{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MPT5TJBLAKMTOWV47EIBEMVA2D","short_pith_number":"pith:MPT5TJBL","canonical_record":{"source":{"id":"1904.10644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T05:18:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7a1effb875d18763ec1700d684ec4546006f5da18d8dbe0461104dde17c32fd8","abstract_canon_sha256":"a7b8d41235805688487ce9c84b7439bfb30a378b25863980797813f1adfbeccc"},"schema_version":"1.0"},"canonical_sha256":"63e7d9a42b0299375abcf9101232a0d0df3e04f28f3f9b5675249cf1830fe295","source":{"kind":"arxiv","id":"1904.10644","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10644","created_at":"2026-05-17T23:47:53Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10644v1","created_at":"2026-05-17T23:47:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10644","created_at":"2026-05-17T23:47:53Z"},{"alias_kind":"pith_short_12","alias_value":"MPT5TJBLAKMT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MPT5TJBLAKMTOWV4","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MPT5TJBL","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MPT5TJBLAKMTOWV47EIBEMVA2D","target":"record","payload":{"canonical_record":{"source":{"id":"1904.10644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T05:18:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7a1effb875d18763ec1700d684ec4546006f5da18d8dbe0461104dde17c32fd8","abstract_canon_sha256":"a7b8d41235805688487ce9c84b7439bfb30a378b25863980797813f1adfbeccc"},"schema_version":"1.0"},"canonical_sha256":"63e7d9a42b0299375abcf9101232a0d0df3e04f28f3f9b5675249cf1830fe295","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:53.140911Z","signature_b64":"WOat6/Yd8OStGH28KFfwPFCXielP4vyDaY2XNqmaR64yaB7DU0Y1cCjqqUMxmr57BTgcsBAovMW2YngwYWkOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63e7d9a42b0299375abcf9101232a0d0df3e04f28f3f9b5675249cf1830fe295","last_reissued_at":"2026-05-17T23:47:53.140505Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:53.140505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.10644","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DL0ZjN8qTBypUyNSUkQMfCThECqZj3f4rsLubM6CqELo4Ac3yPQ1wqFgAy0fDAYxrNlYpn+fbK6L1wL8zatQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:22:06.333141Z"},"content_sha256":"58459fb32d88dc3ac99c38cc701a2cc1c3ba3bd347b66944aa5817fb0a2f9be2","schema_version":"1.0","event_id":"sha256:58459fb32d88dc3ac99c38cc701a2cc1c3ba3bd347b66944aa5817fb0a2f9be2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MPT5TJBLAKMTOWV47EIBEMVA2D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Neil Lawrence, Tom Diethe, Yu Chen","submitted_at":"2019-04-24T05:18:32Z","abstract_excerpt":"Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting. When using Bayesian models in continual learning, knowledge from previous tasks can be retained in two ways: 1). posterior distributions over the parameters, containing the knowledge gained from inference in previous tasks, which then serve as the priors for the following task; 2). coresets, containing knowledge of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10644","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:47:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"av012g4t9fAzmsBWEXpqOtTGdwL/53B8Uj5i2wmutJghAoMMZjkcOtBm0rfH+ZbNXEbrtYMh8//3TRRsqqxQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:22:06.333512Z"},"content_sha256":"99ed1ddcaedab2877da8df422cda3daa402c46714ad4d9787fb64fa3a2ea66fd","schema_version":"1.0","event_id":"sha256:99ed1ddcaedab2877da8df422cda3daa402c46714ad4d9787fb64fa3a2ea66fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPT5TJBLAKMTOWV47EIBEMVA2D/bundle.json","state_url":"https://pith.science/pith/MPT5TJBLAKMTOWV47EIBEMVA2D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPT5TJBLAKMTOWV47EIBEMVA2D/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":"2026-06-01T05:22:06Z","links":{"resolver":"https://pith.science/pith/MPT5TJBLAKMTOWV47EIBEMVA2D","bundle":"https://pith.science/pith/MPT5TJBLAKMTOWV47EIBEMVA2D/bundle.json","state":"https://pith.science/pith/MPT5TJBLAKMTOWV47EIBEMVA2D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPT5TJBLAKMTOWV47EIBEMVA2D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MPT5TJBLAKMTOWV47EIBEMVA2D","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":"a7b8d41235805688487ce9c84b7439bfb30a378b25863980797813f1adfbeccc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T05:18:32Z","title_canon_sha256":"7a1effb875d18763ec1700d684ec4546006f5da18d8dbe0461104dde17c32fd8"},"schema_version":"1.0","source":{"id":"1904.10644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10644","created_at":"2026-05-17T23:47:53Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10644v1","created_at":"2026-05-17T23:47:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10644","created_at":"2026-05-17T23:47:53Z"},{"alias_kind":"pith_short_12","alias_value":"MPT5TJBLAKMT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MPT5TJBLAKMTOWV4","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MPT5TJBL","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:99ed1ddcaedab2877da8df422cda3daa402c46714ad4d9787fb64fa3a2ea66fd","target":"graph","created_at":"2026-05-17T23:47:53Z","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"},"paper":{"abstract_excerpt":"Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting. When using Bayesian models in continual learning, knowledge from previous tasks can be retained in two ways: 1). posterior distributions over the parameters, containing the knowledge gained from inference in previous tasks, which then serve as the priors for the following task; 2). coresets, containing knowledge of ","authors_text":"Neil Lawrence, Tom Diethe, Yu Chen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T05:18:32Z","title":"Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10644","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":"sha256:58459fb32d88dc3ac99c38cc701a2cc1c3ba3bd347b66944aa5817fb0a2f9be2","target":"record","created_at":"2026-05-17T23:47:53Z","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":"a7b8d41235805688487ce9c84b7439bfb30a378b25863980797813f1adfbeccc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T05:18:32Z","title_canon_sha256":"7a1effb875d18763ec1700d684ec4546006f5da18d8dbe0461104dde17c32fd8"},"schema_version":"1.0","source":{"id":"1904.10644","kind":"arxiv","version":1}},"canonical_sha256":"63e7d9a42b0299375abcf9101232a0d0df3e04f28f3f9b5675249cf1830fe295","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63e7d9a42b0299375abcf9101232a0d0df3e04f28f3f9b5675249cf1830fe295","first_computed_at":"2026-05-17T23:47:53.140505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:53.140505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WOat6/Yd8OStGH28KFfwPFCXielP4vyDaY2XNqmaR64yaB7DU0Y1cCjqqUMxmr57BTgcsBAovMW2YngwYWkOAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:53.140911Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.10644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58459fb32d88dc3ac99c38cc701a2cc1c3ba3bd347b66944aa5817fb0a2f9be2","sha256:99ed1ddcaedab2877da8df422cda3daa402c46714ad4d9787fb64fa3a2ea66fd"],"state_sha256":"186ce0dc0373c81d5d0530da3a809d76056faaabc371ce86d8af755f5aafee61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHmAheM8SX5BZNs4MJUFMkrOa2bUaVzGhuAC4KCVN0ltByUwvoJxw2/RJu81YKiVPjj8dNOU7F6R3j4qDqBHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:22:06.335745Z","bundle_sha256":"9e387a76f827dc1c3fa42b4adb95853e626aaf01b171f2d3e2efdf43478cee5b"}}