{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EIMJDG3EK3RDGBBXOKZYKY6VRU","short_pith_number":"pith:EIMJDG3E","canonical_record":{"source":{"id":"2402.17641","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T16:11:05Z","cross_cats_sorted":["cs.AI","cs.CL","math.OC","stat.ML"],"title_canon_sha256":"cac9562ea3f4d7ff35b6126d6ec2c50870f1d6e41a8e750dd897f69bed11ede4","abstract_canon_sha256":"fd9ffca98171540ba110f76bd3d8b3721575c4f43407265de04fc498fbe4d434"},"schema_version":"1.0"},"canonical_sha256":"2218919b6456e233043772b38563d58d17c027e2fb5d90b02d83731406d43bdb","source":{"kind":"arxiv","id":"2402.17641","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17641","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17641v2","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17641","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"EIMJDG3EK3RD","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"EIMJDG3EK3RDGBBX","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"EIMJDG3E","created_at":"2026-07-05T08:28:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EIMJDG3EK3RDGBBXOKZYKY6VRU","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17641","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T16:11:05Z","cross_cats_sorted":["cs.AI","cs.CL","math.OC","stat.ML"],"title_canon_sha256":"cac9562ea3f4d7ff35b6126d6ec2c50870f1d6e41a8e750dd897f69bed11ede4","abstract_canon_sha256":"fd9ffca98171540ba110f76bd3d8b3721575c4f43407265de04fc498fbe4d434"},"schema_version":"1.0"},"canonical_sha256":"2218919b6456e233043772b38563d58d17c027e2fb5d90b02d83731406d43bdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:07.199674Z","signature_b64":"KbgDCS4ouShBCYasbX5yeRIUC1jy1rqBdLPFLnCWJHXJoH1d+o5XHiTDZDhzlz+X0Fr3aNaQOSBdhpO/yLLoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2218919b6456e233043772b38563d58d17c027e2fb5d90b02d83731406d43bdb","last_reissued_at":"2026-07-05T08:28:07.199181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:07.199181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17641","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":"2026-07-05T08:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jcr2Q93N8hYL5ZTWaWJBXnOg/IecERptykW940D/l7i5kWGlhsFqApLzM5KPuD8FoVvvworEqwz1Qo+/O0zxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:43:41.653114Z"},"content_sha256":"3126c40e64728baf04ff5f79908d28128f6a573982df64ae070d33b315da056a","schema_version":"1.0","event_id":"sha256:3126c40e64728baf04ff5f79908d28128f6a573982df64ae070d33b315da056a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EIMJDG3EK3RDGBBXOKZYKY6VRU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Learning is Effective for Large Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bai Cong, Clement Bazan, Daniel Cremers, Gian Maria Marconi, Iryna Gurevych, Mohammad Emtiyaz Khan, Nico Daheim, Peter Nickl, Rio Yokota, Thomas M\\\"ollenhoff, Yuesong Shen","submitted_at":"2024-02-27T16:11:05Z","abstract_excerpt":"We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for training large networks such as GPT-2 and ResNets from scratch. IVON's computational costs are nearly identical to Adam but its predictive uncertainty is better. We show several new use cases of IVON where we improve finetuning and model merging in Large Language Models, accurately predict generalization error, and faithfully estimate sensitivity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17641","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/2402.17641/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":"2026-07-05T08:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xS1ie9zzWJCicsDTiUt2h7tNl3q7z9PfzhOpKb1M8g2oknPc/kvImxj7u8Sw+ZjWYEb7/52nB1v5HoXwz0SRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:43:41.653457Z"},"content_sha256":"d07738662826f3d5d40a6d8d387e741baf7e30ee838fe41866f39f5f01e3ae14","schema_version":"1.0","event_id":"sha256:d07738662826f3d5d40a6d8d387e741baf7e30ee838fe41866f39f5f01e3ae14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU/bundle.json","state_url":"https://pith.science/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU/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":"2026-08-21T22:43:41Z","links":{"resolver":"https://pith.science/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU","bundle":"https://pith.science/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU/bundle.json","state":"https://pith.science/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIMJDG3EK3RDGBBXOKZYKY6VRU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EIMJDG3EK3RDGBBXOKZYKY6VRU","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":"fd9ffca98171540ba110f76bd3d8b3721575c4f43407265de04fc498fbe4d434","cross_cats_sorted":["cs.AI","cs.CL","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T16:11:05Z","title_canon_sha256":"cac9562ea3f4d7ff35b6126d6ec2c50870f1d6e41a8e750dd897f69bed11ede4"},"schema_version":"1.0","source":{"id":"2402.17641","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17641","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17641v2","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17641","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"EIMJDG3EK3RD","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"EIMJDG3EK3RDGBBX","created_at":"2026-07-05T08:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"EIMJDG3E","created_at":"2026-07-05T08:28:07Z"}],"graph_snapshots":[{"event_id":"sha256:d07738662826f3d5d40a6d8d387e741baf7e30ee838fe41866f39f5f01e3ae14","target":"graph","created_at":"2026-07-05T08:28:07Z","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/2402.17641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for training large networks such as GPT-2 and ResNets from scratch. IVON's computational costs are nearly identical to Adam but its predictive uncertainty is better. We show several new use cases of IVON where we improve finetuning and model merging in Large Language Models, accurately predict generalization error, and faithfully estimate sensitivity ","authors_text":"Bai Cong, Clement Bazan, Daniel Cremers, Gian Maria Marconi, Iryna Gurevych, Mohammad Emtiyaz Khan, Nico Daheim, Peter Nickl, Rio Yokota, Thomas M\\\"ollenhoff, Yuesong Shen","cross_cats":["cs.AI","cs.CL","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T16:11:05Z","title":"Variational Learning is Effective for Large Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17641","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":"sha256:3126c40e64728baf04ff5f79908d28128f6a573982df64ae070d33b315da056a","target":"record","created_at":"2026-07-05T08:28:07Z","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":"fd9ffca98171540ba110f76bd3d8b3721575c4f43407265de04fc498fbe4d434","cross_cats_sorted":["cs.AI","cs.CL","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T16:11:05Z","title_canon_sha256":"cac9562ea3f4d7ff35b6126d6ec2c50870f1d6e41a8e750dd897f69bed11ede4"},"schema_version":"1.0","source":{"id":"2402.17641","kind":"arxiv","version":2}},"canonical_sha256":"2218919b6456e233043772b38563d58d17c027e2fb5d90b02d83731406d43bdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2218919b6456e233043772b38563d58d17c027e2fb5d90b02d83731406d43bdb","first_computed_at":"2026-07-05T08:28:07.199181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:07.199181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KbgDCS4ouShBCYasbX5yeRIUC1jy1rqBdLPFLnCWJHXJoH1d+o5XHiTDZDhzlz+X0Fr3aNaQOSBdhpO/yLLoAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:07.199674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17641","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3126c40e64728baf04ff5f79908d28128f6a573982df64ae070d33b315da056a","sha256:d07738662826f3d5d40a6d8d387e741baf7e30ee838fe41866f39f5f01e3ae14"],"state_sha256":"d6df4f3fcbaab7f0e721a9cae0d074ccbc3cc9a940604afdebb10cf6613b9493"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQJgOuDz8XnYbN2/iteVtCzkCHkCPZmugqQb5LN7GXmfrvx8vW7eMHxDIDgAonpMdO9c+ocZFgEAJ8Slj3DWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:43:41.657681Z","bundle_sha256":"f6f964d9b1b87d2afaf292e27022474e678a40105b62523c112e94861546de87"}}