{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35600043", "kind": "science-record", "revision": 5, "content_hash": "sha256:4a612c70565817b3166c9501d97fdc8b81b521d8c813d0c2ed000feeb1c59a8d", "created_at": "2026-11-01T18:14:29Z", "updated_at": "2026-11-01T22:49:06Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "NUF2 Is a Potential Immunological and Prognostic Marker for Non-Small-Cell Lung Cancer.", "doi": "10.1155/2022/1161931", "pmid": "35600043", "authors": ["Xia Li", "Lianlian Zhang", "Zhongquan Yi", "Jing Zhou", "Wenchun Song", "Panwen Zhao", "Jixiang Wu", "Jianxiang Song", "Qinggan Ni"], "journal": "Journal of immunology research", "year": 2022, "abstract": "Background: Globally, non-small-cell lung cancer (NSCLC) is one of the most prevalent tumors. Various studies have investigated its etiology, but the molecular mechanism of NSCLC has not been elucidated.\nMethods: The GSE19804, GSE118370, GSE19188, GSE27262, and GSE33532 microarray datasets were obtained from the Gene Expression Omnibus (GEO) database for the identification of genes involved in NSCLC development as well as progression. Then, the identified differentially expressed genes (DEGs) were subjected to functional enrichment analyses. The protein-protein interaction (PPI) network was built after which module analysis was conducted via the Search Tool for Retrieval of Interacting Genes/Proteins (STRING) and Cytoscape. There were 562 DEGs: 98 downregulated genes and 464 upregulated. These DEGs were established to be enriched in p53 signaling pathway, transendothelial leukocyte migration, cell adhesion molecules, contractions of vascular smooth muscles, coagulation and complement cascades, and axon guidance. Assessment of tumor immunity was performed to determine the roles of hub genes.\nResults: There were 562 dysregulated genes, while 12 genes were hub genes. NUF2 was established to be a candidate immunotherapeutic target with potential clinical implications. The 12 hub genes were highly enriched in the p53 signaling pathway, the cell cycle, progesterone-associated oocyte maturation, cellular senescence, and oocyte meiosis. Survival analysis showed that NUF2 is associated with NSCLC occurrence, invasion, and recurrence.\nConclusion: The NUF2 gene discovered in this study helps us clarify the pathomechanisms of NSCLC occurrence as well as progression and provides a potential diagnostic and therapeutic target for NSCLC.", "claims": [{"id": "claim-method", "statement": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used for screening DEGs between NSCLC samples and noncancer samples. Overall survival and disease-free survival analyses of hub genes were performed using the Kaplan-Meier curves in cBioPortal. Between-group differences were evaluated by the two-tailed Student's t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35600043", "locator": "sections[11] \"4.2. Identification DEGS\" paragraph 2", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used for screening DEGs between NSCLC samples and noncancer samples."}, {"asset": "source:pmid:35600043", "locator": "sections[14] \"4.5. Hub Gene Selection and Analysis\" paragraph 2", "quote": "Overall survival and disease-free survival analyses of hub genes were performed using the Kaplan-Meier curves in cBioPortal."}, {"asset": "source:pmid:35600043", "locator": "sections[18] \"4.9. Statistical Analysis\" paragraph 2", "quote": "Between-group differences were evaluated by the two-tailed Student's t-test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35600043", "locator": "sections[20] \"Data Availability\" paragraph 2", "quote": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "NSCLC patients with NUF2 genome changes showed the highest hazard ratio and significantly decreased overall survival (HR = 2.01, CI 1.7-2.39, P = 2.4e − 16).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35600043", "locator": "sections[6] \"2.4. Hub Gene Identification and Analysis\" paragraph 2", "quote": "We noticed that NSCLC patients with changes of NUF2-related genes showed decreased overall survival, while NSCLC patients with NUF2 genome changes showed the highest hazard ratio."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "NSCLC patients with NUF2 genome changes showed the highest hazard ratio and significantly decreased overall survival (HR = 2.01, CI 1.7-2.39, P = 2.4e − 16).", "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:35600043"], "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:GSE118370"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE118370"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35600043", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2022/1161931", "sha256": "sha256:e71c51e8165bba8145d1d39333c67328ffc5a6b3ca46d14e9d714d2e3ff7bc5d", "bytes": 29784, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2022/1161931", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9119754", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE118370", "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=GSE118370", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE118370", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3325818", "GSM3325819", "GSM3325820", "GSM3325821", "GSM3325822", "GSM3325823", "GSM3325824", "GSM3325825", "GSM3325826", "GSM3325827", "GSM3325828", "GSM3325829"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from lung adenocarcinoma tissues and paired normal lung tissues", "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:GSE19188", "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=GSE19188", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19188", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM475656", "GSM475657", "GSM475658", "GSM475659", "GSM475660", "GSM475661", "GSM475662", "GSM475663", "GSM475664", "GSM475665", "GSM475666", "GSM475667", "GSM475668", "GSM475669", "GSM475670", "GSM475671", "GSM475672", "GSM475673", "GSM475674", "GSM475675", "GSM475676", "GSM475677", "GSM475678", "GSM475679", "GSM475680", "GSM475681", "GSM475682", "GSM475683", "GSM475684", "GSM475685", "GSM475686", "GSM475687", "GSM475688", "GSM475689", "GSM475690", "GSM475691", "GSM475692", "GSM475693", "GSM475694", "GSM475695", "GSM475696", "GSM475697", "GSM475698", "GSM475699", "GSM475700", "GSM475701", "GSM475702", "GSM475703", "GSM475704", "GSM475705", "GSM475706", "GSM475707", "GSM475708", "GSM475709", "GSM475710", "GSM475711", "GSM475712", "GSM475713", "GSM475714", "GSM475715", "GSM475716", "GSM475717", "GSM475718", "GSM475719", "GSM475720", "GSM475721", "GSM475722", "GSM475723", "GSM475724", "GSM475725", "GSM475726", "GSM475727", "GSM475728", "GSM475729", "GSM475730", "GSM475731", "GSM475732", "GSM475733", "GSM475734", "GSM475735", "GSM475736", "GSM475737", "GSM475738", "GSM475739", "GSM475740", "GSM475741", "GSM475742", "GSM475743", "GSM475744", "GSM475745", "GSM475746", "GSM475747", "GSM475748", "GSM475749", "GSM475750", "GSM475751", "GSM475752", "GSM475753", "GSM475754", "GSM475755", "GSM475756", "GSM475757", "GSM475758", "GSM475759", "GSM475760", "GSM475761", "GSM475762", "GSM475763", "GSM475764", "GSM475765", "GSM475766", "GSM475767", "GSM475768", "GSM475769", "GSM475770", "GSM475771", "GSM475772", "GSM475773", "GSM475774", "GSM475775", "GSM475776", "GSM475777", "GSM475778", "GSM475779", "GSM475780", "GSM475781", "GSM475782", "GSM475783", "GSM475784", "GSM475785", "GSM475786", "GSM475787", "GSM475788", "GSM475789", "GSM475790", "GSM475791", "GSM475792", "GSM475793", "GSM475794", "GSM475795", "GSM475796", "GSM475797", "GSM475798", "GSM475799", "GSM475800", "GSM475801", "GSM475802", "GSM475803", "GSM475804", "GSM475805", "GSM475806", "GSM475807", "GSM475808", "GSM475809", "GSM475810", "GSM475811"], "sample_count": 156, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for early stage NSCLC", "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:GSE19804", "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=GSE19804", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19804", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM494556", "GSM494557", "GSM494558", "GSM494559", "GSM494560", "GSM494561", "GSM494562", "GSM494563", "GSM494564", "GSM494565", "GSM494566", "GSM494567", "GSM494568", "GSM494569", "GSM494570", "GSM494571", "GSM494572", "GSM494573", "GSM494574", "GSM494575", "GSM494576", "GSM494577", "GSM494578", "GSM494579", "GSM494580", "GSM494581", "GSM494582", "GSM494583", "GSM494584", "GSM494585", "GSM494586", "GSM494587", "GSM494588", "GSM494589", "GSM494590", "GSM494591", "GSM494592", "GSM494593", "GSM494594", "GSM494595", "GSM494596", "GSM494597", "GSM494598", "GSM494599", "GSM494600", "GSM494601", "GSM494602", "GSM494603", "GSM494604", "GSM494605", "GSM494606", "GSM494607", "GSM494608", "GSM494609", "GSM494610", "GSM494611", "GSM494612", "GSM494613", "GSM494614", "GSM494615", "GSM494616", "GSM494617", "GSM494618", "GSM494619", "GSM494620", "GSM494621", "GSM494622", "GSM494623", "GSM494624", "GSM494625", "GSM494626", "GSM494627", "GSM494628", "GSM494629", "GSM494630", "GSM494631", "GSM494632", "GSM494633", "GSM494634", "GSM494635", "GSM494636", "GSM494637", "GSM494638", "GSM494639", "GSM494640", "GSM494641", "GSM494642", "GSM494643", "GSM494644", "GSM494645", "GSM494646", "GSM494647", "GSM494648", "GSM494649", "GSM494650", "GSM494651", "GSM494652", "GSM494653", "GSM494654", "GSM494655", "GSM494656", "GSM494657", "GSM494658", "GSM494659", "GSM494660", "GSM494661", "GSM494662", "GSM494663", "GSM494664", "GSM494665", "GSM494666", "GSM494667", "GSM494668", "GSM494669", "GSM494670", "GSM494671", "GSM494672", "GSM494673", "GSM494674", "GSM494675"], "sample_count": 120, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide screening of transcriptional modulation in non-smoking female lung cancer in Taiwan", "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:GSE27262", "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=GSE27262", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27262", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM673870", "GSM673871", "GSM673872", "GSM673873", "GSM673874", "GSM673875", "GSM673876", "GSM673877", "GSM673878", "GSM673879", "GSM673880", "GSM673881", "GSM673882", "GSM673883", "GSM673884", "GSM673885", "GSM673886", "GSM673887", "GSM673888", "GSM673889", "GSM673890", "GSM673891", "GSM673892", "GSM673893", "GSM673894", "GSM673895", "GSM673896", "GSM673897", "GSM673898", "GSM673899", "GSM673900", "GSM673901", "GSM673902", "GSM673903", "GSM673904", "GSM673905", "GSM673906", "GSM673907", "GSM673908", "GSM673909", "GSM673910", "GSM673911", "GSM673912", "GSM673913", "GSM673914", "GSM673915", "GSM673916", "GSM673917", "GSM673918", "GSM673919"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of Non-small cell lung cancer in Taiwan", "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:GSE33532", "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=GSE33532", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33532", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM835268", "GSM835269", "GSM835270", "GSM835271", "GSM835272", "GSM835273", "GSM835274", "GSM835275", "GSM835276", "GSM835277", "GSM835278", "GSM835279", "GSM835280", "GSM835281", "GSM835282", "GSM835283", "GSM835284", "GSM835285", "GSM835286", "GSM835287", "GSM835288", "GSM835289", "GSM835290", "GSM835291", "GSM835292", "GSM835293", "GSM835294", "GSM835295", "GSM835296", "GSM835297", "GSM835298", "GSM835299", "GSM835300", "GSM835301", "GSM835302", "GSM835303", "GSM835304", "GSM835305", "GSM835306", "GSM835307", "GSM835308", "GSM835309", "GSM835310", "GSM835311", "GSM835312", "GSM835313", "GSM835314", "GSM835315", "GSM835316", "GSM835317", "GSM835318", "GSM835319", "GSM835320", "GSM835321", "GSM835322", "GSM835323", "GSM835324", "GSM835325", "GSM835326", "GSM835327", "GSM835328", "GSM835329", "GSM835330", "GSM835331", "GSM835332", "GSM835333", "GSM835334", "GSM835335", "GSM835336", "GSM835337", "GSM835338", "GSM835339", "GSM835340", "GSM835341", "GSM835342", "GSM835343", "GSM835344", "GSM835345", "GSM835346", "GSM835347", "GSM835348", "GSM835349", "GSM835350", "GSM835351", "GSM835352", "GSM835353", "GSM835354", "GSM835355", "GSM835356", "GSM835357", "GSM835358", "GSM835359", "GSM835360", "GSM835361", "GSM835362", "GSM835363", "GSM835364", "GSM835365", "GSM835366", "GSM835367"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Intratumor heterogeneity of gene expression profiles in early stage non-small cell lung cancer (NSCLC)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE118370 not downloaded", "asset:data:geo:GSE118370 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE27262 not downloaded", "asset:data:geo:GSE27262 licence not read", "asset:data:geo:GSE33532 not downloaded", "asset:data:geo:GSE33532 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "reordered", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used for screening DEGs between NSCLC samples and noncancer samples. Overall survival and disease-free survival analyses of hub genes were performed using the Kaplan-Meier curves in cBioPortal. Between-group differences were evaluated by the two-tailed Student's t-test."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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": ["method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["GSE19804", "GSE118370", "GSE19188", "GSE27262", "GSE33532"], "resolved_accessions": ["GSE19804", "GSE118370", "GSE19188", "GSE27262", "GSE33532"], "statements": ["The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE19804, GSE118370, GSE19188, GSE27262, GSE33532 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": [], "assets": ["source:pmid:35600043", "data:geo:GSE118370"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE118370"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:46:51Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8653, "completion_tokens": 1697, "cached_tokens": 128}}, "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:35600043", "type": "paper", "label": "pmid:35600043"}, {"id": "source:pmid:35600043", "type": "manuscript", "label": "PMID 35600043 full text"}, {"id": "data:geo:GSE118370", "type": "dataset", "label": "GEO GSE118370"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35600043", "type": "paper", "label": "pmid:35600043"}, {"id": "source:pmid:35600043", "type": "manuscript", "label": "PMID 35600043 full text"}, {"id": "data:geo:GSE118370", "type": "dataset", "label": "GEO GSE118370"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35600043", "type": "extraction", "used": ["source:pmid:35600043"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE118370", "type": "accession_resolution", "used": ["data:geo:GSE118370"], "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:35600043", "parent_hash": "sha256:6817e47e01d9c0ea4c3feb9b2c83e0bdcc244345e8db1f51735a57eab91e71ef", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE118370 licence not read", "asset:data:geo:GSE118370 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE27262 licence not read", "asset:data:geo:GSE27262 not downloaded", "asset:data:geo:GSE33532 licence not read", "asset:data:geo:GSE33532 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r) was used for screening DEGs between NSCLC samples and noncancer samples. Overall survival and disease-free survival analyses of hub genes were performed using the Kaplan-Meier curves in cBioPortal. Between-group differences were evaluated by the two-tailed Student's t-test."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:44:47+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}}}