{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37158948", "kind": "science-record", "revision": 4, "content_hash": "sha256:43170b2bbce822f54f20a017ea931c71f749cc0ff8dc2009a2df2ae411c0be62", "created_at": "2026-11-01T19:01:49Z", "updated_at": "2026-11-01T22:51:51Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and validation of miR-583 and mir-877-5p as biomarkers in patients with breast cancer: an integrated experimental and bioinformatics research.", "doi": "10.1186/s13104-023-06343-w", "pmid": "37158948", "authors": ["Zahra Foruzandeh", "Mohammad Reza Alivand", "Mehdi Ghiami-Rad", "Mohammad Zaefizadeh", "Saeid Ghorbian"], "journal": "BMC research notes", "year": 2023, "abstract": "OBJECTIVES: Breast cancer (BC) is one of the most common cancers with a high mortality rate in women worldwide. The advantages of early cancer diagnosis are apparent, and it is a critical factor in increasing the patient's life and survival. According to mounting evidence, microRNAs (miRNAs) may be crucial regulators of critical biological processes. miRNA dysregulation has been linked to the beginning and progression of various human malignancies, including BC, and can operate as tumor suppressors or oncomiRs. This study aimed to identify novel miRNA biomarkers in BC tissues and non-tumor adjacent tissues of patients with BC. Microarray datasets GSE15852 and GSE42568 for differentially expressed genes (DEGs) and GSE45666, GSE57897, and GSE40525 for differentially expressed miRNAs (DEMs) retrieved from the Gene Expression Omnibus (GEO) database were analyzed using \"R\" software. A protein-protein interaction (PPI) network was created to identify the hub genes. MirNet, miRTarBase, and MirPathDB databases were used to predict DEMs targeted genes. Functional enrichment analysis was used to demonstrate the topmost classifications of molecular pathways. The prognostic capability of selected DEMs was evaluated through a Kaplan-Meier plot. Moreover, the specificity and sensitivity of detected miRNAs to discriminate BC from adjacent controls were assessed by area under the curve (AUC) using the ROC curve analysis. In the last phase of this study, gene expression on 100 BC tissues and 100 healthy adjacent tissues were analyzed and calculated by using the Real-Time PCR method.\nRESULTS: This study declared that miR-583 and miR-877-5p were downregulated in tumor samples in comparison to adjacent non-tumor samples (|logFC|< 0 and P ≤ 0.05). Accordingly, ROC curve analysis demonstrated the biomarker potential of miR-877-5p (AUC = 0.63) and miR-583 (AUC = 0.69). Our results showed that has-miR-583 and has-miR-877-5p could be potential biomarkers in BC.", "claims": [{"id": "claim-method", "statement": "The “R” software and “LIMMA” package were employed to efficiently analyze the chosen datasets utilizing correction, quantile normalization, and log2 conversion.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37158948", "locator": "sections[4] \"Identification of DEMs and DEGs\" paragraph 2", "quote": "The “R” software and “LIMMA” package were employed to efficiently analyze the chosen datasets utilizing correction, quantile normalization, and log2 conversion."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37158948", "locator": "sections[29] \"notes\" paragraph 1", "quote": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "miR-583 and miR-877-5p were downregulated in breast cancer tumor samples relative to adjacent non-tumor samples and showed potential as breast cancer biomarkers.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37158948", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "This study declared that miR-583 and miR-877-5p were downregulated in tumor samples in comparison to adjacent non-tumor samples (|logFC|< 0 and P ≤ 0.05)."}, {"asset": "source:pmid:37158948", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Accordingly, ROC curve analysis demonstrated the biomarker potential of miR-877-5p (AUC = 0.63) and miR-583 (AUC = 0.69)."}, {"asset": "source:pmid:37158948", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Our results showed that has-miR-583 and has-miR-877-5p could be potential biomarkers in BC."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "miR-583 and miR-877-5p were downregulated in breast cancer tumor samples relative to adjacent non-tumor samples and showed potential as breast cancer biomarkers.", "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:37158948"], "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:GSE15852"], "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:GSE15852"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37158948", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13104-023-06343-w", "sha256": "sha256:c9ded1bc44e04adfde87d672c454d53467e4c928fdcbcde39f1fb9aedcd732d3", "bytes": 25906, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13104-023-06343-w", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10169388", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15852", "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=GSE15852", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15852", "version": null, "note": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM398074", "GSM398075", "GSM398076", "GSM398077", "GSM398078", "GSM398079", "GSM398080", "GSM398081", "GSM398082", "GSM398083", "GSM398084", "GSM398085", "GSM398086", "GSM398087", "GSM398088", "GSM398089", "GSM398090", "GSM398091", "GSM398092", "GSM398093", "GSM398094", "GSM398095", "GSM398096", "GSM398097", "GSM398098", "GSM398099", "GSM398100", "GSM398101", "GSM398102", "GSM398103", "GSM398104", "GSM398105", "GSM398106", "GSM398107", "GSM398108", "GSM398109", "GSM398110", "GSM398111", "GSM398112", "GSM398113", "GSM398114", "GSM398115", "GSM398116", "GSM398117", "GSM398118", "GSM398119", "GSM398120", "GSM398121", "GSM398122", "GSM398123", "GSM398124", "GSM398125", "GSM398126", "GSM398127", "GSM398128", "GSM398129", "GSM398130", "GSM398131", "GSM398132", "GSM398133", "GSM398134", "GSM398135", "GSM398136", "GSM398137", "GSM398138", "GSM398139", "GSM398140", "GSM398141", "GSM398142", "GSM398143", "GSM398144", "GSM398145", "GSM398146", "GSM398147", "GSM398148", "GSM398149", "GSM398150", "GSM398151", "GSM398152", "GSM398153", "GSM398154", "GSM398155", "GSM398156", "GSM398157", "GSM398158", "GSM398159"], "sample_count": 86, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from human breast tumors and their paired normal tissues", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE40525", "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=GSE40525", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40525", "version": null, "note": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM995552", "GSM995553", "GSM995554", "GSM995555", "GSM995556", "GSM995557", "GSM995558", "GSM995559", "GSM995560", "GSM995561", "GSM995562", "GSM995563", "GSM995564", "GSM995565", "GSM995566", "GSM995567", "GSM995568", "GSM995569", "GSM995570", "GSM995571", "GSM995572", "GSM995573", "GSM995574", "GSM995575", "GSM995576", "GSM995577", "GSM995578", "GSM995579", "GSM995580", "GSM995581", "GSM995582", "GSM995583", "GSM995584", "GSM995585", "GSM995586", "GSM995587", "GSM995588", "GSM995589", "GSM995590", "GSM995591", "GSM995592", "GSM995593", "GSM995594", "GSM995595", "GSM995596", "GSM995597", "GSM995598", "GSM995599", "GSM995600", "GSM995601", "GSM995602", "GSM995603", "GSM995604", "GSM995605", "GSM995606", "GSM995607", "GSM995608", "GSM995609", "GSM995610", "GSM995611", "GSM995612", "GSM995613", "GSM995614", "GSM995615", "GSM995616", "GSM995617", "GSM995618", "GSM995619", "GSM995620", "GSM995621", "GSM995622", "GSM995623", "GSM995624", "GSM995625", "GSM995626", "GSM995627", "GSM995628", "GSM995629", "GSM995630", "GSM995631", "GSM995632", "GSM995633", "GSM995634", "GSM995635", "GSM995636", "GSM995637", "GSM995638", "GSM995639", "GSM995640", "GSM995641", "GSM995642", "GSM995643", "GSM995644", "GSM995645", "GSM995646", "GSM995647", "GSM995648", "GSM995649", "GSM995650", "GSM995651", "GSM995652", "GSM995653", "GSM995654", "GSM995655", "GSM995656", "GSM995657", "GSM995658", "GSM995659", "GSM995660", "GSM995661", "GSM995662", "GSM995663", "GSM995664", "GSM995665", "GSM995666", "GSM995667", "GSM995668", "GSM995669", "GSM995670", "GSM995671"], "sample_count": 120, "group_sizes": null, "group_sizes_basis": null, "platform": "8227", "taxon": "Homo sapiens", "title": "miR-10b*, a master inhibitor of the cell cycle, is downregulated in human breast tumors", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE42568", "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=GSE42568", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42568", "version": null, "note": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1045191", "GSM1045192", "GSM1045193", "GSM1045194", "GSM1045195", "GSM1045196", "GSM1045197", "GSM1045198", "GSM1045199", "GSM1045200", "GSM1045201", "GSM1045202", "GSM1045203", "GSM1045204", "GSM1045205", "GSM1045206", "GSM1045207", "GSM1045208", "GSM1045209", "GSM1045210", "GSM1045211", "GSM1045212", "GSM1045213", "GSM1045214", "GSM1045215", "GSM1045216", "GSM1045217", "GSM1045218", "GSM1045219", "GSM1045220", "GSM1045221", "GSM1045222", "GSM1045223", "GSM1045224", "GSM1045225", "GSM1045226", "GSM1045227", "GSM1045228", "GSM1045229", "GSM1045230", "GSM1045231", "GSM1045232", "GSM1045233", "GSM1045234", "GSM1045235", "GSM1045236", "GSM1045237", "GSM1045238", "GSM1045239", "GSM1045240", "GSM1045241", "GSM1045242", "GSM1045243", "GSM1045244", "GSM1045245", "GSM1045246", "GSM1045247", "GSM1045248", "GSM1045249", "GSM1045250", "GSM1045251", "GSM1045252", "GSM1045253", "GSM1045254", "GSM1045255", "GSM1045256", "GSM1045257", "GSM1045258", "GSM1045259", "GSM1045260", "GSM1045261", "GSM1045262", "GSM1045263", "GSM1045264", "GSM1045265", "GSM1045266", "GSM1045267", "GSM1045268", "GSM1045269", "GSM1045270", "GSM1045271", "GSM1045272", "GSM1045273", "GSM1045274", "GSM1045275", "GSM1045276", "GSM1045277", "GSM1045278", "GSM1045279", "GSM1045280", "GSM1045281", "GSM1045282", "GSM1045283", "GSM1045284", "GSM1045285", "GSM1045286", "GSM1045287", "GSM1045288", "GSM1045289", "GSM1045290", "GSM1045291", "GSM1045292", "GSM1045293", "GSM1045294", "GSM1045295", "GSM1045296", "GSM1045297", "GSM1045298", "GSM1045299", "GSM1045300", "GSM1045301", "GSM1045302", "GSM1045303", "GSM1045304", "GSM1045305", "GSM1045306", "GSM1045307", "GSM1045308", "GSM1045309", "GSM1045310", "GSM1045311"], "sample_count": 121, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Breast Cancer Gene Expression Analysis", "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:GSE45666", "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=GSE45666", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45666", "version": null, "note": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1111512", "GSM1111513", "GSM1111514", "GSM1111515", "GSM1111516", "GSM1111517", "GSM1111518", "GSM1111519", "GSM1111520", "GSM1111521", "GSM1111522", "GSM1111523", "GSM1111524", "GSM1111525", "GSM1111526", "GSM1111527", "GSM1111528", "GSM1111529", "GSM1111530", "GSM1111531", "GSM1111532", "GSM1111533", "GSM1111534", "GSM1111535", "GSM1111536", "GSM1111537", "GSM1111538", "GSM1111539", "GSM1111540", "GSM1111541", "GSM1111542", "GSM1111543", "GSM1111544", "GSM1111545", "GSM1111546", "GSM1111547", "GSM1111548", "GSM1111549", "GSM1111550", "GSM1111551", "GSM1111552", "GSM1111553", "GSM1111554", "GSM1111555", "GSM1111556", "GSM1111557", "GSM1111558", "GSM1111559", "GSM1111560", "GSM1111561", "GSM1111562", "GSM1111563", "GSM1111564", "GSM1111565", "GSM1111566", "GSM1111567", "GSM1111568", "GSM1111569", "GSM1111570", "GSM1111571", "GSM1111572", "GSM1111573", "GSM1111574", "GSM1111575", "GSM1111576", "GSM1111577", "GSM1111578", "GSM1111579", "GSM1111580", "GSM1111581", "GSM1111582", "GSM1111583", "GSM1111584", "GSM1111585", "GSM1111586", "GSM1111587", "GSM1111588", "GSM1111589", "GSM1111590", "GSM1111591", "GSM1111592", "GSM1111593", "GSM1111594", "GSM1111595", "GSM1111596", "GSM1111597", "GSM1111598", "GSM1111599", "GSM1111600", "GSM1111601", "GSM1111602", "GSM1111603", "GSM1111604", "GSM1111605", "GSM1111606", "GSM1111607", "GSM1111608", "GSM1111609", "GSM1111610", "GSM1111611", "GSM1111612", "GSM1111613", "GSM1111614", "GSM1111615", "GSM1111616", "GSM1111617", "GSM1111618", "GSM1111619", "GSM1111620", "GSM1111621", "GSM1111622", "GSM1111623", "GSM1111624", "GSM1111625", "GSM1111626", "GSM1111627"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "14767", "taxon": "Homo sapiens", "title": "MicroRNA expression profile of breast cancer patients with adjacent normal control group.", "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:GSE57897", "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=GSE57897", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57897", "version": null, "note": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1396751", "GSM1396752", "GSM1396753", "GSM1396754", "GSM1396755", "GSM1396756", "GSM1396757", "GSM1396758", "GSM1396759", "GSM1396760", "GSM1396761", "GSM1396762", "GSM1396763", "GSM1396764", "GSM1396765", "GSM1396766", "GSM1396767", "GSM1396768", "GSM1396769", "GSM1396770", "GSM1396771", "GSM1396772", "GSM1396773", "GSM1396774", "GSM1396775", "GSM1396776", "GSM1396777", "GSM1396778", "GSM1396779", "GSM1396780", "GSM1396781", "GSM1396782", "GSM1396783", "GSM1396784", "GSM1396785", "GSM1396786", "GSM1396787", "GSM1396788", "GSM1396789", "GSM1396790", "GSM1396791", "GSM1396792", "GSM1396793", "GSM1396794", "GSM1396795", "GSM1396796", "GSM1396797", "GSM1396798", "GSM1396799", "GSM1396800", "GSM1396801", "GSM1396802", "GSM1396803", "GSM1396804", "GSM1396805", "GSM1396806", "GSM1396807", "GSM1396808", "GSM1396809", "GSM1396810", "GSM1396811", "GSM1396812", "GSM1396813", "GSM1396814", "GSM1396815", "GSM1396816", "GSM1396817", "GSM1396818", "GSM1396819", "GSM1396820", "GSM1396821", "GSM1396822", "GSM1396823", "GSM1396824", "GSM1396825", "GSM1396826", "GSM1396827", "GSM1396828", "GSM1396829", "GSM1396830", "GSM1396831", "GSM1396832", "GSM1396833", "GSM1396834", "GSM1396835", "GSM1396836", "GSM1396837", "GSM1396838", "GSM1396839", "GSM1396840", "GSM1396841", "GSM1396842", "GSM1396843", "GSM1396844", "GSM1396845", "GSM1396846", "GSM1396847", "GSM1396848", "GSM1396849", "GSM1396850", "GSM1396851", "GSM1396852", "GSM1396853", "GSM1396854", "GSM1396855", "GSM1396856", "GSM1396857", "GSM1396858", "GSM1396859", "GSM1396860", "GSM1396861", "GSM1396862", "GSM1396863", "GSM1396864", "GSM1396865", "GSM1396866", "GSM1396867", "GSM1396868", "GSM1396869", "GSM1396870", "GSM1396871", "GSM1396872", "GSM1396873", "GSM1396874", "GSM1396875", "GSM1396876", "GSM1396877", "GSM1396878", "GSM1396879", "GSM1396880", "GSM1396881", "GSM1396882", "GSM1396883", "GSM1396884", "GSM1396885", "GSM1396886", "GSM1396887", "GSM1396888", "GSM1396889", "GSM1396890", "GSM1396891", "GSM1396892", "GSM1396893", "GSM1396894", "GSM1396895", "GSM1396896", "GSM1396897", "GSM1396898", "GSM1396899", "GSM1396900", "GSM1396901", "GSM1396902", "GSM1396903", "GSM1396904", "GSM1396905", "GSM1396906", "GSM1396907", "GSM1396908", "GSM1396909", "GSM1396910", "GSM1396911", "GSM1396912", "GSM1396913", "GSM1396914", "GSM1396915", "GSM1396916", "GSM1396917", "GSM1396918", "GSM1396919", "GSM1396920", "GSM1396921", "GSM1396922", "GSM1396923", "GSM1396924", "GSM1396925", "GSM1396926", "GSM1396927", "GSM1396928", "GSM1396929", "GSM1396930", "GSM1396931", "GSM1396932", "GSM1396933", "GSM1396934", "GSM1396935", "GSM1396936", "GSM1396937", "GSM1396938", "GSM1396939", "GSM1396940", "GSM1396941", "GSM1396942", "GSM1396943", "GSM1396944", "GSM1396945", "GSM1396946", "GSM1396947", "GSM1396948", "GSM1396949", "GSM1396950", "GSM1396951", "GSM1396952", "GSM1396953", "GSM1396954", "GSM1396955", "GSM1396956", "GSM1396957", "GSM1396958", "GSM1396959", "GSM1396960", "GSM1396961", "GSM1396962", "GSM1396963", "GSM1396964", "GSM1396965", "GSM1396966", "GSM1396967", "GSM1396968", "GSM1396969", "GSM1396970", "GSM1396971", "GSM1396972", "GSM1396973", "GSM1396974", "GSM1396975", "GSM1396976", "GSM1396977", "GSM1396978", "GSM1396979", "GSM1396980", "GSM1396981", "GSM1396982", "GSM1396983", "GSM1396984", "GSM1396985", "GSM1396986", "GSM1396987", "GSM1396988", "GSM1396989", "GSM1396990", "GSM1396991", "GSM1396992", "GSM1396993", "GSM1396994", "GSM1396995", "GSM1396996", "GSM1396997", "GSM1396998", "GSM1396999", "GSM1397000", "GSM1397001", "GSM1397002", "GSM1397003", "GSM1397004", "GSM1397005", "GSM1397006", "GSM1397007", "GSM1397008", "GSM1397009", "GSM1397010", "GSM1397011", "GSM1397012", "GSM1397013", "GSM1397014", "GSM1397015", "GSM1397016", "GSM1397017", "GSM1397018", "GSM1397019", "GSM1397020", "GSM1397021", "GSM1397022", "GSM1397023", "GSM1397024", "GSM1397025", "GSM1397026", "GSM1397027", "GSM1397028", "GSM1397029", "GSM1397030", "GSM1397031", "GSM1397032", "GSM1397033", "GSM1397034", "GSM1397035", "GSM1397036", "GSM1397037", "GSM1397038", "GSM1397039", "GSM1397040", "GSM1397041", "GSM1397042", "GSM1397043", "GSM1397044", "GSM1397045", "GSM1397046", "GSM1397047", "GSM1397048", "GSM1397049", "GSM1397050", "GSM1397051", "GSM1397052", "GSM1397053", "GSM1397054", "GSM1397055", "GSM1397056", "GSM1397057", "GSM1397058", "GSM1397059", "GSM1397060", "GSM1397061", "GSM1397062", "GSM1397063", "GSM1397064", "GSM1397065", "GSM1397066", "GSM1397067", "GSM1397068", "GSM1397069", "GSM1397070", "GSM1397071", "GSM1397072", "GSM1397073", "GSM1397074", "GSM1397075", "GSM1397076", "GSM1397077", "GSM1397078", "GSM1397079", "GSM1397080", "GSM1397081", "GSM1397082", "GSM1397083", "GSM1397084", "GSM1397085", "GSM1397086", "GSM1397087", "GSM1397088", "GSM1397089", "GSM1397090", "GSM1397091", "GSM1397092", "GSM1397093", "GSM1397094", "GSM1397095", "GSM1397096", "GSM1397097", "GSM1397098", "GSM1397099", "GSM1397100", "GSM1397101", "GSM1397102", "GSM1397103", "GSM1397104", "GSM1397105", "GSM1397106", "GSM1397107", "GSM1397108", "GSM1397109", "GSM1397110", "GSM1397111", "GSM1397112", "GSM1397113", "GSM1397114", "GSM1397115", "GSM1397116", "GSM1397117", "GSM1397118", "GSM1397119", "GSM1397120", "GSM1397121", "GSM1397122", "GSM1397123", "GSM1397124", "GSM1397125", "GSM1397126", "GSM1397127", "GSM1397128", "GSM1397129", "GSM1397130", "GSM1397131", "GSM1397132", "GSM1397133", "GSM1397134", "GSM1397135", "GSM1397136", "GSM1397137", "GSM1397138", "GSM1397139", "GSM1397140", "GSM1397141", "GSM1397142", "GSM1397143", "GSM1397144", "GSM1397145", "GSM1397146", "GSM1397147", "GSM1397148", "GSM1397149", "GSM1397150", "GSM1397151", "GSM1397152", "GSM1397153", "GSM1397154", "GSM1397155", "GSM1397156", "GSM1397157", "GSM1397158", "GSM1397159", "GSM1397160", "GSM1397161", "GSM1397162", "GSM1397163", "GSM1397164", "GSM1397165", "GSM1397166", "GSM1397167", "GSM1397168", "GSM1397169", "GSM1397170", "GSM1397171", "GSM1397172", "GSM1397173", "GSM1397174", "GSM1397175", "GSM1397176", "GSM1397177", "GSM1397178", "GSM1397179", "GSM1397180", "GSM1397181", "GSM1397182", "GSM1397183", "GSM1397184", "GSM1397185", "GSM1397186", "GSM1397187", "GSM1397188", "GSM1397189", "GSM1397190", "GSM1397191", "GSM1397192", "GSM1397193", "GSM1397194", "GSM1397195", "GSM1397196", "GSM1397197", "GSM1397198", "GSM1397199", "GSM1397200", "GSM1397201", "GSM1397202", "GSM1397203"], "sample_count": 453, "group_sizes": null, "group_sizes_basis": null, "platform": "18722", "taxon": "Homo sapiens", "title": "The prognostic and predictive value of a five-microRNA-based classifier in breast cancer", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE15852 not downloaded", "asset:data:geo:GSE15852 licence not read", "asset:data:geo:GSE40525 not downloaded", "asset:data:geo:GSE40525 licence not read", "asset:data:geo:GSE42568 not downloaded", "asset:data:geo:GSE42568 licence not read", "asset:data:geo:GSE45666 not downloaded", "asset:data:geo:GSE45666 licence not read", "asset:data:geo:GSE57897 not downloaded", "asset:data:geo:GSE57897 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The “R” software and “LIMMA” package were employed to efficiently analyze the chosen datasets utilizing correction, quantile normalization, and log2 conversion."}}, {"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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-4", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE15852", "GSE42568", "GSE45666", "GSE57897", "GSE40525"], "resolved_accessions": ["GSE15852", "GSE42568", "GSE45666", "GSE57897", "GSE40525"], "statements": ["All datasets supporting the conclusions of this article are available in NCBI/bioproject: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA116827, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA182286, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA195576, https://www.ncbi.nlm.nih.gov/bioproject/PRJNA248377, and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA174219. Further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE15852, GSE42568, GSE45666, GSE57897, GSE40525 in National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:37158948", "data:geo:GSE15852"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15852"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:39:02Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8672, "completion_tokens": 1975, "cached_tokens": 128}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:37158948", "type": "paper", "label": "pmid:37158948"}, {"id": "source:pmid:37158948", "type": "manuscript", "label": "PMID 37158948 full text"}, {"id": "data:geo:GSE15852", "type": "dataset", "label": "GEO GSE15852"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37158948", "type": "paper", "label": "pmid:37158948"}, {"id": "source:pmid:37158948", "type": "manuscript", "label": "PMID 37158948 full text"}, {"id": "data:geo:GSE15852", "type": "dataset", "label": "GEO GSE15852"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37158948", "type": "extraction", "used": ["source:pmid:37158948"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15852", "type": "accession_resolution", "used": ["data:geo:GSE15852"], "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:37158948", "parent_hash": "sha256:4232b90d08d32ea8dcd37725101c2b0c1fe422d60d16b7cb33934ac5b0a7d83b", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE15852 licence not read", "asset:data:geo:GSE15852 not downloaded", "asset:data:geo:GSE40525 licence not read", "asset:data:geo:GSE40525 not downloaded", "asset:data:geo:GSE42568 licence not read", "asset:data:geo:GSE42568 not downloaded", "asset:data:geo:GSE45666 licence not read", "asset:data:geo:GSE45666 not downloaded", "asset:data:geo:GSE57897 licence not read", "asset:data:geo:GSE57897 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": ["-tumor adjacent tissues of patients with BC. Microarray datasets GSE15852 and GSE42568 for different", "on DEGs Each of the target genes analyzed by microarray datasets has their pathways enriched. KEGG p"], "order_basis": "paper_text_order:748", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["es were analyzed and calculated by using the Real-Time PCR method. RESULTS: This study declared that mi"], "order_basis": "paper_text_order:1684", "id": "assay:2"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The “R” software and “LIMMA” package were employed to efficiently analyze the chosen datasets utilizing correction, quantile normalization, and log2 conversion."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T02:36:49+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}}}