{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HWVDYWPI4PC4ULO5RKWWT6GDOV","short_pith_number":"pith:HWVDYWPI","schema_version":"1.0","canonical_sha256":"3daa3c59e8e3c5ca2ddd8aad69f8c375724476c08fc93d08712cb52d3b4d4d92","source":{"kind":"arxiv","id":"2309.07117","version":3},"attestation_state":"computed","paper":{"title":"PILOT: A Pre-Trained Model-Based Continual Learning Toolbox","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Da-Wei Zhou, De-Chuan Zhan, Hai-Long Sun, Han-Jia Ye","submitted_at":"2023-09-13T17:55:11Z","abstract_excerpt":"While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, incremental learning emerges to address real-world scenarios involving new data's arrival. Recently, pre-training has made significant advancements and garnered the attention of numerous researchers. The strong performance of these pre-trained models (PTMs) presents a promising avenue for developing continual learning algorithms that can effectively adapt to real-world scenarios. Cons"},"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":"2309.07117","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-13T17:55:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5113f5cd02a7bf987e6cb3d2ee58b5f5c4db950e420e688859e41c39b7bd1c48","abstract_canon_sha256":"df47d3e81f17d1073d3986d18c12af5ddbd61101ea8b7cbb724539b070fa6fb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:36.180823Z","signature_b64":"/FyaMuY6FU9GHKWsYmGNlXmbj+nOHqwk854uIsG82K+HKaya8JgrcBJiX0KuiiFpGxyB/DKxIdC0lKqdBxaBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3daa3c59e8e3c5ca2ddd8aad69f8c375724476c08fc93d08712cb52d3b4d4d92","last_reissued_at":"2026-07-05T10:26:36.180304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:36.180304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PILOT: A Pre-Trained Model-Based Continual Learning Toolbox","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Da-Wei Zhou, De-Chuan Zhan, Hai-Long Sun, Han-Jia Ye","submitted_at":"2023-09-13T17:55:11Z","abstract_excerpt":"While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, incremental learning emerges to address real-world scenarios involving new data's arrival. Recently, pre-training has made significant advancements and garnered the attention of numerous researchers. The strong performance of these pre-trained models (PTMs) presents a promising avenue for developing continual learning algorithms that can effectively adapt to real-world scenarios. Cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07117","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/2309.07117/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":"2309.07117","created_at":"2026-07-05T10:26:36.180381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07117v3","created_at":"2026-07-05T10:26:36.180381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07117","created_at":"2026-07-05T10:26:36.180381+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWVDYWPI4PC4","created_at":"2026-07-05T10:26:36.180381+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWVDYWPI4PC4ULO5","created_at":"2026-07-05T10:26:36.180381+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWVDYWPI","created_at":"2026-07-05T10:26:36.180381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29592","citing_title":"Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2411.02813","citing_title":"Sparse Orthogonal Parameters Tuning for Continual Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11091","citing_title":"LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11112","citing_title":"Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV","json":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV.json","graph_json":"https://pith.science/api/pith-number/HWVDYWPI4PC4ULO5RKWWT6GDOV/graph.json","events_json":"https://pith.science/api/pith-number/HWVDYWPI4PC4ULO5RKWWT6GDOV/events.json","paper":"https://pith.science/paper/HWVDYWPI"},"agent_actions":{"view_html":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV","download_json":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV.json","view_paper":"https://pith.science/paper/HWVDYWPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07117&json=true","fetch_graph":"https://pith.science/api/pith-number/HWVDYWPI4PC4ULO5RKWWT6GDOV/graph.json","fetch_events":"https://pith.science/api/pith-number/HWVDYWPI4PC4ULO5RKWWT6GDOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV/action/storage_attestation","attest_author":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV/action/author_attestation","sign_citation":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV/action/citation_signature","submit_replication":"https://pith.science/pith/HWVDYWPI4PC4ULO5RKWWT6GDOV/action/replication_record"}},"created_at":"2026-07-05T10:26:36.180381+00:00","updated_at":"2026-07-05T10:26:36.180381+00:00"}