{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JPQTFMYDHGKC7TWDW5644FDDB5","short_pith_number":"pith:JPQTFMYD","schema_version":"1.0","canonical_sha256":"4be132b30339942fcec3b77dce14630f7d171eadeaea81c498ddfec5025af96f","source":{"kind":"arxiv","id":"2402.04009","version":1},"attestation_state":"computed","paper":{"title":"Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianxin Wu, Ke Zhu, Minghao Fu, Ningyuan Tang","submitted_at":"2024-02-06T14:03:15Z","abstract_excerpt":"In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow training speed. Because learnable parameters from these methods are entangled with the pretrained model, gradients related to the frozen pretrained model's parameters have to be computed and stored during finetuning. We propose Low-rank Attention Side-Tuning (LAST), which disentangles the trainable module from the pretrained model by freezing not only parameters b"},"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":"2402.04009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T14:03:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2900114e01f254d4bed2acce0f7b8e0bfd87a42458528afa90cfbc88abb58011","abstract_canon_sha256":"704ee1f4d333753a51f6ffbdc9cf8d6e3b0303fa5bc2d44f9b36b9a74bc8766a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:01.798282Z","signature_b64":"bfJ3yXzgB75vfOy1IOe6raNNDQr8+lgYMI0LoRYoY8fvNzQzqxCObVcEJOpsUQd98MA2IiUJXxdLM15uxQtcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be132b30339942fcec3b77dce14630f7d171eadeaea81c498ddfec5025af96f","last_reissued_at":"2026-07-05T07:42:01.797928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:01.797928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianxin Wu, Ke Zhu, Minghao Fu, Ningyuan Tang","submitted_at":"2024-02-06T14:03:15Z","abstract_excerpt":"In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow training speed. Because learnable parameters from these methods are entangled with the pretrained model, gradients related to the frozen pretrained model's parameters have to be computed and stored during finetuning. We propose Low-rank Attention Side-Tuning (LAST), which disentangles the trainable module from the pretrained model by freezing not only parameters b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04009","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/2402.04009/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":"2402.04009","created_at":"2026-07-05T07:42:01.797986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04009v1","created_at":"2026-07-05T07:42:01.797986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04009","created_at":"2026-07-05T07:42:01.797986+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPQTFMYDHGKC","created_at":"2026-07-05T07:42:01.797986+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPQTFMYDHGKC7TWD","created_at":"2026-07-05T07:42:01.797986+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPQTFMYD","created_at":"2026-07-05T07:42:01.797986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14201","citing_title":"FLASH-D: FlashAttention with Hidden Softmax Division","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5","json":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5.json","graph_json":"https://pith.science/api/pith-number/JPQTFMYDHGKC7TWDW5644FDDB5/graph.json","events_json":"https://pith.science/api/pith-number/JPQTFMYDHGKC7TWDW5644FDDB5/events.json","paper":"https://pith.science/paper/JPQTFMYD"},"agent_actions":{"view_html":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5","download_json":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5.json","view_paper":"https://pith.science/paper/JPQTFMYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04009&json=true","fetch_graph":"https://pith.science/api/pith-number/JPQTFMYDHGKC7TWDW5644FDDB5/graph.json","fetch_events":"https://pith.science/api/pith-number/JPQTFMYDHGKC7TWDW5644FDDB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5/action/storage_attestation","attest_author":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5/action/author_attestation","sign_citation":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5/action/citation_signature","submit_replication":"https://pith.science/pith/JPQTFMYDHGKC7TWDW5644FDDB5/action/replication_record"}},"created_at":"2026-07-05T07:42:01.797986+00:00","updated_at":"2026-07-05T07:42:01.797986+00:00"}