{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SE5UZ6IBRV74Y3EXVKNLKJNNMJ","short_pith_number":"pith:SE5UZ6IB","schema_version":"1.0","canonical_sha256":"913b4cf9018d7fcc6c97aa9ab525ad624dda00972176e28bd629a0c3fc27c3bf","source":{"kind":"arxiv","id":"2504.03450","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Specific and Shared Parameters for Efficient Parameter Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dinh Phung, Mehrtash Harandi, Thanh-Toan Do, Trung Le, Van-Anh Nguyen","submitted_at":"2025-04-04T13:43:54Z","abstract_excerpt":"Foundation models, with a vast number of parameters and pretraining on massive datasets, achieve state-of-the-art performance across various applications. However, efficiently adapting them to downstream tasks with minimal computational overhead remains a challenge. Parameter-Efficient Transfer Learning (PETL) addresses this by fine-tuning only a small subset of parameters while preserving pre-trained knowledge. In this paper, we propose SaS, a novel PETL method that effectively mitigates distributional shifts during fine-tuning. SaS integrates (1) a shared module that captures common statisti"},"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":"2504.03450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-04T13:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"a77fae7ad032759dfd431e7e8e148b322bd787871c3e8092729e852851fefa86","abstract_canon_sha256":"176d6c05cefed02f0eb4647eea41c8a9cf66cdaca18a8deb40f748269f705213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:32.394980Z","signature_b64":"TzQKkQPxsxQpOYOYgzZoh16bBuEogAiVmHdrWH9tSRW6jsK961pkVujADyuL3d+pNh6Vge6IEzTbbUInzaxQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"913b4cf9018d7fcc6c97aa9ab525ad624dda00972176e28bd629a0c3fc27c3bf","last_reissued_at":"2026-07-05T10:44:32.394504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:32.394504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Specific and Shared Parameters for Efficient Parameter Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dinh Phung, Mehrtash Harandi, Thanh-Toan Do, Trung Le, Van-Anh Nguyen","submitted_at":"2025-04-04T13:43:54Z","abstract_excerpt":"Foundation models, with a vast number of parameters and pretraining on massive datasets, achieve state-of-the-art performance across various applications. However, efficiently adapting them to downstream tasks with minimal computational overhead remains a challenge. Parameter-Efficient Transfer Learning (PETL) addresses this by fine-tuning only a small subset of parameters while preserving pre-trained knowledge. In this paper, we propose SaS, a novel PETL method that effectively mitigates distributional shifts during fine-tuning. SaS integrates (1) a shared module that captures common statisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03450","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/2504.03450/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":"2504.03450","created_at":"2026-07-05T10:44:32.394560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03450v1","created_at":"2026-07-05T10:44:32.394560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03450","created_at":"2026-07-05T10:44:32.394560+00:00"},{"alias_kind":"pith_short_12","alias_value":"SE5UZ6IBRV74","created_at":"2026-07-05T10:44:32.394560+00:00"},{"alias_kind":"pith_short_16","alias_value":"SE5UZ6IBRV74Y3EX","created_at":"2026-07-05T10:44:32.394560+00:00"},{"alias_kind":"pith_short_8","alias_value":"SE5UZ6IB","created_at":"2026-07-05T10:44:32.394560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ","json":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ.json","graph_json":"https://pith.science/api/pith-number/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/graph.json","events_json":"https://pith.science/api/pith-number/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/events.json","paper":"https://pith.science/paper/SE5UZ6IB"},"agent_actions":{"view_html":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ","download_json":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ.json","view_paper":"https://pith.science/paper/SE5UZ6IB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03450&json=true","fetch_graph":"https://pith.science/api/pith-number/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/action/storage_attestation","attest_author":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/action/author_attestation","sign_citation":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/action/citation_signature","submit_replication":"https://pith.science/pith/SE5UZ6IBRV74Y3EXVKNLKJNNMJ/action/replication_record"}},"created_at":"2026-07-05T10:44:32.394560+00:00","updated_at":"2026-07-05T10:44:32.394560+00:00"}