{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CWHGMWIYBZDJRUE4ZVOMM5PMZ3","short_pith_number":"pith:CWHGMWIY","schema_version":"1.0","canonical_sha256":"158e6659180e4698d09ccd5cc675eccec58856c4b71cdf4853578013a8871ca2","source":{"kind":"arxiv","id":"2409.11323","version":1},"attestation_state":"computed","paper":{"title":"LPT++: Efficient Training on Mixture of Long-tailed Experts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Dong, Pan Zhou, Wangmeng Zuo","submitted_at":"2024-09-17T16:19:11Z","abstract_excerpt":"We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core components. The first is a universal long-tailed adaptation module, which aggregates long-tailed prompts and visual adapters to adapt the pretrained model to the target domain, meanwhile improving its discriminative ability. The second is the mixture of long-tailed experts framework with a mixture-of-experts (MoE) scorer, which adaptively calculate"},"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":"2409.11323","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T16:19:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a1714a6a94a2cf364775d50c9c6da66938d10fc808d948ae9da88b48d31a980","abstract_canon_sha256":"a7a0a2199b7cefd499700b62081f995f12fe493c93719a7a440a5e5e5fb5705c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:16.516101Z","signature_b64":"WDTuDoRZoSR07r1zHn8Z8PvEXyiMlB7u8Yi0EQHYZHYNmHCV0ZahASaDWIl3hw0Qz/tvsTpkfYGaBbmAC4w6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158e6659180e4698d09ccd5cc675eccec58856c4b71cdf4853578013a8871ca2","last_reissued_at":"2026-07-05T09:08:16.515625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:16.515625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LPT++: Efficient Training on Mixture of Long-tailed Experts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Dong, Pan Zhou, Wangmeng Zuo","submitted_at":"2024-09-17T16:19:11Z","abstract_excerpt":"We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core components. The first is a universal long-tailed adaptation module, which aggregates long-tailed prompts and visual adapters to adapt the pretrained model to the target domain, meanwhile improving its discriminative ability. The second is the mixture of long-tailed experts framework with a mixture-of-experts (MoE) scorer, which adaptively calculate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11323","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/2409.11323/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":"2409.11323","created_at":"2026-07-05T09:08:16.515682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11323v1","created_at":"2026-07-05T09:08:16.515682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11323","created_at":"2026-07-05T09:08:16.515682+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWHGMWIYBZDJ","created_at":"2026-07-05T09:08:16.515682+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWHGMWIYBZDJRUE4","created_at":"2026-07-05T09:08:16.515682+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWHGMWIY","created_at":"2026-07-05T09:08:16.515682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15979","citing_title":"MR-GDINO: Efficient Open-World Continual Object Detection","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3","json":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3.json","graph_json":"https://pith.science/api/pith-number/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/graph.json","events_json":"https://pith.science/api/pith-number/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/events.json","paper":"https://pith.science/paper/CWHGMWIY"},"agent_actions":{"view_html":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3","download_json":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3.json","view_paper":"https://pith.science/paper/CWHGMWIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11323&json=true","fetch_graph":"https://pith.science/api/pith-number/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/action/storage_attestation","attest_author":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/action/author_attestation","sign_citation":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/action/citation_signature","submit_replication":"https://pith.science/pith/CWHGMWIYBZDJRUE4ZVOMM5PMZ3/action/replication_record"}},"created_at":"2026-07-05T09:08:16.515682+00:00","updated_at":"2026-07-05T09:08:16.515682+00:00"}