{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFNC2RCB3TTUHIWRVXVN2HNUK4","short_pith_number":"pith:RFNC2RCB","schema_version":"1.0","canonical_sha256":"895a2d4441dce743a2d1adeadd1db4572d789c435cbb0ac7e0a768f0fe2969b5","source":{"kind":"arxiv","id":"2405.15282","version":2},"attestation_state":"computed","paper":{"title":"Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhinav Jain, Chris Jermaine, Swarat Chaudhuri, Thomas Reps","submitted_at":"2024-05-24T07:11:42Z","abstract_excerpt":"Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as these adapters must be housed and run at the FM server. Traditional prompt tuning offers a potential solution by customising them through task-specific input prefixes, but it under-performs compared to other PEFT methods like LoRA. To address this gap, we propose Low-Rank Prompt Adaptation (LoPA), a prompt-tuning-based approach that performs on par w"},"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":"2405.15282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T07:11:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c2b3deea781dec8109f8ef18cce2509abcf592893d464bd2597aabb525ebf609","abstract_canon_sha256":"738668a28c2e477118cf981ad0a34190d2ea9e1911bff161c9167d6576256e7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:28.913838Z","signature_b64":"/rDxOtuUz4qE4td1qqjBGRhW/i65sVh1U0glrqBi9eBBHXEqbOQpOYDT3WW1hjnZCzCK8ckxxTCVktRMMZPTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"895a2d4441dce743a2d1adeadd1db4572d789c435cbb0ac7e0a768f0fe2969b5","last_reissued_at":"2026-07-05T09:29:28.913380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:28.913380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhinav Jain, Chris Jermaine, Swarat Chaudhuri, Thomas Reps","submitted_at":"2024-05-24T07:11:42Z","abstract_excerpt":"Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as these adapters must be housed and run at the FM server. Traditional prompt tuning offers a potential solution by customising them through task-specific input prefixes, but it under-performs compared to other PEFT methods like LoRA. To address this gap, we propose Low-Rank Prompt Adaptation (LoPA), a prompt-tuning-based approach that performs on par w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15282","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/2405.15282/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":"2405.15282","created_at":"2026-07-05T09:29:28.913437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15282v2","created_at":"2026-07-05T09:29:28.913437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15282","created_at":"2026-07-05T09:29:28.913437+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFNC2RCB3TTU","created_at":"2026-07-05T09:29:28.913437+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFNC2RCB3TTUHIWR","created_at":"2026-07-05T09:29:28.913437+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFNC2RCB","created_at":"2026-07-05T09:29:28.913437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00178","citing_title":"Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4","json":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4.json","graph_json":"https://pith.science/api/pith-number/RFNC2RCB3TTUHIWRVXVN2HNUK4/graph.json","events_json":"https://pith.science/api/pith-number/RFNC2RCB3TTUHIWRVXVN2HNUK4/events.json","paper":"https://pith.science/paper/RFNC2RCB"},"agent_actions":{"view_html":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4","download_json":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4.json","view_paper":"https://pith.science/paper/RFNC2RCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15282&json=true","fetch_graph":"https://pith.science/api/pith-number/RFNC2RCB3TTUHIWRVXVN2HNUK4/graph.json","fetch_events":"https://pith.science/api/pith-number/RFNC2RCB3TTUHIWRVXVN2HNUK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4/action/storage_attestation","attest_author":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4/action/author_attestation","sign_citation":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4/action/citation_signature","submit_replication":"https://pith.science/pith/RFNC2RCB3TTUHIWRVXVN2HNUK4/action/replication_record"}},"created_at":"2026-07-05T09:29:28.913437+00:00","updated_at":"2026-07-05T09:29:28.913437+00:00"}