{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6J44XPZC2STE2ERBDZNW3RTEZM","short_pith_number":"pith:6J44XPZC","schema_version":"1.0","canonical_sha256":"f279cbbf22d4a64d12211e5b6dc664cb3c4c0a90fe584a607c11cf258f9c94a5","source":{"kind":"arxiv","id":"2405.03425","version":2},"attestation_state":"computed","paper":{"title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arsen Sheverdin, Emma Caldwell, Emre Onal, Klemens Fl\\\"oge, Vincent Fortuin","submitted_at":"2024-05-06T12:44:37Z","abstract_excerpt":"Fine-tuned Large Language Models (LLMs) often suffer from overconfidence and poor calibration, particularly when fine-tuned on small datasets. To address these challenges, we propose a simple combination of Low-Rank Adaptation (LoRA) with Gaussian Stochastic Weight Averaging (SWAG), facilitating approximate Bayesian inference in LLMs. Through extensive testing across several Natural Language Processing (NLP) benchmarks, we demonstrate that our straightforward and computationally efficient approach improves model generalization and calibration competitively with comparable, more sophisticated m"},"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":"2405.03425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T12:44:37Z","cross_cats_sorted":[],"title_canon_sha256":"9eb880c709b1c450b812575519c5cd0830b3e2c6932c65c2035cf5ffba26b11b","abstract_canon_sha256":"8e40bae5f458e2f57e24e595be10a58c75266cbba320e7002daa827628cd911f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:24.687289Z","signature_b64":"3EuMFNDhtq3Qjq/rPIOSKfP+uF9G4edIEooCUSXi9uzG3vtpgQ3mmLGCPrJXAqZyE5cP+ibgYvYHutan1UldCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f279cbbf22d4a64d12211e5b6dc664cb3c4c0a90fe584a607c11cf258f9c94a5","last_reissued_at":"2026-07-05T08:46:24.686785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:24.686785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arsen Sheverdin, Emma Caldwell, Emre Onal, Klemens Fl\\\"oge, Vincent Fortuin","submitted_at":"2024-05-06T12:44:37Z","abstract_excerpt":"Fine-tuned Large Language Models (LLMs) often suffer from overconfidence and poor calibration, particularly when fine-tuned on small datasets. To address these challenges, we propose a simple combination of Low-Rank Adaptation (LoRA) with Gaussian Stochastic Weight Averaging (SWAG), facilitating approximate Bayesian inference in LLMs. Through extensive testing across several Natural Language Processing (NLP) benchmarks, we demonstrate that our straightforward and computationally efficient approach improves model generalization and calibration competitively with comparable, more sophisticated m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03425","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/2405.03425/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":"2405.03425","created_at":"2026-07-05T08:46:24.686846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03425v2","created_at":"2026-07-05T08:46:24.686846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03425","created_at":"2026-07-05T08:46:24.686846+00:00"},{"alias_kind":"pith_short_12","alias_value":"6J44XPZC2STE","created_at":"2026-07-05T08:46:24.686846+00:00"},{"alias_kind":"pith_short_16","alias_value":"6J44XPZC2STE2ERB","created_at":"2026-07-05T08:46:24.686846+00:00"},{"alias_kind":"pith_short_8","alias_value":"6J44XPZC","created_at":"2026-07-05T08:46:24.686846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29184","citing_title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27747","citing_title":"Soft Specialists: $\\alpha$-R\\'enyi Ensembles for Uncertainty-Aware LLM Post-Training","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM","json":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM.json","graph_json":"https://pith.science/api/pith-number/6J44XPZC2STE2ERBDZNW3RTEZM/graph.json","events_json":"https://pith.science/api/pith-number/6J44XPZC2STE2ERBDZNW3RTEZM/events.json","paper":"https://pith.science/paper/6J44XPZC"},"agent_actions":{"view_html":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM","download_json":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM.json","view_paper":"https://pith.science/paper/6J44XPZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03425&json=true","fetch_graph":"https://pith.science/api/pith-number/6J44XPZC2STE2ERBDZNW3RTEZM/graph.json","fetch_events":"https://pith.science/api/pith-number/6J44XPZC2STE2ERBDZNW3RTEZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/action/storage_attestation","attest_author":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/action/author_attestation","sign_citation":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/action/citation_signature","submit_replication":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/action/replication_record"}},"created_at":"2026-07-05T08:46:24.686846+00:00","updated_at":"2026-07-05T08:46:24.686846+00:00"}