{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6J44XPZC2STE2ERBDZNW3RTEZM","short_pith_number":"pith:6J44XPZC","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"},"canonical_sha256":"f279cbbf22d4a64d12211e5b6dc664cb3c4c0a90fe584a607c11cf258f9c94a5","source":{"kind":"arxiv","id":"2405.03425","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03425","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03425v2","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03425","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"6J44XPZC2STE","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_16","alias_value":"6J44XPZC2STE2ERB","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_8","alias_value":"6J44XPZC","created_at":"2026-07-05T08:46:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6J44XPZC2STE2ERBDZNW3RTEZM","target":"record","payload":{"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"},"canonical_sha256":"f279cbbf22d4a64d12211e5b6dc664cb3c4c0a90fe584a607c11cf258f9c94a5","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"},"source_kind":"arxiv","source_id":"2405.03425","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1Yh60asDWrCqFfOr+UxSThx+/KCORhRVYVFiWimdkC4JVoNIxvRs3L4awTfHNRDVbIKAjZekkG2lqYu53hnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:24:18.648994Z"},"content_sha256":"873eeca406a539847568312121a757bd8990d24c4c275934947831ffc1de58a2","schema_version":"1.0","event_id":"sha256:873eeca406a539847568312121a757bd8990d24c4c275934947831ffc1de58a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6J44XPZC2STE2ERBDZNW3RTEZM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17IfmHPNG2GNlsrb5vJgOvJPWEHENjP62xkU66w1MqATy/Nq8OIhpyNScSvO1/Qi3uKdONBSYY+MEOgcgQRBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:24:18.649490Z"},"content_sha256":"567bc84813795cb729fca9a02d7744e828cdcb691d53c1e818c5b976ce905fa7","schema_version":"1.0","event_id":"sha256:567bc84813795cb729fca9a02d7744e828cdcb691d53c1e818c5b976ce905fa7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/bundle.json","state_url":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6J44XPZC2STE2ERBDZNW3RTEZM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T08:24:18Z","links":{"resolver":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM","bundle":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/bundle.json","state":"https://pith.science/pith/6J44XPZC2STE2ERBDZNW3RTEZM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6J44XPZC2STE2ERBDZNW3RTEZM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6J44XPZC2STE2ERBDZNW3RTEZM","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":"8e40bae5f458e2f57e24e595be10a58c75266cbba320e7002daa827628cd911f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T12:44:37Z","title_canon_sha256":"9eb880c709b1c450b812575519c5cd0830b3e2c6932c65c2035cf5ffba26b11b"},"schema_version":"1.0","source":{"id":"2405.03425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03425","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03425v2","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03425","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"6J44XPZC2STE","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_16","alias_value":"6J44XPZC2STE2ERB","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_8","alias_value":"6J44XPZC","created_at":"2026-07-05T08:46:24Z"}],"graph_snapshots":[{"event_id":"sha256:567bc84813795cb729fca9a02d7744e828cdcb691d53c1e818c5b976ce905fa7","target":"graph","created_at":"2026-07-05T08:46:24Z","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/2405.03425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arsen Sheverdin, Emma Caldwell, Emre Onal, Klemens Fl\\\"oge, Vincent Fortuin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T12:44:37Z","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03425","kind":"arxiv","version":2},"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":"sha256:873eeca406a539847568312121a757bd8990d24c4c275934947831ffc1de58a2","target":"record","created_at":"2026-07-05T08:46:24Z","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":"8e40bae5f458e2f57e24e595be10a58c75266cbba320e7002daa827628cd911f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T12:44:37Z","title_canon_sha256":"9eb880c709b1c450b812575519c5cd0830b3e2c6932c65c2035cf5ffba26b11b"},"schema_version":"1.0","source":{"id":"2405.03425","kind":"arxiv","version":2}},"canonical_sha256":"f279cbbf22d4a64d12211e5b6dc664cb3c4c0a90fe584a607c11cf258f9c94a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f279cbbf22d4a64d12211e5b6dc664cb3c4c0a90fe584a607c11cf258f9c94a5","first_computed_at":"2026-07-05T08:46:24.686785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:24.686785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3EuMFNDhtq3Qjq/rPIOSKfP+uF9G4edIEooCUSXi9uzG3vtpgQ3mmLGCPrJXAqZyE5cP+ibgYvYHutan1UldCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:24.687289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:873eeca406a539847568312121a757bd8990d24c4c275934947831ffc1de58a2","sha256:567bc84813795cb729fca9a02d7744e828cdcb691d53c1e818c5b976ce905fa7"],"state_sha256":"859cd422faa8a267a9d6c84ff9cc4884b33174d994396376283fec3317a01e5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"agtPT8ZDT6wYBDidyJvg64JSTLoWWDFcO7sEFJ9n/PE0cZI6b7wR2IaM7Gsp2R0wJkAy7wbfUF1wxZFrDXdABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:24:18.654442Z","bundle_sha256":"c4e1d566017c6c5dca507a6b202f7e37771908ed8ed169952a1401117fec85fe"}}