{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:67TCJBPCDDIV3XMNNIBG2G4HLI","short_pith_number":"pith:67TCJBPC","schema_version":"1.0","canonical_sha256":"f7e62485e218d15ddd8d6a026d1b875a16e5f775aeb80e58383b2af5ac3aa0e9","source":{"kind":"arxiv","id":"2302.05080","version":1},"attestation_state":"computed","paper":{"title":"Long-Tailed Partial Label Learning via Dynamic Rebalancing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Feng Hong, Jiangchao Yao, Yanfeng Wang, Ya Zhang, Zhihan Zhou","submitted_at":"2023-02-10T06:43:53Z","abstract_excerpt":"Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The straightforward combination of LT and PLL, i.e., LT-PLL, suffers from a fundamental dilemma: LT methods build upon a given class distribution that is unavailable in PLL, and the performance of PLL is severely influenced in long-tailed context. We show that even with the auxiliary of an oracle class prior, the state-of-the-art methods underperform due to an adverse fact that the constant rebalancing in LT is harsh to t"},"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":"2302.05080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T06:43:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4c7b1f5fc2c7da20b72c9e1f6adccf5291b938f40fe6df1602fb74bc321f3f9c","abstract_canon_sha256":"07b6cf6af7f06346306c3e9f71e8e8e3b53d4d08f83d7cc7755363c95780125e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:35.170107Z","signature_b64":"NB6sayee7BCjwlWZQCRJD7dMAHd3gsWboGHTD2JcwcAPtFAaUtFv2nHW4s8PjKIXSrQrX23MEOW+F4ybtYi3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7e62485e218d15ddd8d6a026d1b875a16e5f775aeb80e58383b2af5ac3aa0e9","last_reissued_at":"2026-07-05T05:40:35.169718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:35.169718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Tailed Partial Label Learning via Dynamic Rebalancing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Feng Hong, Jiangchao Yao, Yanfeng Wang, Ya Zhang, Zhihan Zhou","submitted_at":"2023-02-10T06:43:53Z","abstract_excerpt":"Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The straightforward combination of LT and PLL, i.e., LT-PLL, suffers from a fundamental dilemma: LT methods build upon a given class distribution that is unavailable in PLL, and the performance of PLL is severely influenced in long-tailed context. We show that even with the auxiliary of an oracle class prior, the state-of-the-art methods underperform due to an adverse fact that the constant rebalancing in LT is harsh to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05080","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/2302.05080/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":"2302.05080","created_at":"2026-07-05T05:40:35.169773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05080v1","created_at":"2026-07-05T05:40:35.169773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05080","created_at":"2026-07-05T05:40:35.169773+00:00"},{"alias_kind":"pith_short_12","alias_value":"67TCJBPCDDIV","created_at":"2026-07-05T05:40:35.169773+00:00"},{"alias_kind":"pith_short_16","alias_value":"67TCJBPCDDIV3XMN","created_at":"2026-07-05T05:40:35.169773+00:00"},{"alias_kind":"pith_short_8","alias_value":"67TCJBPC","created_at":"2026-07-05T05:40:35.169773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05027","citing_title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI","json":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI.json","graph_json":"https://pith.science/api/pith-number/67TCJBPCDDIV3XMNNIBG2G4HLI/graph.json","events_json":"https://pith.science/api/pith-number/67TCJBPCDDIV3XMNNIBG2G4HLI/events.json","paper":"https://pith.science/paper/67TCJBPC"},"agent_actions":{"view_html":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI","download_json":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI.json","view_paper":"https://pith.science/paper/67TCJBPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05080&json=true","fetch_graph":"https://pith.science/api/pith-number/67TCJBPCDDIV3XMNNIBG2G4HLI/graph.json","fetch_events":"https://pith.science/api/pith-number/67TCJBPCDDIV3XMNNIBG2G4HLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI/action/storage_attestation","attest_author":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI/action/author_attestation","sign_citation":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI/action/citation_signature","submit_replication":"https://pith.science/pith/67TCJBPCDDIV3XMNNIBG2G4HLI/action/replication_record"}},"created_at":"2026-07-05T05:40:35.169773+00:00","updated_at":"2026-07-05T05:40:35.169773+00:00"}