{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUOSISGQQM5ZRHMLWH2OZNOKNA","short_pith_number":"pith:PUOSISGQ","schema_version":"1.0","canonical_sha256":"7d1d2448d0833b989d8bb1f4ecb5ca683ebe6b77e45d934c40834cfabcfe5a46","source":{"kind":"arxiv","id":"2408.08295","version":1},"attestation_state":"computed","paper":{"title":"SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gengwei Zhang, Guoliang Kang, Ling Chen, Liyuan Wang, Yunchao Wei","submitted_at":"2024-08-15T17:50:07Z","abstract_excerpt":"In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trained models (PTMs) can greatly facilitate knowledge transfer and alleviate catastrophic forgetting, but also suffers from progressive overfitting of pre-trained knowledge into specific downstream tasks. A majority of current efforts often keep the PTMs frozen and incorporate task-specific prompts to instruct representation learning, coupled with a prompt selection process for inference. However, due to the limited cap"},"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":"2408.08295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T17:50:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"276584fdc2f0bdfe8eee790dbfca2c833da6a5069d451a538e6eea772f00422b","abstract_canon_sha256":"eda0cae4e4f6aca0e62278326511dcde82b0950c5ebb1eba92c88cf55b5103db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:46.725437Z","signature_b64":"SoU6ClL2QmVpvGHk6amiqWpeSC/J7R76w+B9fSn3Slive/yirxrj3f5wvYkvTiPomktqTKLYEbfRKdA4rnCAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d1d2448d0833b989d8bb1f4ecb5ca683ebe6b77e45d934c40834cfabcfe5a46","last_reissued_at":"2026-07-05T08:55:46.725014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:46.725014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gengwei Zhang, Guoliang Kang, Ling Chen, Liyuan Wang, Yunchao Wei","submitted_at":"2024-08-15T17:50:07Z","abstract_excerpt":"In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trained models (PTMs) can greatly facilitate knowledge transfer and alleviate catastrophic forgetting, but also suffers from progressive overfitting of pre-trained knowledge into specific downstream tasks. A majority of current efforts often keep the PTMs frozen and incorporate task-specific prompts to instruct representation learning, coupled with a prompt selection process for inference. However, due to the limited cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08295","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/2408.08295/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":"2408.08295","created_at":"2026-07-05T08:55:46.725069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08295v1","created_at":"2026-07-05T08:55:46.725069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08295","created_at":"2026-07-05T08:55:46.725069+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUOSISGQQM5Z","created_at":"2026-07-05T08:55:46.725069+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUOSISGQQM5ZRHML","created_at":"2026-07-05T08:55:46.725069+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUOSISGQ","created_at":"2026-07-05T08:55:46.725069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.12318","citing_title":"Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA","json":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA.json","graph_json":"https://pith.science/api/pith-number/PUOSISGQQM5ZRHMLWH2OZNOKNA/graph.json","events_json":"https://pith.science/api/pith-number/PUOSISGQQM5ZRHMLWH2OZNOKNA/events.json","paper":"https://pith.science/paper/PUOSISGQ"},"agent_actions":{"view_html":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA","download_json":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA.json","view_paper":"https://pith.science/paper/PUOSISGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08295&json=true","fetch_graph":"https://pith.science/api/pith-number/PUOSISGQQM5ZRHMLWH2OZNOKNA/graph.json","fetch_events":"https://pith.science/api/pith-number/PUOSISGQQM5ZRHMLWH2OZNOKNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA/action/storage_attestation","attest_author":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA/action/author_attestation","sign_citation":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA/action/citation_signature","submit_replication":"https://pith.science/pith/PUOSISGQQM5ZRHMLWH2OZNOKNA/action/replication_record"}},"created_at":"2026-07-05T08:55:46.725069+00:00","updated_at":"2026-07-05T08:55:46.725069+00:00"}