column_count": 11, "numeric_cells": 38, "header_rows": 2, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33603773:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4392f1414474507390774b78509f7278d805b5c019ebaf7bbf997d527abd4c41", "bytes": 1544, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#T2", "version": null, "note": "Results of CMap analysis of co-DEGs in CRSwNP.", "structure": {"pmcid": "PMC7884819", "section_index": 18, "section_title": "Prediction of Potential Novel Drugs for the Treatment of CRSwNP by CMap", "row_count": 16, "column_count": 9}, "table": {"label": "Table 2", "caption": "Results of CMap analysis of co-DEGs in CRSwNP.", "rows": [["Rank", "CMap name", "Mean", "N", "Enrichment", "P-value", "CID", "Molecular formula", "Group"], ["1", "Alfadolone", "0.715", "3", "0.942", "0.00024", "9798416", "C21H32O4", "Approved"], ["2", "Hydralazine", "0.27", "6", "0.752", "0.00058", "3637", "C8H8N4", "Approved"], ["3", "SC-560", "0.631", "3", "0.905", "0.00176", "4306515", "C17H12ClF3N2O", "Experimental"], ["4", "Iopamidol", "−0.255", "4", "−0.825", "0.00177", "65492", "C17H22I3N3O8", "Approved"], ["5", "Iloprost", "−0.686", "3", "−0.899", "0.00194", "5311181", "C22H32O4", "Approved"], ["6", "Clorgiline", "0.287", "4", "0.8", "0.003", "4380", "C13H15Cl2NO", "Experimental"], ["7", "Cefotetan", "0.484", "3", "0.877", "0.00355", "53025", "C17H17N7O8S4", "Approved"], ["8", "Etynodiol", "−0.319", "4", "−0.793", "0.00374", "14687", "C20H28O2", "Experimental"], ["9", "Disulfiram", "0.576", "5", "0.722", "0.00378", "3117", "C10H20N2S4", "Approved"], ["10", "Ketotifen", "−0.322", "4", "−0.782", "0.00462", "3827", "C19H19NOS", "Approved"], ["11", "Florfenicol", "0.242", "4", "0.764", "0.00585", "114811", "C12H14Cl2FNO4S", "Approved"], ["12", "Clidinium bromide", "−0.303", "4", "−0.753", "0.00746", "19004", "C22H26BrNO3", "Approved"], ["13", "Ramifenazone", "0.62", "4", "0.731", "0.01038", "5037", "C14H19N3O", "Experimental"], ["14", "Nafcillin", "0.454", "4", "0.725", "0.0115", "8982", "C21H22N2O5S", "Approved"], ["15", "Bepridil", "0.284", "4", "0.724", "0.01162", "2351", "C24H34N2O", "Approved"]], "row_count": 16, "column_count": 9, "numeric_cells": 105, "header_rows": 1, "locator": "section[18]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:GSE136825 not downloaded", "asset:data:geo:GSE136825 licence not read", "asset:data:geo:GSE23552 not downloaded", "asset:data:geo:GSE23552 licence not read", "asset:data:geo:GSE36830 not downloaded", "asset:data:geo:GSE36830 licence not read", "asset:data:geo:GSE72713 not downloaded", "asset:data:geo:GSE72713 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differences between groups were assessed by ANOVA."}}, {"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"}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE136825", "GSE36830", "GSE23552", "GSE72713"], "resolved_accessions": ["GSE136825", "GSE36830", "GSE23552", "GSE72713"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s."], "basis": "The paper names GSE136825, GSE36830, GSE23552, GSE72713 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:33603773", "data:geo:GSE136825", "asset:table:pmid:33603773:1", "asset:table:pmid:33603773:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE136825"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:09Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 39228, "completion_tokens": 1764, "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:33603773", "type": "paper", "label": "pmid:33603773"}, {"id": "source:pmid:33603773", "type": "manuscript", "label": "PMID 33603773 full text"}, {"id": "data:geo:GSE136825", "type": "dataset", "label": "GEO GSE136825"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33603773", "type": "paper", "label": "pmid:33603773"}, {"id": "source:pmid:33603773", "type": "manuscript", "label": "PMID 33603773 full text"}, {"id": "data:geo:GSE136825", "type": "dataset", "label": "GEO GSE136825"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33603773", "type": "extraction", "used": ["source:pmid:33603773"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE136825", "type": "accession_resolution", "used": ["data:geo:GSE136825"], "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:33603773", "parent_hash": "sha256:0e7fb827a7a937504e3fcb52d92484b0b1bc7c3abca5f1408679522ff28a7f85", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE136825 licence not read", "asset:data:geo:GSE136825 not downloaded", "asset:data:geo:GSE23552 licence not read", "asset:data:geo:GSE23552 not downloaded", "asset:data:geo:GSE36830 licence not read", "asset:data:geo:GSE36830 not downloaded", "asset:data:geo:GSE72713 licence not read", "asset:data:geo:GSE72713 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ork analysis and real-time quantitative PCR (RT-qPCR) showed that 7 genes might be crucial in CRS", "analysis and real-time quantitative PCR (RT-qPCR) showed that 7 genes might be crucial in CRS", "otein interaction (PPI) network analysis and real-time quantitative PCR (RT-qPCR) showed that 7 genes might be cruci", "ssed genes; CMap, Connectivity Map database; RT-qPCR, real-time quantitative PCR; WB, western blo"], "order_basis": "paper_text_order:1169", "id": "assay:1"}, {"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": ["Materials and Methods Microarray Studies, Datasets and Characteristics of Cli", "Repository In the present study, we selected microarray and high-throughput sequencing datasets of n", "controls evaluated with the GPL570 platform (Affymetrix Human Genome U133 Plus 2.0 Array) (Stevens e", "ens et al., 2015b). GSE23552 is based on the Affymetrix Human Exon 1.0 ST Array and includes nasal p"], "order_basis": "paper_text_order:1643", "id": "assay:2"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["se; RT-qPCR, real-time quantitative PCR; WB, western blot; IHC, immunohistochemistry. Patient Recruitm"], "order_basis": "paper_text_order:3502", "id": "assay:3"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ime quantitative PCR; WB, western blot; IHC, immunohistochemistry. Patient Recruitment This study was approved", "eal-time quantitative PCR; WB, western blot; IHC, immunohistochemistry. Patient Recruitment T"], "order_basis": "paper_text_order:3516", "id": "assay:4"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differences between groups were assessed by ANOVA."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"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":"2026-11-04T03:34:19+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}}}