{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30719133", "kind": "science-record", "revision": 8, "content_hash": "sha256:ad7f942ddaab569b859eac2cbc06441c5d5a1c48d2afed59ec0f65c99c32677c", "created_at": "2026-11-01T15:40:41Z", "updated_at": "2026-11-01T22:00:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "High Expression Levels of AGGF1 and MFAP4 Predict Primary Platinum-Based Chemoresistance and are Associated with Adverse Prognosis in Patients with Serous Ovarian Cancer.", "doi": "10.7150/jca.28127", "pmid": "30719133", "authors": ["Haiyue Zhao", "Qian Sun", "Lisong Li", "Jinhua Zhou", "Cong Zhang", "Ting Hu", "Xuemei Zhou", "Long Zhang", "Baiyu Wang", "Bo Li", "Tao Zhu", "Hong Li"], "journal": "Journal of Cancer", "year": 2019, "abstract": "Primary platinum-based chemoresistance occurs in approximately one-third of patients with serous ovarian cancer (SOC); however, traditional clinical indicators are poor predictors of chemoresistance. So we aimed to identify novel genes as predictors of primary platinum-based chemoresistance. Gene expression microarray analyses were performed to identify the genes related to primary platinum resistance in SOC on two discovery datasets (GSE51373, GSE63885) and one validation dataset (TCGA). Univariate and multivariate analyses with logistic regression were performed to evaluate the predictive values of the genes for platinum resistance. Machine learning algorithms (linear kernel support vector machine and artificial neural network) were applied to build prediction models. Univariate and multivariate analyses with Cox proportional hazards regression and log-rank tests were used to assess the effects of these gene signatures for platinum resistance on prognosis in two independent datasets (GSE9891, GSE32062). AGGF1 and MFAP4 were found highly expressed in patients with platinum-resistant SOC and independently predicted platinum resistance. Platinum resistance prediction models based on these targets had robust predictive power (highest AUC: 0.8056, 95% CI: 0.6338-0.9773; lowest AUC: 0.7245, 95% CI: 0.6052-0.8438). An AGGF1- and MFAP4-centered protein interaction network was built, and hypothetical regulatory pathways were identified. Enrichment analysis indicated that aberrations of extracellular matrix may play important roles in platinum resistance in SOC. High AGGF1 and MFAP4 expression levels were also related to shorter recurrence-free and overall survival in patients with SOC after adjustment for other clinical variables. Therefore, AGGF1 and MFAP4 are potential predictive biomarkers for response to platinum-based chemotherapy and survival outcomes in SOC.", "claims": [{"id": "claim-method", "statement": "Univariate analysis with Cox proportional hazards regression model was used to evaluate the correlations of AGGF1 and MFAP4 expression statuses with RFS and OS, and multivariate analysis with Cox proportional hazards regression model was applied to test the independent predictive ability of these two gene signatures for RFS and OS after adjusting for various clinical characteristics.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30719133", "locator": "sections[9] \"Survival analysis of AGGF1 and MFAP4\" paragraph 2", "quote": "Univariate analysis with Cox proportional hazards regression model was used to evaluate the correlations of AGGF1 and MFAP4 expression statuses with RFS and OS, and multivariate analysis with Cox proportional hazards regression model was applied to test the independent predictive ability of these two gene signatures for RFS and OS after adjusting for various clinical characteristics."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30719133", "locator": "sections[5] \"Screening and validation of platinum resistance-related genes\" paragraph 2", "quote": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:30719133"], "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:GSE32062"], "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:GSE32062"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30719133", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.28127", "sha256": "sha256:746ab498e5f38de34d8bd18bc1fc40231fd1f8d0051ac95633b6dcc116d42d28", "bytes": 43238, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.28127", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6360311", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE32062", "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=GSE32062", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32062", "version": null, "note": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM794865", "GSM794866", "GSM794867", "GSM794868", "GSM794869", "GSM794870", "GSM794871", "GSM794872", "GSM794873", "GSM794874", "GSM794875", "GSM794876", "GSM794877", "GSM794878", "GSM794879", "GSM794880", "GSM794881", "GSM794882", "GSM794883", "GSM794884", "GSM794885", "GSM794886", "GSM794887", "GSM794888", "GSM794889", "GSM794890", "GSM794891", "GSM794892", "GSM794893", "GSM794894", "GSM794895", "GSM794896", "GSM794897", "GSM794898", "GSM794899", "GSM794900", "GSM794901", "GSM794902", "GSM794903", "GSM794904", "GSM794905", "GSM794906", "GSM794907", "GSM794908", "GSM794909", "GSM794910", "GSM794911", "GSM794912", "GSM794913", "GSM794914", "GSM794915", "GSM794916", "GSM794917", "GSM794918", "GSM794919", "GSM794920", "GSM794921", "GSM794922", "GSM794923", "GSM794924", "GSM794925", "GSM794926", "GSM794927", "GSM794928", "GSM794929", "GSM794930", "GSM794931", "GSM794932", "GSM794933", "GSM794934", "GSM794935", "GSM794936", "GSM794937", "GSM794938", "GSM794939", "GSM794940", "GSM794941", "GSM794942", "GSM794943", "GSM794944", "GSM794945", "GSM794946", "GSM794947", "GSM794948", "GSM794949", "GSM794950", "GSM794951", "GSM794952", "GSM794953", "GSM794954", "GSM794955", "GSM794956", "GSM794957", "GSM794958", "GSM794959", "GSM794960", "GSM794961", "GSM794962", "GSM794963", "GSM794964", "GSM794965", "GSM794966", "GSM794967", "GSM794968", "GSM794969", "GSM794970", "GSM794971", "GSM794972", "GSM794973", "GSM794974", "GSM794975", "GSM794976", "GSM794977", "GSM794978", "GSM794979", "GSM794980", "GSM794981", "GSM794982", "GSM794983", "GSM794984", "GSM794985", "GSM794986", "GSM794987", "GSM794988", "GSM794989", "GSM794990", "GSM794991", "GSM794992", "GSM794993", "GSM794994", "GSM794995", "GSM794996", "GSM794997", "GSM794998", "GSM794999", "GSM795000", "GSM795001", "GSM795002", "GSM795003", "GSM795004", "GSM795005", "GSM795006", "GSM795007", "GSM795008", "GSM795009", "GSM795010", "GSM795011", "GSM795012", "GSM795013", "GSM795014", "GSM795015", "GSM795016", "GSM795017", "GSM795018", "GSM795019", "GSM795020", "GSM795021", "GSM795022", "GSM795023", "GSM795024", "GSM795025", "GSM795026", "GSM795027", "GSM795028", "GSM795029", "GSM795030", "GSM795031", "GSM795032", "GSM795033", "GSM795034", "GSM795035", "GSM795036", "GSM795037", "GSM795038", "GSM795039", "GSM795040", "GSM795041", "GSM795042", "GSM795043", "GSM795044", "GSM795045", "GSM795046", "GSM795047", "GSM795048", "GSM795049", "GSM795050", "GSM795051", "GSM795052", "GSM795053", "GSM795054", "GSM795055", "GSM795056", "GSM795057", "GSM795058", "GSM795059", "GSM795060", "GSM795061", "GSM795062", "GSM795063", "GSM795064", "GSM795065", "GSM795066", "GSM795067", "GSM795068", "GSM795069", "GSM795070", "GSM795071", "GSM795072", "GSM795073", "GSM795074", "GSM795075", "GSM795076", "GSM795077", "GSM795078", "GSM795079", "GSM795080", "GSM795081", "GSM795082", "GSM795083", "GSM795084", "GSM795085", "GSM795086", "GSM795087", "GSM795088", "GSM795089", "GSM795090", "GSM795091", "GSM795092", "GSM795093", "GSM795094", "GSM795095", "GSM795096", "GSM795097", "GSM795098", "GSM795099", "GSM795100", "GSM795101", "GSM795102", "GSM795103", "GSM795104", "GSM795105", "GSM795106", "GSM795107", "GSM795108", "GSM795109", "GSM795110", "GSM795111", "GSM795112", "GSM795113", "GSM795114", "GSM795115", "GSM795116", "GSM795117", "GSM795118", "GSM795119", "GSM795120", "GSM795121", "GSM795122", "GSM795123", "GSM795124", "GSM797484", "GSM797485", "GSM797486", "GSM797487", "GSM797488", "GSM797489", "GSM797490", "GSM797491", "GSM797492", "GSM797493"], "sample_count": 270, "group_sizes": null, "group_sizes_basis": null, "platform": "570;6480", "taxon": "Homo sapiens", "title": "Immune-activation as a therapeutic direction for patients with high-risk ovarian cancer based on gene expression signature (1)", "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:GSE51373", "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=GSE51373", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51373", "version": null, "note": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1243877", "GSM1243878", "GSM1243879", "GSM1243880", "GSM1243881", "GSM1243882", "GSM1243883", "GSM1243884", "GSM1243885", "GSM1243886", "GSM1243887", "GSM1243888", "GSM1243889", "GSM1243890", "GSM1243891", "GSM1243892", "GSM1243893", "GSM1243894", "GSM1243895", "GSM1243896", "GSM1243897", "GSM1243898", "GSM1243899", "GSM1243900", "GSM1243901", "GSM1243902", "GSM1243903", "GSM1243904"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data from high grade serous ovarian cancer", "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:GSE63885", "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=GSE63885", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63885", "version": null, "note": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1559299", "GSM1559300", "GSM1559301", "GSM1559302", "GSM1559303", "GSM1559304", "GSM1559305", "GSM1559306", "GSM1559307", "GSM1559308", "GSM1559309", "GSM1559310", "GSM1559311", "GSM1559312", "GSM1559313", "GSM1559314", "GSM1559315", "GSM1559316", "GSM1559317", "GSM1559318", "GSM1559319", "GSM1559320", "GSM1559321", "GSM1559322", "GSM1559323", "GSM1559324", "GSM1559325", "GSM1559326", "GSM1559327", "GSM1559328", "GSM1559329", "GSM1559330", "GSM1559331", "GSM1559332", "GSM1559333", "GSM1559334", "GSM1559335", "GSM1559336", "GSM1559337", "GSM1559338", "GSM1559339", "GSM1559340", "GSM1559341", "GSM1559342", "GSM1559343", "GSM1559344", "GSM1559345", "GSM1559346", "GSM1559347", "GSM1559348", "GSM1559349", "GSM1559350", "GSM1559351", "GSM1559352", "GSM1559353", "GSM1559354", "GSM1559355", "GSM1559356", "GSM1559357", "GSM1559358", "GSM1559359", "GSM1559360", "GSM1559361", "GSM1559362", "GSM1559363", "GSM1559364", "GSM1559365", "GSM1559366", "GSM1559367", "GSM1559368", "GSM1559369", "GSM1559370", "GSM1559371", "GSM1559372", "GSM1559373", "GSM1559374", "GSM1559375", "GSM1559376", "GSM1559377", "GSM1559378", "GSM1559379", "GSM1559380", "GSM1559381", "GSM1559382", "GSM1559383", "GSM1559384", "GSM1559385", "GSM1559386", "GSM1559387", "GSM1559388", "GSM1559389", "GSM1559390", "GSM1559391", "GSM1559392", "GSM1559393", "GSM1559394", "GSM1559395", "GSM1559396", "GSM1559397", "GSM1559398", "GSM1559399"], "sample_count": 101, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling in ovarian cancer", "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:GSE9891", "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=GSE9891", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE9891", "version": null, "note": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM249714", "GSM249715", "GSM249716", "GSM249717", "GSM249718", "GSM249719", "GSM249720", "GSM249721", "GSM249722", "GSM249723", "GSM249724", "GSM249725", "GSM249726", "GSM249727", "GSM249728", "GSM249729", "GSM249730", "GSM249731", "GSM249732", "GSM249733", "GSM249734", "GSM249735", "GSM249736", "GSM249737", "GSM249738", "GSM249739", "GSM249740", "GSM249741", "GSM249742", "GSM249743", "GSM249744", "GSM249745", "GSM249746", "GSM249747", "GSM249748", "GSM249749", "GSM249750", "GSM249751", "GSM249752", "GSM249753", "GSM249754", "GSM249755", "GSM249756", "GSM249757", "GSM249758", "GSM249759", "GSM249760", "GSM249761", "GSM249762", "GSM249763", "GSM249764", "GSM249765", "GSM249766", "GSM249767", "GSM249768", "GSM249769", "GSM249770", "GSM249771", "GSM249773", "GSM249774", "GSM249775", "GSM249776", "GSM249777", "GSM249778", "GSM249779", "GSM249780", "GSM249781", "GSM249782", "GSM249783", "GSM249784", "GSM249785", "GSM249786", "GSM249788", "GSM249789", "GSM249790", "GSM249791", "GSM249792", "GSM249793", "GSM249794", "GSM249795", "GSM249796", "GSM249797", "GSM249798", "GSM249799", "GSM249800", "GSM249801", "GSM249802", "GSM249803", "GSM249804", "GSM249805", "GSM249806", "GSM249807", "GSM249808", "GSM249809", "GSM249810", "GSM249811", "GSM249812", "GSM249813", "GSM249814", "GSM249815", "GSM249816", "GSM249817", "GSM249818", "GSM249819", "GSM249820", "GSM249821", "GSM249822", "GSM249823", "GSM249824", "GSM249825", "GSM249826", "GSM249827", "GSM249828", "GSM249829", "GSM249830", "GSM249831", "GSM249832", "GSM249833", "GSM249834", "GSM249835", "GSM249836", "GSM249837", "GSM249838", "GSM249839", "GSM249840", "GSM249841", "GSM249842", "GSM249843", "GSM249844", "GSM249845", "GSM249846", "GSM249847", "GSM249848", "GSM249849", "GSM249850", "GSM249851", "GSM249852", "GSM249853", "GSM249854", "GSM249855", "GSM249856", "GSM249857", "GSM249858", "GSM249859", "GSM249860", "GSM249861", "GSM249862", "GSM249863", "GSM249864", "GSM249865", "GSM249866", "GSM249867", "GSM249868", "GSM249869", "GSM249870", "GSM249871", "GSM249872", "GSM249873", "GSM249874", "GSM249875", "GSM249876", "GSM249877", "GSM249878", "GSM249879", "GSM249880", "GSM249881", "GSM249882", "GSM249883", "GSM249884", "GSM249885", "GSM249886", "GSM249887", "GSM249888", "GSM249889", "GSM249890", "GSM249891", "GSM249892", "GSM249893", "GSM249894", "GSM249895", "GSM249896", "GSM249897", "GSM249898", "GSM249899", "GSM249900", "GSM249901", "GSM249902", "GSM249903", "GSM249904", "GSM249905", "GSM249906", "GSM249907", "GSM249908", "GSM249909", "GSM249910", "GSM249911", "GSM249912", "GSM249913", "GSM249914", "GSM249915", "GSM249916", "GSM249917", "GSM249918", "GSM249919", "GSM249920", "GSM249921", "GSM249922", "GSM249923", "GSM249924", "GSM249925", "GSM249926", "GSM249927", "GSM249928", "GSM249929", "GSM249930", "GSM249931", "GSM249932", "GSM249933", "GSM249934", "GSM249935", "GSM249936", "GSM249937", "GSM249938", "GSM249939", "GSM249940", "GSM249941", "GSM249942", "GSM249943", "GSM249944", "GSM249945", "GSM249946", "GSM249947", "GSM249948", "GSM249949", "GSM249950", "GSM249951", "GSM249953", "GSM249954", "GSM249955", "GSM249956", "GSM249957", "GSM249958", "GSM249959", "GSM249960", "GSM249961", "GSM249962", "GSM249963", "GSM249964", "GSM249965", "GSM249966", "GSM249967", "GSM249968", "GSM249969", "GSM249970", "GSM249971", "GSM249972", "GSM249973", "GSM249974", "GSM249975", "GSM249976", "GSM249977", "GSM249978", "GSM249979", "GSM249980", "GSM249981", "GSM249982", "GSM249983", "GSM249984", "GSM249985", "GSM249986", "GSM249987", "GSM249988", "GSM249989", "GSM249990", "GSM249991", "GSM249992", "GSM249993", "GSM249994", "GSM249995", "GSM249996", "GSM249997", "GSM249998", "GSM249999", "GSM250000", "GSM250001"], "sample_count": 285, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression profile of 285 ovarian tumour samples", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30719133:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a7b097219b57cc93c313e8c8e6f6aeba553ed8f0c1219811fc77f8ed29939cd7", "bytes": 896, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "General information of involved 3 datasets for developing gene signatures of predicting platinum resistance.", "structure": {"pmcid": "PMC6360311", "section_index": 3, "section_title": "Preparation of SOC datasets", "row_count": 17, "column_count": 4}, "table": {"label": "Table 1", "caption": "General information of involved 3 datasets for developing gene signatures of predicting platinum resistance.", "rows": [["Characteristic", "GSE63885", "GSE51373", "TCGA"], ["Platform", "HG-U133_Plus_2", "HG-U133_Plus_2", "HT_HG-U133A"], ["Total sample number", "101", "28", "578"], ["Enrolled samples*", "70", "28", "454"], ["Age", "", "", ""], ["median (range)", "/", "54 (47 - 79)", "58 (26 - 89)"], ["Chemotherapeutic response", "", ""], ["sensitive", "38", "18", "318"], ["resistance", "32", "10", "136"], ["Tumor grade", "", "", ""], ["1/2/3/4/unknown", "0/9/46/15/0", "high grade", "5/55/383/1/10"], ["Tumor stage", "", "", ""], ["I/II/III/IV/unknown", "0/2/59/9/0", "0/5/19/3/1", "13/21/350/68/2"], ["Debulking", "", "", ""], ["optimal", "14", "/", "301"], ["suboptimal", "56", "/", "111"], ["unknown", "0", "/", "42"]], "row_count": 17, "column_count": 4, "numeric_cells": 31, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30719133:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aca598dbcbf9fdfd1c7aeeff4d59036ed4e6e9d29a3f23fc884815fedb856b77", "bytes": 2203, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Univariable and multivariable logistic regression models for platinum resistance in the discovery and validation datasets.", "structure": {"pmcid": "PMC6360311", "section_index": 12, "section_title": "AGGF and MFAP4 were independent predictors of primary platinum resistance", "row_count": 31, "column_count": 8}, "table": {"label": "Table 2", "caption": "Univariable and multivariable logistic regression models for platinum resistance in the discovery and validation datasets.", "rows": [["Datasets and clinical factors", "Univariate analysis", "Multivariate analysis"], ["OR", "95%CI", "p value", "OR", "95%CI", "p value"], ["GSE63885"], ["Tumor stage", "II", "1 (reference)", "1 (reference)"], ["III", "13205836.02", "0 - Inf", "0.99", "3537708.16", "0 - Inf", "0.99"], ["IV", "19564201.51", "0 - Inf", "0.99", "4665494.34", "0 - Inf", "0.99"], ["Tumor grade", "G2", "1 (reference)", "1 (reference)"], ["G3", "2.94", "0.55 - 15.7", "0.20", "1.87", "0.27 - 12.9", "0.52"], ["G4", "5.25", "0.8 - 34.43", "0.08", "3.05", "0.36 - 26.11", "0.30"], ["AGGF1", "high vs. low", "3.71", "1.33 - 10.32", "0.01", "3.32", "1.07 - 10.28", "0.03"], ["MFAP4", "high vs. low", "4.67", "1.69 - 12.9", "0.003", "3.64", "1.18 - 11.22", "0.02"], ["GSE51373"], ["Tumor stage", "II", "1 (reference)", "1 (reference)"], ["III", "2.33", "0.22 - 25.24", "0.48", "0.64", "0 - 139.25", "0.87"], ["IV", "8", "0.31 - 206.37", "0.21", "0.52", "0 - 279.37", "0.83"], ["Age", ">=60 vs. <60", "0.13", "0.01 - 1.22", "0.07", "0.11", "0 - 3.02", "0.19"], ["AGGF1", "high vs. low", "14.14", "1.46 - 137.3", "0.02", "18.51", "0.93 - 369.88", "0.05"], ["MFAP4", "high vs. low", "10.4", "1.62 - 66.9", "0.01", "15.22", "1.11 - 207.9", "0.04"], ["TCGA"], ["Tumor stage", "Ⅰ", "1 (reference)", "1 (reference)"], ["II", "0.28", "0.02 - 3.39", "0.31", "0", "0 - Inf", "0.98"], ["III", "2.39", "0.52 - 10.97", "0.26", "1.02", "0.2 - 5.06", "0.98"], ["IV", "3.2", "0.66 -15.61", "0.15", "1.64", "0.31 - 8.72", "0.56"], ["Tumor grade", "G1", "1 (reference)", "1 (reference)"], ["G2", "1.95", "0.2 - 18.7", "0.56", "1.5", "0.13 - 16.7", "0.74"], ["G3", "1.72", "0.19 - 15.52", "0.63", "1.15", "0.11 - 11.81", "0.90"], ["G4", "0", "0 - Inf", "0.98", "0", "0 - Inf", "0.99"], ["Age", ">=60 vs. <60", "1.08", "0.72 - 1.62", "0.71", "0.99", "0.62 - 1.59", "0.98"], ["Surgery", "Suboptimal vs. Optimal", "3.36", "2.13 - 5.3", "< 0.001", "3.16", "1.93 - 5.16", "< 0.001"], ["AGGF1", "high vs. low", "2.24", "1.47 - 3.41", "< 0.001", "2.54", "1.58 - 4.08", "< 0.001"], ["MFAP4", "high vs low", "1.81", "1.21 - 2.72", "0.004", "1.64", "1.03 - 2.62", "0.03"]], "row_count": 31, "column_count": 8, "numeric_cells": 142, "header_rows": 2, "locator": "section[12]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:30719133:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9a0a38a3d4aacc11a61c3b4353cf879248d710a39fa274e7d85b103bff9d6aca", "bytes": 1787, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#T3A", "version": null, "note": "Univariate and multivariate Cox regression analysis for recurrence free survival in GSE9891 and GSE32062.", "structure": {"pmcid": "PMC6360311", "section_index": 19, "section_title": "(untitled)", "row_count": 22, "column_count": 8}, "table": {"label": "Table 3A", "caption": "Univariate and multivariate Cox regression analysis for recurrence free survival in GSE9891 and GSE32062.", "rows": [["Datasets and clinical factors", "Univariate analysis", "Multivariate analysis"], ["HR", "95%CI", "p value", "HR", "95%CI", "p value"], ["GSE9891"], ["Age", "≥60y vs. <60y", "1.282", "0.954 -1.724", "0.10", "1.479", "1.056 - 2.071", "0.023"], ["Tumor stage", "I", "1 (reference)", "1 (reference)"], ["II", "2.603", "0.477 - 14.22", "0.269", "2.972", "0.540 - 16.377", "0.211"], ["III", "9.774", "2.418 - 39.51", "0.001", "7.966", "1.941 - 32.692", "0.004"], ["IV", "14.809", "3.452 - 63.52", "2.86e-04", "10.498", "2.314 - 47.623", "0.002"], ["Tumor grade", "G1", "1 (reference)", "1 (reference)"], ["G2", "3.116", "1.252 - 7.755", "0.015", "1.711", "0.604 - 4.845", "0.312"], ["G3", "2.723", "1.109 - 6.684", "0.029", "1.406", "0.502 - 3.936", "0.517"], ["Surgery", "Suboptimal vs. optimal", "2.058", "1.489 - 2.844", "1.218e-05", "1.704", "1.203 - 2.413", "0.003"], ["AGGF1", "high vs. low", "1.532", "1.071 - 2.192", "0.020", "1.578", "1.069 - 2.330", "0.022"], ["MFAP4", "high vs. low", "1.708", "1.260 - 2.315", "5.595e-04", "1.418", "1.003 - 2.006", "0.048"], ["GSE32062"], ["Tumor stage", "III", "1 (reference)", "1 (reference)"], ["IV", "1.515", "1.088 - 2.109", "0.014", "1.327", "0.948 - 1.858", "0.099"], ["Tumor grade", "G2", "1 (reference)", "1 (reference)"], ["G3", "1.151", "0.868 - 1.527", "0.330", "1.121", "0.840 - 1.498", "0.438"], ["Surgery", "Suboptimal vs. optimal", "1.772", "1.315 - 2.387", "1.683e-04", "1.667", "1.234 - 2.250", "0.001"], ["AGGF1", "high vs. low", "1.777", "1.263 - 2.5", "9.666e-04", "1.757", "1.246 - 2.476", "0.001"], ["MFAP4", "high vs. low", "1.494", "1.096 - 2.037", "0.011", "1.417", "1.039 - 1.933", "0.028"]], "row_count": 22, "column_count": 8, "numeric_cells": 97, "header_rows": 2, "locator": "section[19]/table-wrap[1]#T3A"}}, {"id": "asset:table:pmid:30719133:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5048cc7fb2cac3326bf45c3e6fab519008c6c02352a84624c9668981ac299533", "bytes": 1880, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[2]#T3B", "version": null, "note": "Univariate and multivariate Cox regression analysis for overall survival in GSE9891 and GSE32062.", "structure": {"pmcid": "PMC6360311", "section_index": 19, "section_title": "(untitled)", "row_count": 22, "column_count": 8}, "table": {"label": "Table 3B", "caption": "Univariate and multivariate Cox regression analysis for overall survival in GSE9891 and GSE32062.", "rows": [["Datasets and clinical factors", "", "Univariate analysis", "Multivariate analysis"], ["", "HR", "95%CI", "p value", "HR", "95%CI", "p value"], ["GSE9891", "", "", "", "", "", "", ""], ["Age", "≥60y vs <60y", "1.458", "1.001 - 2.122", "0.049", "1.729", "1.125 - 2.655", "0.012"], ["Tumor stage", "I", "1 (reference)", "", "", "1 (reference)", "", ""], ["", "II", "0.483", "0.044 - 5.347", "0.553", "0.705", "0.062 - 7.947", "0.777"], ["", "III", "3.672", "0.903 - 14.935", "0.069", "3.103", "0.740 - 13.020", "0.122"], ["", "IV", "5.739", "1.301 - 25.319", "0.021", "4.929", "1.035 - 23.483", "0.045"], ["Tumor grade", "G1", "1 (reference)", "", "", "1 (reference)", "", ""], ["", "G2", "3.070", "0.937 - 10.06", "0.064", "1.343", "0.387 - 4.663", "0.642"], ["", "G3", "3.181", "0.999 - 10.13", "0.0502", "1.534", "0.453 - 5.192", "0.491"], ["Surgery", "Suboptimal vs optimal", "1.662", "1.117 - 2.471", "0.012", "1.309", "0.850 - 2.014", "0.221"], ["AGGF1", "high vs. low", "1.662", "1.081 - 2.555", "0.021", "2.014", "1.240 - 3.270", "0.005"], ["MFAP4", "high vs. low", "1.98", "1.33 - 2.947", "0.001", "1.660", "1.065 - 2.586", "0.025"], ["GSE32062", "", "", "", "", "", "", ""], ["Tumor stage", "III", "1 (reference)", "", "", "1 (reference)", "", ""], ["", "IV", "1.466", "0.981 - 2.189", "0.062", "1.323", "0.881 - 1.986", "0.177"], ["Tumor grade", "G2", "1 (reference)", "", "", "1 (reference)", "", ""], ["", "G3", "0.978", "0.684 - 1.399", "0.904", "0.926", "0.645 - 1.328", "0.675"], ["Surgery", "Suboptimal vs optimal", "2.013", "1.363 - 2.972", "4.347e-04", "1.909", "1.291 - 2.822", "0.001"], ["AGGF1", "high vs. low", "1.678", "1.091 - 2.579", "0.018", "1.543", "1.001 - 2.376", "0.049"], ["MFAP4", "high vs. low", "1.622", "1.081 - 2.436", "0.020", "1.581", "1.053 - 2.374", "0.027"]], "row_count": 22, "column_count": 8, "numeric_cells": 97, "header_rows": 2, "locator": "section[19]/table-wrap[2]#T3B"}}], "gaps": ["asset:data:geo:GSE32062 not downloaded", "asset:data:geo:GSE32062 licence not read", "asset:data:geo:GSE51373 not downloaded", "asset:data:geo:GSE51373 licence not read", "asset:data:geo:GSE63885 not downloaded", "asset:data:geo:GSE63885 licence not read", "asset:data:geo:GSE9891 not downloaded", "asset:data:geo:GSE9891 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Univariate analysis with Cox proportional hazards regression model was used to evaluate the correlations of AGGF1 and MFAP4 expression statuses with RFS and OS, and multivariate analysis with Cox proportional hazards regression model was applied to test the independent predictive ability of these two gene signatures for RFS and OS after adjusting for various clinical characteristics."}}, {"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": "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": 0.7, "band": "medium", "quote": "log-rank"}}, {"id": "method-4", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}, {"id": "method-5", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-6", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "logistic regression"}}, {"id": "method-7", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "chi-square"}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE63885", "GSE51373", "GSE9891", "GSE32062"], "resolved_accessions": ["GSE63885", "GSE51373", "GSE9891", "GSE32062"], "statements": ["GSE63885 and GSE51373 were defined as the discovery sets to explore gene signatures with high efficiency to distinguish platinum-resistant and platinum-sensitive patients, and TCGA SOC dataset (hereinafter inferred as TCGA) was analyzed as the validation dataset."], "basis": "The paper names GSE63885, GSE51373, GSE9891, GSE32062 in National Center for Biotechnology Information Gene Expression Omnibus database (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:30719133", "data:geo:GSE32062", "asset:table:pmid:30719133:1", "asset:table:pmid:30719133:2", "asset:table:pmid:30719133:3", "asset:table:pmid:30719133:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE32062"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:47Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 32572, "completion_tokens": 3162, "cached_tokens": 656}}, "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:30719133", "type": "paper", "label": "pmid:30719133"}, {"id": "source:pmid:30719133", "type": "manuscript", "label": "PMID 30719133 full text"}, {"id": "data:geo:GSE32062", "type": "dataset", "label": "GEO GSE32062"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30719133", "type": "paper", "label": "pmid:30719133"}, {"id": "source:pmid:30719133", "type": "manuscript", "label": "PMID 30719133 full text"}, {"id": "data:geo:GSE32062", "type": "dataset", "label": "GEO GSE32062"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30719133", "type": "extraction", "used": ["source:pmid:30719133"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE32062", "type": "accession_resolution", "used": ["data:geo:GSE32062"], "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:30719133", "parent_hash": "sha256:cce6039912458b2e0c39430a14217d87ad16c8ca504cf801a19e827ac2bf17f7", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE32062 licence not read", "asset:data:geo:GSE32062 not downloaded", "asset:data:geo:GSE51373 licence not read", "asset:data:geo:GSE51373 not downloaded", "asset:data:geo:GSE63885 licence not read", "asset:data:geo:GSE63885 not downloaded", "asset:data:geo:GSE9891 licence not read", "asset:data:geo:GSE9891 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": 0.93, "evidence": ["tinum-based chemoresistance. Gene expression microarray analyses were performed to identify the gene"], "order_basis": "paper_text_order:435", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Univariate analysis with Cox proportional hazards regression model was used to evaluate the correlations of AGGF1 and MFAP4 expression statuses with RFS and OS, and multivariate analysis with Cox proportional hazards regression model was applied to test the independent predictive ability of these two gene signatures for RFS and OS after adjusting for various clinical characteristics."], "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":"2026-11-04T02:15:50+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}}}