{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:552C4TPTUC3QX47EH6RUUYCVQU","short_pith_number":"pith:552C4TPT","schema_version":"1.0","canonical_sha256":"ef742e4df3a0b70bf3e43fa34a605585340191745042ea3c7caabaac34f2c3a5","source":{"kind":"arxiv","id":"2407.10281","version":1},"attestation_state":"computed","paper":{"title":"Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Wang, SongLin Dong, Xinyuan Gao, Yihong Gong, Yuhang He","submitted_at":"2024-07-14T17:40:40Z","abstract_excerpt":"The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale pre-trained models as the backbone and use key-query matching to generate trainable prompts to learn new knowledge. However, the domain gap between the pre-training dataset and the downstream datasets can easily lead to inaccuracies in key-query matching prompt selection when directly generating queries using the pre-trained model, which hampers learning new knowl"},"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":"2407.10281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-14T17:40:40Z","cross_cats_sorted":[],"title_canon_sha256":"612608d19faf58fb94792fa6d36f9f3a4315858efa860c12e0c1c9c87209be0e","abstract_canon_sha256":"077a2dd44d2c5ee26d9dc7353da505d9394b3c7e94b96a73f2bb7d790b71b0ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:41.750576Z","signature_b64":"9/xe/IwEXP14qZyYYZRiU8rgtzQL9aCOgauVrfUrTKO7uj3h00okFjWP0Ruxjp3AObJYl6typJkDDkzbibLiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef742e4df3a0b70bf3e43fa34a605585340191745042ea3c7caabaac34f2c3a5","last_reissued_at":"2026-07-05T08:43:41.750200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:41.750200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Wang, SongLin Dong, Xinyuan Gao, Yihong Gong, Yuhang He","submitted_at":"2024-07-14T17:40:40Z","abstract_excerpt":"The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale pre-trained models as the backbone and use key-query matching to generate trainable prompts to learn new knowledge. However, the domain gap between the pre-training dataset and the downstream datasets can easily lead to inaccuracies in key-query matching prompt selection when directly generating queries using the pre-trained model, which hampers learning new knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10281","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/2407.10281/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":"2407.10281","created_at":"2026-07-05T08:43:41.750255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10281v1","created_at":"2026-07-05T08:43:41.750255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10281","created_at":"2026-07-05T08:43:41.750255+00:00"},{"alias_kind":"pith_short_12","alias_value":"552C4TPTUC3Q","created_at":"2026-07-05T08:43:41.750255+00:00"},{"alias_kind":"pith_short_16","alias_value":"552C4TPTUC3QX47E","created_at":"2026-07-05T08:43:41.750255+00:00"},{"alias_kind":"pith_short_8","alias_value":"552C4TPT","created_at":"2026-07-05T08:43:41.750255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09471","citing_title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU","json":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU.json","graph_json":"https://pith.science/api/pith-number/552C4TPTUC3QX47EH6RUUYCVQU/graph.json","events_json":"https://pith.science/api/pith-number/552C4TPTUC3QX47EH6RUUYCVQU/events.json","paper":"https://pith.science/paper/552C4TPT"},"agent_actions":{"view_html":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU","download_json":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU.json","view_paper":"https://pith.science/paper/552C4TPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10281&json=true","fetch_graph":"https://pith.science/api/pith-number/552C4TPTUC3QX47EH6RUUYCVQU/graph.json","fetch_events":"https://pith.science/api/pith-number/552C4TPTUC3QX47EH6RUUYCVQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU/action/storage_attestation","attest_author":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU/action/author_attestation","sign_citation":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU/action/citation_signature","submit_replication":"https://pith.science/pith/552C4TPTUC3QX47EH6RUUYCVQU/action/replication_record"}},"created_at":"2026-07-05T08:43:41.750255+00:00","updated_at":"2026-07-05T08:43:41.750255+00:00"}