{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38643462", "kind": "science-record", "revision": 5, "content_hash": "sha256:f0f5e3fd56c72dfc25bfd185862cec57e403543b036c6e5b4b32e0ce8e0fbb82", "created_at": "2026-11-01T19:20:36Z", "updated_at": "2026-11-01T22:54:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrative analysis based on the cell cycle-related genes identifies TPX2 as a novel prognostic biomarker associated with tumor immunity in breast cancer.", "doi": "10.18632/aging.205752", "pmid": "38643462", "authors": ["Xinli Liu", "Wenyi Wang", "Bing Chen", "Shengjie Wang"], "journal": "Aging", "year": 2024, "abstract": "BACKGROUND: This study aims to identify the essential cell cycle-related genes associated with prognosis in breast cancer (BRCA), and to verify the relationship between the central gene and immune infiltration, so as to provide detailed and comprehensive information for the treatment of BRCA.\nMATERIALS AND METHODS: Gene expression profiles (GSE10780, GSE21422, GSE61304) and the Cancer Genome Atlas (TCGA) BRCA data were used to identify differentially expressed genes (DEGs) and further functional enrichment analysis. STRING and Cytoscape were employed for the protein-protein interaction (PPI) network construction. TPX2 was viewed as the crucial prognostic gene by the Survival and Cox analysis. Furthermore, the connection between TPX2 expression and immune infiltrating cells and immune checkpoints in BRCA was also performed by the TIMER online database and R software.\nRESULTS: A total of 18 cell cycle-related DEGs were identified in this study. Subsequently, an intersection analysis based on TCGA-BRCA prognostic genes and the above DEGs identified three genes (TPX2, UBE2C, CCNE2) as crucial prognostic candidate biomarkers. Moreover, we also demonstrated that TPX2 is closely associated with immune infiltration in BRCA and a positive relation between TPX2 and PD-L1 expression was firstly detected.\nCONCLUSIONS: These results revealed that TPX2 is a potential prognostic biomarker and closely correlated with immune infiltration in BRCA, which could provide powerful and efficient strategies for breast cancer immunotherapy.", "claims": [{"id": "claim-method", "statement": "The Kaplan-Meier method with the log-rank test was employed for analyzing the survival endpoint of these genes in the study. Multivariate and univariate Cox regression analyses including specific indicators, age, pathological stage, TNM stage, TPX2 expression, were performed in the study, and the nomogram analysis was depicted via “RMS” package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38643462", "locator": "sections[5] \"Identification of prognosis-related DEGs and survival analysis\" paragraph 2", "quote": "The Kaplan-Meier method with the log-rank test was employed for analyzing the survival endpoint of these genes in the study. Multivariate and univariate Cox regression analyses including specific indicators, age, pathological stage, TNM stage, TPX2 expression, were performed in the study, and the nomogram analysis was depicted via “RMS” package."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used in this study are available from the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38643462", "locator": "sections[14] \"Availability of data and material\" paragraph 2", "quote": "The data used in this study are available from the corresponding authors."}], "state": "complete"}, {"id": "claim-target-result", "statement": "These results revealed that TPX2 is a potential prognostic biomarker and closely correlated with immune infiltration in BRCA, which could provide powerful and efficient strategies for breast cancer immunotherapy.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38643462", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "These results revealed that TPX2 is a potential prognostic biomarker and closely correlated with immune infiltration in BRCA, which could provide powerful and efficient strategies for breast cancer immunotherapy."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "These results revealed that TPX2 is a potential prognostic biomarker and closely correlated with immune infiltration in BRCA, which could provide powerful and efficient strategies for breast cancer immunotherapy.", "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:38643462"], "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:EMTAB8107"], "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:EMTAB8107"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38643462", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.205752", "sha256": "sha256:7748d5fcebc62c4ce9f6a8bcb3759e473149d71f893293f6da57e3d7c2ffbca9", "bytes": 45988, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.205752", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11087105", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:EMTAB8107", "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=EMTAB8107", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "EMTAB8107", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:19Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE10780", "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=GSE10780", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10780", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM272133", "GSM272134", "GSM272135", "GSM272136", "GSM272137", "GSM272138", "GSM272139", "GSM272140", "GSM272141", "GSM272142", "GSM272143", "GSM272144", "GSM272145", "GSM272146", "GSM272147", "GSM272148", "GSM272149", "GSM272150", "GSM272151", "GSM272152", "GSM272153", "GSM272154", "GSM272155", "GSM272156", "GSM272157", "GSM272158", "GSM272159", "GSM272160", "GSM272161", "GSM272162", "GSM272163", "GSM272164", "GSM272165", "GSM272166", "GSM272167", "GSM272168", "GSM272169", "GSM272170", "GSM272171", "GSM272172", "GSM272173", "GSM272174", "GSM272175", "GSM272176", "GSM272177", "GSM272178", "GSM272179", "GSM272180", "GSM272181", "GSM272182", "GSM272183", "GSM272184", "GSM272185", "GSM272186", "GSM272187", "GSM272188", "GSM272189", "GSM272190", "GSM272191", "GSM272192", "GSM272193", "GSM272194", "GSM272195", "GSM272196", "GSM272197", "GSM272198", "GSM272199", "GSM272200", "GSM272201", "GSM272202", "GSM272203", "GSM272204", "GSM272205", "GSM272206", "GSM272207", "GSM272208", "GSM272209", "GSM272210", "GSM272211", "GSM272212", "GSM272213", "GSM272214", "GSM272215", "GSM272216", "GSM272217", "GSM272218", "GSM272219", "GSM272220", "GSM272221", "GSM272222", "GSM272223", "GSM272224", "GSM272225", "GSM272226", "GSM272227", "GSM272228", "GSM272229", "GSM272230", "GSM272231", "GSM272232", "GSM272233", "GSM272234", "GSM272235", "GSM272236", "GSM272237", "GSM272238", "GSM272239", "GSM272240", "GSM272241", "GSM272242", "GSM272243", "GSM272244", "GSM272245", "GSM272246", "GSM272247", "GSM272248", "GSM272249", "GSM272250", "GSM272251", "GSM272252", "GSM272253", "GSM272254", "GSM272255", "GSM272256", "GSM272257", "GSM272258", "GSM272259", "GSM272260", "GSM272261", "GSM272262", "GSM272263", "GSM272264", "GSM272265", "GSM272266", "GSM272267", "GSM272268", "GSM272269", "GSM272270", "GSM272271", "GSM272272", "GSM272273", "GSM272274", "GSM272275", "GSM272276", "GSM272277", "GSM272278", "GSM272279", "GSM272280", "GSM272281", "GSM272282", "GSM272283", "GSM272284", "GSM272285", "GSM272286", "GSM272287", "GSM272288", "GSM272289", "GSM272290", "GSM272291", "GSM272292", "GSM272293", "GSM272294", "GSM272295", "GSM272296", "GSM272297", "GSM272298", "GSM272299", "GSM272300", "GSM272301", "GSM272302", "GSM272303", "GSM272304", "GSM272305", "GSM272306", "GSM272307", "GSM272308", "GSM272309", "GSM272310", "GSM272311", "GSM272312", "GSM272313", "GSM272314", "GSM272315", "GSM272316", "GSM272317"], "sample_count": 185, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Proliferative genes dominate malignancy-risk gene signature in histologically-normal breast tissue", "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:GSE110686", "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=GSE110686", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE110686", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3011853", "GSM3011854"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Single-cell RNA-seq of six thousand purified CD3+ T cells from human primary TNBCs", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE148673", "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=GSE148673", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE148673", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4476485", "GSM4476486", "GSM4476487", "GSM4476488", "GSM4476489", "GSM4476490", "GSM4476491", "GSM4476492", "GSM4476493", "GSM4476494", "GSM4476495", "GSM5074416", "GSM5074417"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Delineating copy number and clonal substructure in human tumors from single-cell transcriptomes ", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE176078", "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=GSE176078", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE176078", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5354513", "GSM5354514", "GSM5354515", "GSM5354516", "GSM5354517", "GSM5354518", "GSM5354519", "GSM5354520", "GSM5354521", "GSM5354522", "GSM5354523", "GSM5354524", "GSM5354525", "GSM5354526", "GSM5354527", "GSM5354528", "GSM5354529", "GSM5354530", "GSM5354531", "GSM5354532", "GSM5354533", "GSM5354534", "GSM5354535", "GSM5354536", "GSM5354537", "GSM5354538"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "A single-cell and spatially resolved atlas of human breast cancers", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE21422", "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=GSE21422", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21422", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM535604", "GSM535605", "GSM535606", "GSM535607", "GSM535608", "GSM535609", "GSM535610", "GSM535611", "GSM535612", "GSM535613", "GSM535614", "GSM535615", "GSM535616", "GSM535617", "GSM535618", "GSM535619", "GSM535620", "GSM535621", "GSM535622"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression profiling of human DCIS and invasive ductal breast carcinoma", "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:GSE61304", "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=GSE61304", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE61304", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1501818", "GSM1501819", "GSM1501820", "GSM1501821", "GSM1501822", "GSM1501823", "GSM1501824", "GSM1501825", "GSM1501826", "GSM1501827", "GSM1501828", "GSM1501829", "GSM1501830", "GSM1501831", "GSM1501832", "GSM1501833", "GSM1501834", "GSM1501835", "GSM1501836", "GSM1501837", "GSM1501838", "GSM1501839", "GSM1501840", "GSM1501841", "GSM1501842", "GSM1501843", "GSM1501844", "GSM1501845", "GSM1501846", "GSM1501847", "GSM1501848", "GSM1501849", "GSM1501850", "GSM1501851", "GSM1501852", "GSM1501853", "GSM1501854", "GSM1501855", "GSM1501856", "GSM1501857", "GSM1501858", "GSM1501859", "GSM1501860", "GSM1501861", "GSM1501862", "GSM1501863", "GSM1501864", "GSM1501865", "GSM1501866", "GSM1501867", "GSM1501868", "GSM1501869", "GSM1501870", "GSM1501871", "GSM1501872", "GSM1501873", "GSM1501874", "GSM1501875", "GSM1501876", "GSM1501877", "GSM1501878", "GSM1501879"], "sample_count": 62, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Novel bio-marker discovery for stratification and prognosis of breast cancer patients", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:EMTAB8017", "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=EMTAB8017", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "EMTAB8017", "version": null, "note": "The data used in this study are available from the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are available from the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:19Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:EMTAB8107 not downloaded", "asset:data:geo:EMTAB8107 licence not read", "asset:data:geo:GSE10780 not downloaded", "asset:data:geo:GSE10780 licence not read", "asset:data:geo:GSE110686 not downloaded", "asset:data:geo:GSE110686 licence not read", "asset:data:geo:GSE148673 not downloaded", "asset:data:geo:GSE148673 licence not read", "asset:data:geo:GSE176078 not downloaded", "asset:data:geo:GSE176078 licence not read", "asset:data:geo:GSE21422 not downloaded", "asset:data:geo:GSE21422 licence not read", "asset:data:geo:GSE61304 not downloaded", "asset:data:geo:GSE61304 licence not read", "asset:data:geo:EMTAB8017 not downloaded", "asset:data:geo:EMTAB8017 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The Kaplan-Meier method with the log-rank test was employed for analyzing the survival endpoint of these genes in the study. Multivariate and univariate Cox regression analyses including specific indicators, age, pathological stage, TNM stage, TPX2 expression, were performed in the study, and the nomogram analysis was depicted via “RMS” package."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-5", "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE10780", "GSE21422", "GSE61304", "GSE110686", "GSE176078", "GSE148673", "EMTAB8107", "EMTAB8017"], "resolved_accessions": ["GSE10780", "GSE21422", "GSE61304", "GSE110686", "GSE176078", "GSE148673", "EMTAB8107"], "statements": ["The data used in this study are available from the corresponding authors."], "basis": "The paper names GSE10780, GSE21422, GSE61304, GSE110686, GSE176078, GSE148673, EMTAB8107 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:38643462", "data:geo:EMTAB8107"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:EMTAB8107"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:16:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13915, "completion_tokens": 3674, "cached_tokens": 264}}, "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:38643462", "type": "paper", "label": "pmid:38643462"}, {"id": "source:pmid:38643462", "type": "manuscript", "label": "PMID 38643462 full text"}, {"id": "data:geo:EMTAB8107", "type": "dataset", "label": "GEO EMTAB8107"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38643462", "type": "paper", "label": "pmid:38643462"}, {"id": "source:pmid:38643462", "type": "manuscript", "label": "PMID 38643462 full text"}, {"id": "data:geo:EMTAB8107", "type": "dataset", "label": "GEO EMTAB8107"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38643462", "type": "extraction", "used": ["source:pmid:38643462"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-EMTAB8107", "type": "accession_resolution", "used": ["data:geo:EMTAB8107"], "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:38643462", "parent_hash": "sha256:e7511ac4dda6f96e05f16a0065423624c108a06bb9de407a524ebfa86a89dccc", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:EMTAB8017 licence not read", "asset:data:geo:EMTAB8017 not downloaded", "asset:data:geo:EMTAB8107 licence not read", "asset:data:geo:EMTAB8107 not downloaded", "asset:data:geo:GSE10780 licence not read", "asset:data:geo:GSE10780 not downloaded", "asset:data:geo:GSE110686 licence not read", "asset:data:geo:GSE110686 not downloaded", "asset:data:geo:GSE148673 licence not read", "asset:data:geo:GSE148673 not downloaded", "asset:data:geo:GSE176078 licence not read", "asset:data:geo:GSE176078 not downloaded", "asset:data:geo:GSE21422 licence not read", "asset:data:geo:GSE21422 not downloaded", "asset:data:geo:GSE61304 licence not read", "asset:data:geo:GSE61304 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["s instructions [29]. These cell strains were cultured in an incubator with a criteria of 5% CO2 humid", "reagents All human breast cancer cell lines MCF-7, BT-474, T-47D, MDA-MB-453, MDA-MB-231, SUM-"], "order_basis": "paper_text_order:2919", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The Kaplan-Meier method with the log-rank test was employed for analyzing the survival endpoint of these genes in the study. Multivariate and univariate Cox regression analyses including specific indicators, age, pathological stage, TNM stage, TPX2 expression, were performed in the study, and the nomogram analysis was depicted via “RMS” package."], "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":"2026-11-04T00:38:09+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}}}