{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VK23TL4KH573LE7AZO3H5RZ3FV","short_pith_number":"pith:VK23TL4K","schema_version":"1.0","canonical_sha256":"aab5b9af8a3f7fb593e0cbb67ec73b2d4e1e6fb8a533717ff359da471ce0e97f","source":{"kind":"arxiv","id":"2409.10673","version":2},"attestation_state":"computed","paper":{"title":"A Bayesian Interpretation of Adaptive Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haolin Chen, Philip N. Garner","submitted_at":"2024-09-16T19:14:35Z","abstract_excerpt":"Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ratio (SNR), along with the Improved Variational Online Newton (IVON) optimizer, for adaptive parameter budget allocation. The resulting Bayesian counterpart not only has matched or surpassed the performance of using the sensitivity-based importance metric but is also a faster alternative to AdaLoRA with Adam. Our theoretical analysis reveals a significant connection between the two metrics, providing a Bayesian perspe"},"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":"2409.10673","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-16T19:14:35Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"6be779e4cef605ddc69818e281c443df23b9c4e0898ea3ac25fd1dd7519826d5","abstract_canon_sha256":"4839ad734f67cdc6a44c586363be60d34b7c3ca40640c5095f42890264a7e062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:52.582240Z","signature_b64":"PpL2FKk2uABP8a1ph0f25GJqW2V5r6XsCoTvKgsNVjSU3hEm+kUNaPv/Xp3QStsebMaKy50Qlf7PO1UsJn2rBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab5b9af8a3f7fb593e0cbb67ec73b2d4e1e6fb8a533717ff359da471ce0e97f","last_reissued_at":"2026-07-05T09:59:52.581898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:52.581898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bayesian Interpretation of Adaptive Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haolin Chen, Philip N. Garner","submitted_at":"2024-09-16T19:14:35Z","abstract_excerpt":"Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ratio (SNR), along with the Improved Variational Online Newton (IVON) optimizer, for adaptive parameter budget allocation. The resulting Bayesian counterpart not only has matched or surpassed the performance of using the sensitivity-based importance metric but is also a faster alternative to AdaLoRA with Adam. Our theoretical analysis reveals a significant connection between the two metrics, providing a Bayesian perspe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10673","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/2409.10673/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":"2409.10673","created_at":"2026-07-05T09:59:52.581954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10673v2","created_at":"2026-07-05T09:59:52.581954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10673","created_at":"2026-07-05T09:59:52.581954+00:00"},{"alias_kind":"pith_short_12","alias_value":"VK23TL4KH573","created_at":"2026-07-05T09:59:52.581954+00:00"},{"alias_kind":"pith_short_16","alias_value":"VK23TL4KH573LE7A","created_at":"2026-07-05T09:59:52.581954+00:00"},{"alias_kind":"pith_short_8","alias_value":"VK23TL4K","created_at":"2026-07-05T09:59:52.581954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14280","citing_title":"Improving LoRA with Variational Learning","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV","json":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV.json","graph_json":"https://pith.science/api/pith-number/VK23TL4KH573LE7AZO3H5RZ3FV/graph.json","events_json":"https://pith.science/api/pith-number/VK23TL4KH573LE7AZO3H5RZ3FV/events.json","paper":"https://pith.science/paper/VK23TL4K"},"agent_actions":{"view_html":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV","download_json":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV.json","view_paper":"https://pith.science/paper/VK23TL4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10673&json=true","fetch_graph":"https://pith.science/api/pith-number/VK23TL4KH573LE7AZO3H5RZ3FV/graph.json","fetch_events":"https://pith.science/api/pith-number/VK23TL4KH573LE7AZO3H5RZ3FV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV/action/storage_attestation","attest_author":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV/action/author_attestation","sign_citation":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV/action/citation_signature","submit_replication":"https://pith.science/pith/VK23TL4KH573LE7AZO3H5RZ3FV/action/replication_record"}},"created_at":"2026-07-05T09:59:52.581954+00:00","updated_at":"2026-07-05T09:59:52.581954+00:00"}