{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FLJTD2SLIRPDDJCKKAVQNP53IQ","short_pith_number":"pith:FLJTD2SL","schema_version":"1.0","canonical_sha256":"2ad331ea4b445e31a44a502b06bfbb4411e3ca98555f73fc7ac42dd973d638c0","source":{"kind":"arxiv","id":"2506.05027","version":1},"attestation_state":"computed","paper":{"title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kuang He, Min-Ling Zhang, Tong Wei, Wei Tang","submitted_at":"2025-06-05T13:37:33Z","abstract_excerpt":"Partial label learning (PLL) seeks to train generalizable classifiers from datasets with inexact supervision, a common challenge in real-world applications. Existing studies have developed numerous approaches to progressively refine and recover ground-truth labels by training convolutional neural networks. However, limited attention has been given to foundation models that offer transferrable representations. In this work, we empirically conduct comprehensive evaluations of 11 foundation models across 13 PLL approaches on 8 benchmark datasets under 3 PLL scenarios. We further propose PartialCL"},"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":"2506.05027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T13:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"988522bec6e4c5e56fbe51d651058439511faf4228739b49cb68acef992614be","abstract_canon_sha256":"41b93317c9ee69fc9271891cf22886c8416588b44d5a480c2ce35ed307080d59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:41.201157Z","signature_b64":"/4uRg3DGYzsKlUUuEk8MJ/g3+8comiWvK4MYD3gp8aT2XQ/iCArW6JII4+KRselqR7eLX8+t/brILQNXtGryCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad331ea4b445e31a44a502b06bfbb4411e3ca98555f73fc7ac42dd973d638c0","last_reissued_at":"2026-07-05T11:16:41.200622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:41.200622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kuang He, Min-Ling Zhang, Tong Wei, Wei Tang","submitted_at":"2025-06-05T13:37:33Z","abstract_excerpt":"Partial label learning (PLL) seeks to train generalizable classifiers from datasets with inexact supervision, a common challenge in real-world applications. Existing studies have developed numerous approaches to progressively refine and recover ground-truth labels by training convolutional neural networks. However, limited attention has been given to foundation models that offer transferrable representations. In this work, we empirically conduct comprehensive evaluations of 11 foundation models across 13 PLL approaches on 8 benchmark datasets under 3 PLL scenarios. We further propose PartialCL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05027","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/2506.05027/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":"2506.05027","created_at":"2026-07-05T11:16:41.200684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05027v1","created_at":"2026-07-05T11:16:41.200684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05027","created_at":"2026-07-05T11:16:41.200684+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLJTD2SLIRPD","created_at":"2026-07-05T11:16:41.200684+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLJTD2SLIRPDDJCK","created_at":"2026-07-05T11:16:41.200684+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLJTD2SL","created_at":"2026-07-05T11:16:41.200684+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/FLJTD2SLIRPDDJCKKAVQNP53IQ","json":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ.json","graph_json":"https://pith.science/api/pith-number/FLJTD2SLIRPDDJCKKAVQNP53IQ/graph.json","events_json":"https://pith.science/api/pith-number/FLJTD2SLIRPDDJCKKAVQNP53IQ/events.json","paper":"https://pith.science/paper/FLJTD2SL"},"agent_actions":{"view_html":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ","download_json":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ.json","view_paper":"https://pith.science/paper/FLJTD2SL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05027&json=true","fetch_graph":"https://pith.science/api/pith-number/FLJTD2SLIRPDDJCKKAVQNP53IQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FLJTD2SLIRPDDJCKKAVQNP53IQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ/action/storage_attestation","attest_author":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ/action/author_attestation","sign_citation":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ/action/citation_signature","submit_replication":"https://pith.science/pith/FLJTD2SLIRPDDJCKKAVQNP53IQ/action/replication_record"}},"created_at":"2026-07-05T11:16:41.200684+00:00","updated_at":"2026-07-05T11:16:41.200684+00:00"}