{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B4YHFIFOXUMAA3QW4GTIXQ5VFX","short_pith_number":"pith:B4YHFIFO","schema_version":"1.0","canonical_sha256":"0f3072a0aebd18006e16e1a68bc3b52de75d04289d10ab9f96f2d2fd9b83866d","source":{"kind":"arxiv","id":"2606.05927","version":1},"attestation_state":"computed","paper":{"title":"Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Zhou, Bin Liu, Grigorios Tsoumakas, Haoyu Peng, Jin Wang, Jun Wu, QiaoSong Chen","submitted_at":"2026-06-04T09:30:21Z","abstract_excerpt":"The complex imbalanced label distribution poses a crucial challenge to multi-label classification, as most classifiers are biased towards the majority class and high-frequent labels. Oversampling is an efficient and flexible solution that augments instances to provide a more balanced training dataset for multi-label classifiers. Most existing oversampling methods create synthetic instances in a heuristic way that essentially relies on neighborhood information retrieved using Euclidean distance within the entire feature space. However, they fail to consider the varying semantic relevance of fea"},"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":"2606.05927","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T09:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"b37ae3a82cf6dda23750c81909294b92bbb388916ab402c30f33108ef2054d0f","abstract_canon_sha256":"7825a621c0893420ef3cd936e0a559f82b22e42f5a962c41b07ffeddb941a91b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:27.955128Z","signature_b64":"uZS9ZOuMNN7VKObRWbaN9OdAvU44yjp1IsoimewbBsK+25C7i9U0aqHr9WvKPgb//vNcuxjEtRZwG7IoGVAPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f3072a0aebd18006e16e1a68bc3b52de75d04289d10ab9f96f2d2fd9b83866d","last_reissued_at":"2026-06-05T01:15:27.954727Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:27.954727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Zhou, Bin Liu, Grigorios Tsoumakas, Haoyu Peng, Jin Wang, Jun Wu, QiaoSong Chen","submitted_at":"2026-06-04T09:30:21Z","abstract_excerpt":"The complex imbalanced label distribution poses a crucial challenge to multi-label classification, as most classifiers are biased towards the majority class and high-frequent labels. Oversampling is an efficient and flexible solution that augments instances to provide a more balanced training dataset for multi-label classifiers. Most existing oversampling methods create synthetic instances in a heuristic way that essentially relies on neighborhood information retrieved using Euclidean distance within the entire feature space. However, they fail to consider the varying semantic relevance of fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05927","kind":"arxiv","version":1},"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/2606.05927/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":"2606.05927","created_at":"2026-06-05T01:15:27.954790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05927v1","created_at":"2026-06-05T01:15:27.954790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05927","created_at":"2026-06-05T01:15:27.954790+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4YHFIFOXUMA","created_at":"2026-06-05T01:15:27.954790+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4YHFIFOXUMAA3QW","created_at":"2026-06-05T01:15:27.954790+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4YHFIFO","created_at":"2026-06-05T01:15:27.954790+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/B4YHFIFOXUMAA3QW4GTIXQ5VFX","json":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX.json","graph_json":"https://pith.science/api/pith-number/B4YHFIFOXUMAA3QW4GTIXQ5VFX/graph.json","events_json":"https://pith.science/api/pith-number/B4YHFIFOXUMAA3QW4GTIXQ5VFX/events.json","paper":"https://pith.science/paper/B4YHFIFO"},"agent_actions":{"view_html":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX","download_json":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX.json","view_paper":"https://pith.science/paper/B4YHFIFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05927&json=true","fetch_graph":"https://pith.science/api/pith-number/B4YHFIFOXUMAA3QW4GTIXQ5VFX/graph.json","fetch_events":"https://pith.science/api/pith-number/B4YHFIFOXUMAA3QW4GTIXQ5VFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX/action/storage_attestation","attest_author":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX/action/author_attestation","sign_citation":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX/action/citation_signature","submit_replication":"https://pith.science/pith/B4YHFIFOXUMAA3QW4GTIXQ5VFX/action/replication_record"}},"created_at":"2026-06-05T01:15:27.954790+00:00","updated_at":"2026-06-05T01:15:27.954790+00:00"}