{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37158817", "kind": "science-record", "revision": 3, "content_hash": "sha256:d1369e14b2daa868765bc203edb9d4bd60129af3afd82dacf1f71e2929d9d0a2", "created_at": "2026-11-01T19:01:49Z", "updated_at": "2026-11-01T22:09:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "High expression of PPFIA1 in human esophageal squamous cell carcinoma correlates with tumor metastasis and poor prognosis.", "doi": "10.1186/s12885-023-10872-9", "pmid": "37158817", "authors": ["Yongyin Gao", "Lizhao Guan", "Ran Jia", "Wanyi Xiao", "Youming Han", "Yue Li", "Peng Tang", "Zhentao Yu", "Hongdian Zhang"], "journal": "BMC cancer", "year": 2023, "abstract": "BACKGROUND: PTPRF interacting protein alpha 1 (PPFIA1) is reportedly related to the occurrence and progression of several kinds of malignancies. However, its role in esophageal squamous cell carcinoma (ESCC) is unclear. This current study investigated the prognostic significance and biological functions of PPFIA1 in ESCC.\nMETHODS: Oncomine, Gene Expression Profiling Interactive Analysis (GEPIA), and Gene Expression Omnibus (GEO) were used to investigate PPFIA1 expression in esophageal cancer. The relationship between PPFIA1 expression and clinicopathological characteristics and patient survival was evaluated in GSE53625 dataset, and verified in the cDNA array based on qRT-PCR and tissue microarray (TMA) dataset based on immunohistochemistry. The impact of PPFIA1 on the migration and invasion of cancer cells were investigated by wound-healing and transwell assays, respectively.\nRESULTS: The expression of PPFIA1 was obviously increased in ESCC tissues versus adjacent esophageal tissues according to online database analyses (all P < 0.05). High PPFIA1 expression was closely related to several clinicopathological characteristics, including tumor location, histological grade, tumor invasion depth, lymph node metastasis, and tumor-node-metastasis (TNM) stage. High PPFIA1 expression was related to worse outcomes and was identified as an independent prognostic factor of overall survival in ESCC patients (GSE53625 dataset, P = 0.019; cDNA array dataset, P < 0.001; TMA dataset, P = 0.039). Downregulation of PPFIA1 expression can significantly reduce the migration and invasion ability of ESCC cells.\nCONCLUSION: PPFIA1 is related to the migration and invasion of ESCC cells, and can be used as a potential biomarker to evaluate the prognosis of ESCC patients.", "claims": [{"id": "claim-method", "statement": "Survival analysis was carried out through the Kaplan–Meier method and the log-rank test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37158817", "locator": "sections[14] \"Statistical analyses\" paragraph 2", "quote": "Survival analysis was carried out through the Kaplan–Meier method and the log-rank test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37158817", "locator": "sections[32] \"notes\" paragraph 1", "quote": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "High PPFIA1 expression was related to worse outcomes and was identified as an independent prognostic factor of overall survival in ESCC patients (GSE53625 dataset, P = 0.019; cDNA array dataset, P < 0.001; TMA dataset, P = 0.039).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37158817", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "High PPFIA1 expression was related to worse outcomes and was identified as an independent prognostic factor of overall survival in ESCC patients (GSE53625 dataset, P = 0.019; cDNA array dataset, P < 0.001; TMA dataset, P = 0.039)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "High PPFIA1 expression was related to worse outcomes and was identified as an independent prognostic factor of overall survival in ESCC patients (GSE53625 dataset, P = 0.019; cDNA array dataset, P < 0.001; TMA dataset, P = 0.039).", "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:37158817"], "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:GSE20347"], "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:GSE20347"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37158817", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-023-10872-9", "sha256": "sha256:80b114f59feceda642fb257a8b65337b6ebf5e476918ba32f1b8bb237801dbd6", "bytes": 35693, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-023-10872-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10169376", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20347", "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=GSE20347", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20347", "version": null, "note": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM509787", "GSM509788", "GSM509789", "GSM509790", "GSM509791", "GSM509792", "GSM509793", "GSM509794", "GSM509795", "GSM509796", "GSM509797", "GSM509798", "GSM509799", "GSM509800", "GSM509801", "GSM509802", "GSM509803", "GSM509804", "GSM509805", "GSM509806", "GSM509807", "GSM509808", "GSM509809", "GSM509810", "GSM509811", "GSM509812", "GSM509813", "GSM509814", "GSM509815", "GSM509816", "GSM509817", "GSM509818", "GSM509819", "GSM509820"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Analysis of gene expression in esophageal squamous cell carcinoma (ESCC)", "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:GSE23400", "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=GSE23400", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE23400", "version": null, "note": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM573846", "GSM573847", "GSM573848", "GSM573849", "GSM573850", "GSM573851", "GSM573852", "GSM573853", "GSM573854", "GSM573855", "GSM573856", "GSM573857", "GSM573858", "GSM573859", "GSM573860", "GSM573861", "GSM573862", "GSM573863", "GSM573864", "GSM573865", "GSM573866", "GSM573867", "GSM573868", "GSM573869", "GSM573870", "GSM573871", "GSM573872", "GSM573873", "GSM573874", "GSM573875", "GSM573876", "GSM573877", "GSM573878", "GSM573879", "GSM573880", "GSM573881", "GSM573882", "GSM573883", "GSM573884", "GSM573885", "GSM573886", "GSM573887", "GSM573888", "GSM573889", "GSM573890", "GSM573891", "GSM573892", "GSM573893", "GSM573894", "GSM573895", "GSM573896", "GSM573897", "GSM573898", "GSM573899", "GSM573900", "GSM573901", "GSM573902", "GSM573903", "GSM573904", "GSM573905", "GSM573906", "GSM573907", "GSM573908", "GSM573909", "GSM573910", "GSM573911", "GSM573912", "GSM573913", "GSM573914", "GSM573915", "GSM573916", "GSM573917", "GSM573918", "GSM573919", "GSM573920", "GSM573921", "GSM573922", "GSM573923", "GSM573924", "GSM573925", "GSM573926", "GSM573927", "GSM573928", "GSM573929", "GSM573930", "GSM573931", "GSM573932", "GSM573933", "GSM573934", "GSM573935", "GSM573936", "GSM573937", "GSM573938", "GSM573939", "GSM573940", "GSM573941", "GSM573942", "GSM573943", "GSM573944", "GSM573945", "GSM573946", "GSM573947", "GSM573948", "GSM573949", "GSM573950", "GSM573951", "GSM573952", "GSM573953", "GSM573954", "GSM573955", "GSM573956", "GSM573957", "GSM573958", "GSM573959", "GSM573960", "GSM573961", "GSM573962", "GSM573963", "GSM573964", "GSM573965", "GSM573966", "GSM573967", "GSM573968", "GSM573969", "GSM573970", "GSM573971", "GSM573972", "GSM573973", "GSM573974", "GSM573975", "GSM573976", "GSM573977", "GSM573978", "GSM573979", "GSM573980", "GSM573981", "GSM573982", "GSM573983", "GSM573984", "GSM573985", "GSM573986", "GSM573987", "GSM573988", "GSM573989", "GSM573990", "GSM573991", "GSM573992", "GSM573993", "GSM573994", "GSM573995", "GSM573996", "GSM573997", "GSM573998", "GSM573999", "GSM574000", "GSM574001", "GSM574002", "GSM574003", "GSM574004", "GSM574005", "GSM574006", "GSM574007", "GSM574008", "GSM574009", "GSM574010", "GSM574011", "GSM574012", "GSM574013", "GSM574014", "GSM574015", "GSM574016", "GSM574017", "GSM574018", "GSM574019", "GSM574020", "GSM574021", "GSM574022", "GSM574023", "GSM574024", "GSM574025", "GSM574026", "GSM574027", "GSM574028", "GSM574029", "GSM574030", "GSM574031", "GSM574032", "GSM574033", "GSM574034", "GSM574035", "GSM574036", "GSM574037", "GSM574038", "GSM574039", "GSM574040", "GSM574041", "GSM574042", "GSM574043", "GSM574044", "GSM574045", "GSM574046", "GSM574047", "GSM574048", "GSM574049", "GSM574050", "GSM574051", "GSM574052", "GSM574053"], "sample_count": 208, "group_sizes": null, "group_sizes_basis": null, "platform": "97;96", "taxon": "Homo sapiens", "title": "Global gene expression profiling and validation in esophageal squamous cell carcinoma (ESCC)", "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:GSE26886", "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=GSE26886", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26886", "version": null, "note": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM661721", "GSM661722", "GSM661723", "GSM661724", "GSM661725", "GSM661726", "GSM661727", "GSM661728", "GSM661729", "GSM661730", "GSM661731", "GSM661732", "GSM661733", "GSM661734", "GSM661735", "GSM661736", "GSM661737", "GSM661738", "GSM661739", "GSM661740", "GSM661741", "GSM661742", "GSM661743", "GSM661744", "GSM661745", "GSM661746", "GSM661747", "GSM661748", "GSM661749", "GSM661750", "GSM661751", "GSM661752", "GSM661753", "GSM661754", "GSM661755", "GSM661756", "GSM661757", "GSM661758", "GSM661759", "GSM661760", "GSM661761", "GSM661762", "GSM661763", "GSM661764", "GSM661765", "GSM661766", "GSM661767", "GSM661768", "GSM661769", "GSM661770", "GSM661771", "GSM661772", "GSM661773", "GSM661774", "GSM661775", "GSM661776", "GSM661777", "GSM661778", "GSM661779", "GSM661780", "GSM661781", "GSM661782", "GSM661783", "GSM661784", "GSM661785", "GSM661786", "GSM661787", "GSM661788", "GSM661789"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of Barrett's esophagus, adenocarcinoma, esophageal squamous epithelium and squamous cell 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:GSE29001", "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=GSE29001", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29001", "version": null, "note": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM718595", "GSM718596", "GSM718597", "GSM718598", "GSM718599", "GSM718600", "GSM718601", "GSM718602", "GSM718603", "GSM718604", "GSM718605", "GSM718606", "GSM718607", "GSM718608", "GSM718609", "GSM718610", "GSM718611", "GSM718612", "GSM718613", "GSM718614", "GSM718615", "GSM718616", "GSM718617", "GSM718618", "GSM718619", "GSM718620", "GSM718621", "GSM718622", "GSM718623", "GSM718624", "GSM718625", "GSM718626", "GSM718627", "GSM718628", "GSM718629", "GSM718630", "GSM718631", "GSM718632", "GSM718633", "GSM718634", "GSM718635", "GSM718636", "GSM718637", "GSM718638", "GSM718639"], "sample_count": 45, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Identification of Unique Therapeutic Targets in Esophageal Squamous Cell 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:GSE45670", "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=GSE45670", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45670", "version": null, "note": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1111662", "GSM1111663", "GSM1111664", "GSM1111665", "GSM1111666", "GSM1111667", "GSM1111668", "GSM1111669", "GSM1111670", "GSM1111671", "GSM1111672", "GSM1111673", "GSM1111674", "GSM1111675", "GSM1111676", "GSM1111677", "GSM1111678", "GSM1111679", "GSM1111680", "GSM1111681", "GSM1111682", "GSM1111683", "GSM1111684", "GSM1111685", "GSM1111686", "GSM1111687", "GSM1111688", "GSM1111689", "GSM1111690", "GSM1111691", "GSM1111692", "GSM1111693", "GSM1111694", "GSM1111695", "GSM1111696", "GSM1111697", "GSM1111698", "GSM1111699"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from esophageal squamous cell carcinomas and normal esophageal epithelia", "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:GSE53625", "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=GSE53625", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53625", "version": null, "note": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1296956", "GSM1296957", "GSM1296958", "GSM1296959", "GSM1296960", "GSM1296961", "GSM1296962", "GSM1296963", "GSM1296964", "GSM1296965", "GSM1296966", "GSM1296967", "GSM1296968", "GSM1296969", "GSM1296970", "GSM1296971", "GSM1296972", "GSM1296973", "GSM1296974", "GSM1296975", "GSM1296976", "GSM1296977", "GSM1296978", "GSM1296979", "GSM1296980", "GSM1296981", "GSM1296982", "GSM1296983", "GSM1296984", "GSM1296985", "GSM1296986", "GSM1296987", "GSM1296988", "GSM1296989", "GSM1296990", "GSM1296991", "GSM1296992", "GSM1296993", "GSM1296994", "GSM1296995", "GSM1296996", "GSM1296997", "GSM1296998", "GSM1296999", "GSM1297000", "GSM1297001", "GSM1297002", "GSM1297003", "GSM1297004", "GSM1297005", "GSM1297006", "GSM1297007", "GSM1297008", "GSM1297009", "GSM1297010", "GSM1297011", "GSM1297012", "GSM1297013", "GSM1297014", "GSM1297015", "GSM1297016", "GSM1297017", "GSM1297018", "GSM1297019", "GSM1297020", "GSM1297021", "GSM1297022", "GSM1297023", "GSM1297024", "GSM1297025", "GSM1297026", "GSM1297027", "GSM1297028", "GSM1297029", "GSM1297030", "GSM1297031", "GSM1297032", "GSM1297033", "GSM1297034", "GSM1297035", "GSM1297036", "GSM1297037", "GSM1297038", "GSM1297039", "GSM1297040", "GSM1297041", "GSM1297042", "GSM1297043", "GSM1297044", "GSM1297045", "GSM1297046", "GSM1297047", "GSM1297048", "GSM1297049", "GSM1297050", "GSM1297051", "GSM1297052", "GSM1297053", "GSM1297054", "GSM1297055", "GSM1297056", "GSM1297057", "GSM1297058", "GSM1297059", "GSM1297060", "GSM1297061", "GSM1297062", "GSM1297063", "GSM1297064", "GSM1297065", "GSM1297066", "GSM1297067", "GSM1297068", "GSM1297069", "GSM1297070", "GSM1297071", "GSM1297072", "GSM1297073", "GSM1297074", "GSM1297075", "GSM1297076", "GSM1297077", "GSM1297078", "GSM1297079", "GSM1297080", "GSM1297081", "GSM1297082", "GSM1297083", "GSM1297084", "GSM1297085", "GSM1297086", "GSM1297087", "GSM1297088", "GSM1297089", "GSM1297090", "GSM1297091", "GSM1297092", "GSM1297093", "GSM1297094", "GSM1297095", "GSM1297096", "GSM1297097", "GSM1297098", "GSM1297099", "GSM1297100", "GSM1297101", "GSM1297102", "GSM1297103", "GSM1297104", "GSM1297105", "GSM1297106", "GSM1297107", "GSM1297108", "GSM1297109", "GSM1297110", "GSM1297111", "GSM1297112", "GSM1297113", "GSM1297114", "GSM1297115", "GSM1297116", "GSM1297117", "GSM1297118", "GSM1297119", "GSM1297120", "GSM1297121", "GSM1297122", "GSM1297123", "GSM1297124", "GSM1297125", "GSM1297126", "GSM1297127", "GSM1297128", "GSM1297129", "GSM1297130", "GSM1297131", "GSM1297132", "GSM1297133", "GSM1297134", "GSM1297135", "GSM1297136", "GSM1297137", "GSM1297138", "GSM1297139", "GSM1297140", "GSM1297141", "GSM1297142", "GSM1297143", "GSM1297144", "GSM1297145", "GSM1297146", "GSM1297147", "GSM1297148", "GSM1297149", "GSM1297150", "GSM1297151", "GSM1297152", "GSM1297153", "GSM1297154", "GSM1297155", "GSM1297156", "GSM1297157", "GSM1297158", "GSM1297159", "GSM1297160", "GSM1297161", "GSM1297162", "GSM1297163", "GSM1297164", "GSM1297165", "GSM1297166", "GSM1297167", "GSM1297168", "GSM1297169", "GSM1297170", "GSM1297171", "GSM1297172", "GSM1297173", "GSM1297174", "GSM1297175", "GSM1297176", "GSM1297177", "GSM1297178", "GSM1297179", "GSM1297180", "GSM1297181", "GSM1297182", "GSM1297183", "GSM1297184", "GSM1297185", "GSM1297186", "GSM1297187", "GSM1297188", "GSM1297189", "GSM1297190", "GSM1297191", "GSM1297192", "GSM1297193", "GSM1297194", "GSM1297195", "GSM1297196", "GSM1297197", "GSM1297198", "GSM1297199", "GSM1297200", "GSM1297201", "GSM1297202", "GSM1297203", "GSM1297204", "GSM1297205", "GSM1297206", "GSM1297207", "GSM1297208", "GSM1297209", "GSM1297210", "GSM1297211", "GSM1297212", "GSM1297213", "GSM1297214", "GSM1297215", "GSM1297216", "GSM1297217", "GSM1297218", "GSM1297219", "GSM1297220", "GSM1297221", "GSM1297222", "GSM1297223", "GSM1297224", "GSM1297225", "GSM1297226", "GSM1297227", "GSM1297228", "GSM1297229", "GSM1297230", "GSM1297231", "GSM1297232", "GSM1297233", "GSM1297234", "GSM1297235", "GSM1297236", "GSM1297237", "GSM1297238", "GSM1297239", "GSM1297240", "GSM1297241", "GSM1297242", "GSM1297243", "GSM1297244", "GSM1297245", "GSM1297246", "GSM1297247", "GSM1297248", "GSM1297249", "GSM1297250", "GSM1297251", "GSM1297252", "GSM1297253", "GSM1297254", "GSM1297255", "GSM1297256", "GSM1297257", "GSM1297258", "GSM1297259", "GSM1297260", "GSM1297261", "GSM1297262", "GSM1297263", "GSM1297264", "GSM1297265", "GSM1297266", "GSM1297267", "GSM1297268", "GSM1297269", "GSM1297270", "GSM1297271", "GSM1297272", "GSM1297273", "GSM1297274", "GSM1297275", "GSM1297276", "GSM1297277", "GSM1297278", "GSM1297279", "GSM1297280", "GSM1297281", "GSM1297282", "GSM1297283", "GSM1297284", "GSM1297285", "GSM1297286", "GSM1297287", "GSM1297288", "GSM1297289", "GSM1297290", "GSM1297291", "GSM1297292", "GSM1297293", "GSM1297294", "GSM1297295", "GSM1297296", "GSM1297297", "GSM1297298", "GSM1297299", "GSM1297300", "GSM1297301", "GSM1297302", "GSM1297303", "GSM1297304", "GSM1297305", "GSM1297306", "GSM1297307", "GSM1297308", "GSM1297309", "GSM1297310", "GSM1297311", "GSM1297312", "GSM1297313"], "sample_count": 358, "group_sizes": null, "group_sizes_basis": null, "platform": "18109", "taxon": "Homo sapiens", "title": "LncRNA profile study reveals a three-lncRNA signature associated with the survival of esophageal squamous cell carcinoma patients", "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:GSE20347 not downloaded", "asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE23400 not downloaded", "asset:data:geo:GSE23400 licence not read", "asset:data:geo:GSE26886 not downloaded", "asset:data:geo:GSE26886 licence not read", "asset:data:geo:GSE29001 not downloaded", "asset:data:geo:GSE29001 licence not read", "asset:data:geo:GSE45670 not downloaded", "asset:data:geo:GSE45670 licence not read", "asset:data:geo:GSE53625 not downloaded", "asset:data:geo:GSE53625 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Survival analysis was carried out through the Kaplan–Meier method and the log-rank test."}}, {"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": 0.8, "band": "high", "quote": "PPI"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_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": ["GSE53625", "GSE23400", "GSE20347", "GSE29001", "GSE45670", "GSE26886"], "resolved_accessions": ["GSE53625", "GSE23400", "GSE20347", "GSE29001", "GSE45670", "GSE26886"], "statements": ["The datasets that support the findings of this study are available from third parties, with the weblinks provided in the manuscript methodology section and can be located at the following sites: GEPIA (http://gepia.cancer-pku.cn/detail.php), Oncomine (http://www.oncomine.org), GEO database (https://www.ncbi.nlm.nih.gov/geo/), GSE53625 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53625). TCGA database (https://cancergenome.nih.gov/), Kaplan–Meier Plotter (www.kmplot.com) and STRING (http://string-db.org/)."], "basis": "The paper names GSE53625, GSE23400, GSE20347, GSE29001, GSE45670, GSE26886 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": ["logrank_test"], "assets": ["source:pmid:37158817", "data:geo:GSE20347"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20347"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:39:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11218, "completion_tokens": 3344, "cached_tokens": 256}}, "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:37158817", "type": "paper", "label": "pmid:37158817"}, {"id": "source:pmid:37158817", "type": "manuscript", "label": "PMID 37158817 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37158817", "type": "paper", "label": "pmid:37158817"}, {"id": "source:pmid:37158817", "type": "manuscript", "label": "PMID 37158817 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37158817", "type": "extraction", "used": ["source:pmid:37158817"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20347", "type": "accession_resolution", "used": ["data:geo:GSE20347"], "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:37158817", "parent_hash": "sha256:399030edda46863b9fea53a39945782550164f676ae694fc3c1b8b30b42ce4cd", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE20347 not downloaded", "asset:data:geo:GSE23400 licence not read", "asset:data:geo:GSE23400 not downloaded", "asset:data:geo:GSE26886 licence not read", "asset:data:geo:GSE26886 not downloaded", "asset:data:geo:GSE29001 licence not read", "asset:data:geo:GSE29001 not downloaded", "asset:data:geo:GSE45670 licence not read", "asset:data:geo:GSE45670 not downloaded", "asset:data:geo:GSE53625 licence not read", "asset:data:geo:GSE53625 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["n the cDNA array based on qRT-PCR and tissue microarray (TMA) dataset based on immunohistochemistry.", "merase chain reaction (qRT-PCR) An ESCC cDNA microarray with patient diagnosis information was purch", "IA1 in ESCC tissues was detected in a tissue microarray. A Negative PPFIA1 expression in sections of", ", TNM tumor-node-metastasis, TMA TMA, tissue microarray Correlations between PPFIA1 expression and t"], "order_basis": "paper_text_order:774", "id": "assay:1"}, {"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": ["and tissue microarray (TMA) dataset based on immunohistochemistry. The impact of PPFIA1 on the migration and i", "assessed PPFIA1 protein expression using an IHC staining-based TMA dataset containing sample"], "order_basis": "paper_text_order:808", "id": "assay:2"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ified by the 2−∆∆CT method. Cell culture and transfection The human ESCC cell lines Kyse-30 and Ec-109", "hanghai, China). ESCC cells were transiently transfected with these siRNAs using Lipofectamine 2000 r", "the manufacturer's instructions. 48 h after transfection, the RNA and protein were harvested and anal", "ing 10% fetal bovine serum (Gibco, USA). The siRNA targeting PPFIA1 (si-PPFIA1) and negative co"], "order_basis": "paper_text_order:3224", "id": "assay:3"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Survival analysis was carried out through the Kaplan–Meier method and the log-rank test."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T01:48:59+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}}}