{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Y2HPKGJ4ZN4M32XKCR4VV7BZHD","short_pith_number":"pith:Y2HPKGJ4","canonical_record":{"source":{"id":"1902.02476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T05:15:46Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"7911fd6d4c7ae8e6b69ded30e9397ad8df0ac044020dd8e53b5c1bbae87a92ee","abstract_canon_sha256":"c473da09ba6eca40f0ee6e8c3493f504f08f56378c5c02f2eebf18da51e428c2"},"schema_version":"1.0"},"canonical_sha256":"c68ef5193ccb78cdeaea14795afc3938fe0dccc11d02bc2874451fd56d7b8bfd","source":{"kind":"arxiv","id":"1902.02476","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02476","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02476v2","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02476","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"Y2HPKGJ4ZN4M","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"Y2HPKGJ4ZN4M32XK","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"Y2HPKGJ4","created_at":"2026-07-05T00:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Y2HPKGJ4ZN4M32XKCR4VV7BZHD","target":"record","payload":{"canonical_record":{"source":{"id":"1902.02476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T05:15:46Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"7911fd6d4c7ae8e6b69ded30e9397ad8df0ac044020dd8e53b5c1bbae87a92ee","abstract_canon_sha256":"c473da09ba6eca40f0ee6e8c3493f504f08f56378c5c02f2eebf18da51e428c2"},"schema_version":"1.0"},"canonical_sha256":"c68ef5193ccb78cdeaea14795afc3938fe0dccc11d02bc2874451fd56d7b8bfd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:46.366280Z","signature_b64":"yIDKQOp9sEKBccI9dR49Pk+uBLV2q/Y4b6ZqYbOwf1zZAWhnjAsrUih9eMyj7NdVYkS2vM4yW95K/zUew+WmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c68ef5193ccb78cdeaea14795afc3938fe0dccc11d02bc2874451fd56d7b8bfd","last_reissued_at":"2026-07-05T00:28:46.365752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:46.365752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.02476","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":"2026-07-05T00:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8g8qfYM2Ch7uANRWtDPfcNL0YOtleiB97o2hPc+gB8rY2nZqp+Vm40mffENqLPqgUxCyiJ8kS2HW2gXVUdLLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:58:23.477737Z"},"content_sha256":"7516742ed1be854f917bc050a9373e1f6f75e10ea754084eda5a347389679974","schema_version":"1.0","event_id":"sha256:7516742ed1be854f917bc050a9373e1f6f75e10ea754084eda5a347389679974"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Y2HPKGJ4ZN4M32XKCR4VV7BZHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Dmitry Vetrov, Pavel Izmailov, Timur Garipov, Wesley Maddox","submitted_at":"2019-02-07T05:15:46Z","abstract_excerpt":"We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient descent (SGD) iterates with a modified learning rate schedule, has recently been shown to improve generalization in deep learning. With SWAG, we fit a Gaussian using the SWA solution as the first moment and a low rank plus diagonal covariance also derived from the SGD iterates, forming an approximate posterior distribution over neural network weights; we then sa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02476","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/1902.02476/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":"2026-07-05T00:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BlQqKrvbG69z9Ny4EREyBMUCP0NzrRBhrqfEXuBroL+tdsxsa6mAq5VT+n1tUH/erI8iGrjpxi5oh1dflAu1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:58:23.478078Z"},"content_sha256":"52393f1fca701508401d7c7ed4c933f7943935c5e1a69d91a720774f98f884de","schema_version":"1.0","event_id":"sha256:52393f1fca701508401d7c7ed4c933f7943935c5e1a69d91a720774f98f884de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD/bundle.json","state_url":"https://pith.science/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD/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":"2026-08-18T13:58:23Z","links":{"resolver":"https://pith.science/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD","bundle":"https://pith.science/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD/bundle.json","state":"https://pith.science/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2HPKGJ4ZN4M32XKCR4VV7BZHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Y2HPKGJ4ZN4M32XKCR4VV7BZHD","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":"c473da09ba6eca40f0ee6e8c3493f504f08f56378c5c02f2eebf18da51e428c2","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T05:15:46Z","title_canon_sha256":"7911fd6d4c7ae8e6b69ded30e9397ad8df0ac044020dd8e53b5c1bbae87a92ee"},"schema_version":"1.0","source":{"id":"1902.02476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02476","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02476v2","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02476","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"Y2HPKGJ4ZN4M","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"Y2HPKGJ4ZN4M32XK","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"Y2HPKGJ4","created_at":"2026-07-05T00:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:52393f1fca701508401d7c7ed4c933f7943935c5e1a69d91a720774f98f884de","target":"graph","created_at":"2026-07-05T00:28:46Z","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/1902.02476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient descent (SGD) iterates with a modified learning rate schedule, has recently been shown to improve generalization in deep learning. With SWAG, we fit a Gaussian using the SWA solution as the first moment and a low rank plus diagonal covariance also derived from the SGD iterates, forming an approximate posterior distribution over neural network weights; we then sa","authors_text":"Andrew Gordon Wilson, Dmitry Vetrov, Pavel Izmailov, Timur Garipov, Wesley Maddox","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T05:15:46Z","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02476","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":"sha256:7516742ed1be854f917bc050a9373e1f6f75e10ea754084eda5a347389679974","target":"record","created_at":"2026-07-05T00:28:46Z","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":"c473da09ba6eca40f0ee6e8c3493f504f08f56378c5c02f2eebf18da51e428c2","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T05:15:46Z","title_canon_sha256":"7911fd6d4c7ae8e6b69ded30e9397ad8df0ac044020dd8e53b5c1bbae87a92ee"},"schema_version":"1.0","source":{"id":"1902.02476","kind":"arxiv","version":2}},"canonical_sha256":"c68ef5193ccb78cdeaea14795afc3938fe0dccc11d02bc2874451fd56d7b8bfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c68ef5193ccb78cdeaea14795afc3938fe0dccc11d02bc2874451fd56d7b8bfd","first_computed_at":"2026-07-05T00:28:46.365752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:46.365752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yIDKQOp9sEKBccI9dR49Pk+uBLV2q/Y4b6ZqYbOwf1zZAWhnjAsrUih9eMyj7NdVYkS2vM4yW95K/zUew+WmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:46.366280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7516742ed1be854f917bc050a9373e1f6f75e10ea754084eda5a347389679974","sha256:52393f1fca701508401d7c7ed4c933f7943935c5e1a69d91a720774f98f884de"],"state_sha256":"ef3407aa1c467fc33f1fddf0517a9f59394b2ba40975dfac4df8bbf625dc7f24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQNjgU1IjQKK0cFj4v1RBlE7ckGeXC26XNhf7qBy4FKu0IrAAL9BCMdiUAZia2ZR5IMjtMVkD4nx/4gGuE+OAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:58:23.481955Z","bundle_sha256":"37f68b765e2140821d361280c13ec7a22ead7907c3d0aad8f5d3cc252bddeb45"}}