{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LA4DEKKIYFXPVQJO26D2YW6ZGK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5dee2ca1941cdabe310cefb047e5a0a4c57be59895b2b525ca4f1e8150e75f56","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T07:49:43Z","title_canon_sha256":"3ccf8f6d00fe7bf2b05fa5f7b91d80e9d457a3bf748d904582cfa7f39d4aec8d"},"schema_version":"1.0","source":{"id":"2506.14280","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14280","created_at":"2026-07-05T11:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14280v1","created_at":"2026-07-05T11:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14280","created_at":"2026-07-05T11:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"LA4DEKKIYFXP","created_at":"2026-07-05T11:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"LA4DEKKIYFXPVQJO","created_at":"2026-07-05T11:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"LA4DEKKI","created_at":"2026-07-05T11:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:d21db6552e6ca6ed2505973ca850838feb96f219d392f648126bd065628c17e9","target":"graph","created_at":"2026-07-05T11:22:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.14280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bayesian methods have recently been used to improve LoRA finetuning and, although they improve calibration, their effect on other metrics (such as accuracy) is marginal and can sometimes even be detrimental. Moreover, Bayesian methods also increase computational overheads and require additional tricks for them to work well. Here, we fix these issues by using a recently proposed variational algorithm called IVON. We show that IVON is easy to implement and has similar costs to AdamW, and yet it can also drastically improve many metrics by using a simple posterior pruning technique. We present ex","authors_text":"Bai Cong, Mohammad Emtiyaz Khan, Nico Daheim, Rio Yokota, Thomas M\\\"ollenhoff, Yuesong Shen","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T07:49:43Z","title":"Improving LoRA with Variational Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14280","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:01894f143ec715374e31c08f2c3016fae1b8b865dbff5fbfe9f35a9968a60f85","target":"record","created_at":"2026-07-05T11:22:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5dee2ca1941cdabe310cefb047e5a0a4c57be59895b2b525ca4f1e8150e75f56","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T07:49:43Z","title_canon_sha256":"3ccf8f6d00fe7bf2b05fa5f7b91d80e9d457a3bf748d904582cfa7f39d4aec8d"},"schema_version":"1.0","source":{"id":"2506.14280","kind":"arxiv","version":1}},"canonical_sha256":"5838322948c16efac12ed787ac5bd9328e98d2f261908718807a15637de0c787","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5838322948c16efac12ed787ac5bd9328e98d2f261908718807a15637de0c787","first_computed_at":"2026-07-05T11:22:52.551653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:52.551653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4tHx/aLzTs321YXovQAsYsh4K94EfZ1GcmdwgAjvf2XHbUu0trOLPou7OTF4LCvf7ZCZR+FqQ8wB6Ozj3DKcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:52.552133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14280","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01894f143ec715374e31c08f2c3016fae1b8b865dbff5fbfe9f35a9968a60f85","sha256:d21db6552e6ca6ed2505973ca850838feb96f219d392f648126bd065628c17e9"],"state_sha256":"514d270d774c74fdad421f926985bcabb3e213897c6c0b5fa4e2e6a13677c9fd"}