{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KOV4OJOT4CA2YKBWAOMVA5JDWS","short_pith_number":"pith:KOV4OJOT","schema_version":"1.0","canonical_sha256":"53abc725d3e081ac28360399507523b4b44212cdec62ff9d808d4125fe2257ec","source":{"kind":"arxiv","id":"2512.08371","version":4},"attestation_state":"computed","paper":{"title":"A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew W. Brown, Colby J. Vorland, Donna L. Maney, Simon Chung","submitted_at":"2025-12-09T08:54:20Z","abstract_excerpt":"Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2512.08371","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-09T08:54:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8dee88ee96f6bdd0da98c961cc3b0372c34253c26ddf65426faadde117886775","abstract_canon_sha256":"01180db3fef93043d2331d7b2f089cecea30477fdb474cf0be2fb9dbf1910e48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:53.529252Z","signature_b64":"BCeDp/B5hz59Rhj789kuum7l1wjt8Hf8AcRR1PMAHagHRDyVJIAEXGBvYAM7MgriNt5Zg/2Ds5YgXV1r2+nCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53abc725d3e081ac28360399507523b4b44212cdec62ff9d808d4125fe2257ec","last_reissued_at":"2026-05-27T01:04:53.528534Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:53.528534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew W. Brown, Colby J. Vorland, Donna L. Maney, Simon Chung","submitted_at":"2025-12-09T08:54:20Z","abstract_excerpt":"Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.08371","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.08371/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.08371","created_at":"2026-05-27T01:04:53.528612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.08371v4","created_at":"2026-05-27T01:04:53.528612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.08371","created_at":"2026-05-27T01:04:53.528612+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOV4OJOT4CA2","created_at":"2026-05-27T01:04:53.528612+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOV4OJOT4CA2YKBW","created_at":"2026-05-27T01:04:53.528612+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOV4OJOT","created_at":"2026-05-27T01:04:53.528612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS","json":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS.json","graph_json":"https://pith.science/api/pith-number/KOV4OJOT4CA2YKBWAOMVA5JDWS/graph.json","events_json":"https://pith.science/api/pith-number/KOV4OJOT4CA2YKBWAOMVA5JDWS/events.json","paper":"https://pith.science/paper/KOV4OJOT"},"agent_actions":{"view_html":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS","download_json":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS.json","view_paper":"https://pith.science/paper/KOV4OJOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.08371&json=true","fetch_graph":"https://pith.science/api/pith-number/KOV4OJOT4CA2YKBWAOMVA5JDWS/graph.json","fetch_events":"https://pith.science/api/pith-number/KOV4OJOT4CA2YKBWAOMVA5JDWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS/action/storage_attestation","attest_author":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS/action/author_attestation","sign_citation":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS/action/citation_signature","submit_replication":"https://pith.science/pith/KOV4OJOT4CA2YKBWAOMVA5JDWS/action/replication_record"}},"created_at":"2026-05-27T01:04:53.528612+00:00","updated_at":"2026-05-27T01:04:53.528612+00:00"}