{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJE32S25JCK62SGRTSOADMKIR4","short_pith_number":"pith:YJE32S25","schema_version":"1.0","canonical_sha256":"c249bd4b5d4895ed48d19c9c01b1488f267ec88c2cb904b07ec93dc725e59717","source":{"kind":"arxiv","id":"2407.05229","version":2},"attestation_state":"computed","paper":{"title":"HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hang Su, Jingyi Xie, Jun Zhu, Liyuan Wang, Xingxing Zhang","submitted_at":"2024-07-07T01:50:25Z","abstract_excerpt":"The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving tasks, a promising direction involves keeping the pre-trained backbone frozen while employing parameter-efficient tuning (PET) techniques to instruct representation learning. Despite the popularity of Prompt-based PET for CL, its empirical design often leads to sub-optimal performance in our evaluation of different PTMs and target tasks. To this end, we propose"},"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":"2407.05229","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-07T01:50:25Z","cross_cats_sorted":[],"title_canon_sha256":"eb80c9448510479b34af973886b85835041df779e74440f18bedbfe89a4a7bbf","abstract_canon_sha256":"7b726cd84843bd43e955497741f6d5e5e82fb7847c9ebdfcf1cab7bec287be23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:08.810223Z","signature_b64":"pCSqgr6/71QEW/D++Dmoe4YBI2i8ZaqIaya40oZhVV10giDLsNrV8T9GLMfhSmQ+cTAYPCCRV2l5CxKLplxvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c249bd4b5d4895ed48d19c9c01b1488f267ec88c2cb904b07ec93dc725e59717","last_reissued_at":"2026-07-05T10:50:08.809755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:08.809755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hang Su, Jingyi Xie, Jun Zhu, Liyuan Wang, Xingxing Zhang","submitted_at":"2024-07-07T01:50:25Z","abstract_excerpt":"The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving tasks, a promising direction involves keeping the pre-trained backbone frozen while employing parameter-efficient tuning (PET) techniques to instruct representation learning. Despite the popularity of Prompt-based PET for CL, its empirical design often leads to sub-optimal performance in our evaluation of different PTMs and target tasks. To this end, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05229","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/2407.05229/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":"2407.05229","created_at":"2026-07-05T10:50:08.809814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05229v2","created_at":"2026-07-05T10:50:08.809814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05229","created_at":"2026-07-05T10:50:08.809814+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJE32S25JCK6","created_at":"2026-07-05T10:50:08.809814+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJE32S25JCK62SGR","created_at":"2026-07-05T10:50:08.809814+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJE32S25","created_at":"2026-07-05T10:50:08.809814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10355","citing_title":"TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4","json":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4.json","graph_json":"https://pith.science/api/pith-number/YJE32S25JCK62SGRTSOADMKIR4/graph.json","events_json":"https://pith.science/api/pith-number/YJE32S25JCK62SGRTSOADMKIR4/events.json","paper":"https://pith.science/paper/YJE32S25"},"agent_actions":{"view_html":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4","download_json":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4.json","view_paper":"https://pith.science/paper/YJE32S25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05229&json=true","fetch_graph":"https://pith.science/api/pith-number/YJE32S25JCK62SGRTSOADMKIR4/graph.json","fetch_events":"https://pith.science/api/pith-number/YJE32S25JCK62SGRTSOADMKIR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4/action/storage_attestation","attest_author":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4/action/author_attestation","sign_citation":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4/action/citation_signature","submit_replication":"https://pith.science/pith/YJE32S25JCK62SGRTSOADMKIR4/action/replication_record"}},"created_at":"2026-07-05T10:50:08.809814+00:00","updated_at":"2026-07-05T10:50:08.809814+00:00"}