{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AFUEXSQAVYKALIBQBKYYRLUKVI","short_pith_number":"pith:AFUEXSQA","schema_version":"1.0","canonical_sha256":"01684bca00ae1405a0300ab188ae8aaa1dc4cb43394d1020506c0b6e687cc256","source":{"kind":"arxiv","id":"2501.15955","version":3},"attestation_state":"computed","paper":{"title":"Rethinking the Bias of Foundation Model under Long-tailed Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing Su, Bin Qin, Hao Chen, Jiahao Chen, Jiangmeng Li","submitted_at":"2025-01-27T11:00:19Z","abstract_excerpt":"Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these models, overlooking the inherent biases introduced by the imbalanced training data they rely on. In this paper, we examine how such imbalances from pre-training affect long-tailed downstream tasks. Specifically, we find the imbalance biases inherited in foundation models on downstream task as paramete"},"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":"2501.15955","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T11:00:19Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2f84a98095540271a6a3d88cd5e458dded1d182326f9139c6d7cf5a021177258","abstract_canon_sha256":"0e570b72ebbed722481b092c93c1ce29a4ba2538fea5e406ab3195b6857b8a4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:30.478950Z","signature_b64":"oV/dKrxqeVEptmLai9R3DvSsib4ln+2ijOwAi2kmgQe1VWVT9xhdbnyzCF6Cj2foDOe344QFA+aYWxvWP00iBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01684bca00ae1405a0300ab188ae8aaa1dc4cb43394d1020506c0b6e687cc256","last_reissued_at":"2026-07-05T11:50:30.478277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:30.478277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Bias of Foundation Model under Long-tailed Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing Su, Bin Qin, Hao Chen, Jiahao Chen, Jiangmeng Li","submitted_at":"2025-01-27T11:00:19Z","abstract_excerpt":"Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these models, overlooking the inherent biases introduced by the imbalanced training data they rely on. In this paper, we examine how such imbalances from pre-training affect long-tailed downstream tasks. Specifically, we find the imbalance biases inherited in foundation models on downstream task as paramete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15955","kind":"arxiv","version":3},"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/2501.15955/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":"2501.15955","created_at":"2026-07-05T11:50:30.478364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15955v3","created_at":"2026-07-05T11:50:30.478364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15955","created_at":"2026-07-05T11:50:30.478364+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFUEXSQAVYKA","created_at":"2026-07-05T11:50:30.478364+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFUEXSQAVYKALIBQ","created_at":"2026-07-05T11:50:30.478364+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFUEXSQA","created_at":"2026-07-05T11:50:30.478364+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/AFUEXSQAVYKALIBQBKYYRLUKVI","json":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI.json","graph_json":"https://pith.science/api/pith-number/AFUEXSQAVYKALIBQBKYYRLUKVI/graph.json","events_json":"https://pith.science/api/pith-number/AFUEXSQAVYKALIBQBKYYRLUKVI/events.json","paper":"https://pith.science/paper/AFUEXSQA"},"agent_actions":{"view_html":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI","download_json":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI.json","view_paper":"https://pith.science/paper/AFUEXSQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15955&json=true","fetch_graph":"https://pith.science/api/pith-number/AFUEXSQAVYKALIBQBKYYRLUKVI/graph.json","fetch_events":"https://pith.science/api/pith-number/AFUEXSQAVYKALIBQBKYYRLUKVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI/action/storage_attestation","attest_author":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI/action/author_attestation","sign_citation":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI/action/citation_signature","submit_replication":"https://pith.science/pith/AFUEXSQAVYKALIBQBKYYRLUKVI/action/replication_record"}},"created_at":"2026-07-05T11:50:30.478364+00:00","updated_at":"2026-07-05T11:50:30.478364+00:00"}