{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YPSRJZEXP7CGIYD3HWI6D37APB","short_pith_number":"pith:YPSRJZEX","schema_version":"1.0","canonical_sha256":"c3e514e4977fc464607b3d91e1efe07859f3a4e6289530760a68f3faae7a1136","source":{"kind":"arxiv","id":"2412.06418","version":2},"attestation_state":"computed","paper":{"title":"Continual Learning for Segment Anything Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Wang, Jianguo Zhang, Jinglong Yang, Jun Cen, Wenjian Huang, Yichen Wu","submitted_at":"2024-12-09T11:51:28Z","abstract_excerpt":"Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In real-world scenarios, we are generally confronted with the dynamic scenario where the data comes in a streaming manner. Driven by the practical need, in this paper, we first propose a novel Continual SAM adaptation (CoSAM) benchmark with 8 different task domains and carefully analyze the limitations of the existing SAM one-step adaptation methods in the conti"},"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":"2412.06418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T11:51:28Z","cross_cats_sorted":[],"title_canon_sha256":"cb5b21da7fd22a55e8c3ad25ba549b0b189bd2cb0fb9f5c72cc05c59390ce7a5","abstract_canon_sha256":"7f26b20cd1a37253e71a90b82c472d92c4e40c7eff67fd0638e467a377c0b24c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:07.865324Z","signature_b64":"YqC/+FwuqyuOu3HX5ZZUULWrKZt/Gnwab15aXRqmSWAJwe2W8WwzhUOrDCnaJXImye4xU028Linb0F6AbI2bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e514e4977fc464607b3d91e1efe07859f3a4e6289530760a68f3faae7a1136","last_reissued_at":"2026-07-05T09:50:07.864825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:07.864825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning for Segment Anything Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Wang, Jianguo Zhang, Jinglong Yang, Jun Cen, Wenjian Huang, Yichen Wu","submitted_at":"2024-12-09T11:51:28Z","abstract_excerpt":"Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In real-world scenarios, we are generally confronted with the dynamic scenario where the data comes in a streaming manner. Driven by the practical need, in this paper, we first propose a novel Continual SAM adaptation (CoSAM) benchmark with 8 different task domains and carefully analyze the limitations of the existing SAM one-step adaptation methods in the conti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06418","kind":"arxiv","version":2},"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/2412.06418/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":"2412.06418","created_at":"2026-07-05T09:50:07.864888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06418v2","created_at":"2026-07-05T09:50:07.864888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06418","created_at":"2026-07-05T09:50:07.864888+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPSRJZEXP7CG","created_at":"2026-07-05T09:50:07.864888+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPSRJZEXP7CGIYD3","created_at":"2026-07-05T09:50:07.864888+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPSRJZEX","created_at":"2026-07-05T09:50:07.864888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20135","citing_title":"Data-Distill-Net: A Data Distillation Approach Tailored for Reply-based Continual Learning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB","json":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB.json","graph_json":"https://pith.science/api/pith-number/YPSRJZEXP7CGIYD3HWI6D37APB/graph.json","events_json":"https://pith.science/api/pith-number/YPSRJZEXP7CGIYD3HWI6D37APB/events.json","paper":"https://pith.science/paper/YPSRJZEX"},"agent_actions":{"view_html":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB","download_json":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB.json","view_paper":"https://pith.science/paper/YPSRJZEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06418&json=true","fetch_graph":"https://pith.science/api/pith-number/YPSRJZEXP7CGIYD3HWI6D37APB/graph.json","fetch_events":"https://pith.science/api/pith-number/YPSRJZEXP7CGIYD3HWI6D37APB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB/action/storage_attestation","attest_author":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB/action/author_attestation","sign_citation":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB/action/citation_signature","submit_replication":"https://pith.science/pith/YPSRJZEXP7CGIYD3HWI6D37APB/action/replication_record"}},"created_at":"2026-07-05T09:50:07.864888+00:00","updated_at":"2026-07-05T09:50:07.864888+00:00"}