{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2TDMSFZMKLUFUAB35WQ73OXEKS","short_pith_number":"pith:2TDMSFZM","canonical_record":{"source":{"id":"1802.07329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-20T21:11:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fdd01cf77f1413127c81cf49a0a6c330cc0e7c40ad1c1fc9f866e09fe28d790","abstract_canon_sha256":"1fcbd83e2af9021950d7b87f9f8e265e5252ad5550fb2ffe62a67e3a90d7bfec"},"schema_version":"1.0"},"canonical_sha256":"d4c6c9172c52e85a003beda1fdbae45484bc68c2aa9a00b77e15c49f82c67063","source":{"kind":"arxiv","id":"1802.07329","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07329","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07329v3","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07329","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"2TDMSFZMKLUF","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2TDMSFZMKLUFUAB3","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2TDMSFZM","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2TDMSFZMKLUFUAB35WQ73OXEKS","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-20T21:11:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fdd01cf77f1413127c81cf49a0a6c330cc0e7c40ad1c1fc9f866e09fe28d790","abstract_canon_sha256":"1fcbd83e2af9021950d7b87f9f8e265e5252ad5550fb2ffe62a67e3a90d7bfec"},"schema_version":"1.0"},"canonical_sha256":"d4c6c9172c52e85a003beda1fdbae45484bc68c2aa9a00b77e15c49f82c67063","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:56.349188Z","signature_b64":"NjVSIayyyx+iKxj1aK3tddeiTY78PyRO3oP/cOoAJJUdwOL1+FBwmNxuzO/uvGMTCF2ztNXvBE/nwQ9odLlNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4c6c9172c52e85a003beda1fdbae45484bc68c2aa9a00b77e15c49f82c67063","last_reissued_at":"2026-05-18T00:19:56.348362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:56.348362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07329","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DEAatqxZ8Z+4didiOVXPVOL7AMMW5rh0Kah5U2ihKT8eg5hxGN7mG3IQmMwoj/Kxvl96Ms4JJlKDDxePGNSeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:32:29.538393Z"},"content_sha256":"3d67d1f2eec8762cbcbcd0dd87bdce7c034ed52def4980cfe9d2e7aed1b215cf","schema_version":"1.0","event_id":"sha256:3d67d1f2eec8762cbcbcd0dd87bdce7c034ed52def4980cfe9d2e7aed1b215cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2TDMSFZMKLUFUAB35WQ73OXEKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Incremental Learning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Podoprikhin, Dmitry Vetrov, Max Kochurov, Timur Garipov","submitted_at":"2018-02-20T21:11:17Z","abstract_excerpt":"In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each time, so one would rather use a previously learned model and the new data to improve performance. However, deep neural networks are prone to getting stuck in a suboptimal solution when trained on only new data as compared to the full dataset. Our work focuses on a continuous learning setup where the task is always the same and new parts of data arrive sequentially. We apply a Bayesian approach to update the posterio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07329","kind":"arxiv","version":3},"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":"2026-05-18T00:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvwoYewhQmAKz+6M70U1kZNkc2q88uO+sQ0a0B73c7LvyYpXiFeSrpUw4XiFqqRMTrV01wOfgsZm23Q4PKzAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:32:29.538746Z"},"content_sha256":"4ccfd470d70d7ad71d1c9578559fc1f49bf8ffbad9a03b6e020acaff6ef14b89","schema_version":"1.0","event_id":"sha256:4ccfd470d70d7ad71d1c9578559fc1f49bf8ffbad9a03b6e020acaff6ef14b89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TDMSFZMKLUFUAB35WQ73OXEKS/bundle.json","state_url":"https://pith.science/pith/2TDMSFZMKLUFUAB35WQ73OXEKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TDMSFZMKLUFUAB35WQ73OXEKS/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":"2026-06-01T15:32:29Z","links":{"resolver":"https://pith.science/pith/2TDMSFZMKLUFUAB35WQ73OXEKS","bundle":"https://pith.science/pith/2TDMSFZMKLUFUAB35WQ73OXEKS/bundle.json","state":"https://pith.science/pith/2TDMSFZMKLUFUAB35WQ73OXEKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TDMSFZMKLUFUAB35WQ73OXEKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2TDMSFZMKLUFUAB35WQ73OXEKS","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":"1fcbd83e2af9021950d7b87f9f8e265e5252ad5550fb2ffe62a67e3a90d7bfec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-20T21:11:17Z","title_canon_sha256":"3fdd01cf77f1413127c81cf49a0a6c330cc0e7c40ad1c1fc9f866e09fe28d790"},"schema_version":"1.0","source":{"id":"1802.07329","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07329","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07329v3","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07329","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"2TDMSFZMKLUF","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2TDMSFZMKLUFUAB3","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2TDMSFZM","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:4ccfd470d70d7ad71d1c9578559fc1f49bf8ffbad9a03b6e020acaff6ef14b89","target":"graph","created_at":"2026-05-18T00:19:56Z","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":"In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each time, so one would rather use a previously learned model and the new data to improve performance. However, deep neural networks are prone to getting stuck in a suboptimal solution when trained on only new data as compared to the full dataset. Our work focuses on a continuous learning setup where the task is always the same and new parts of data arrive sequentially. We apply a Bayesian approach to update the posterio","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Podoprikhin, Dmitry Vetrov, Max Kochurov, Timur Garipov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-20T21:11:17Z","title":"Bayesian Incremental Learning for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07329","kind":"arxiv","version":3},"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":"sha256:3d67d1f2eec8762cbcbcd0dd87bdce7c034ed52def4980cfe9d2e7aed1b215cf","target":"record","created_at":"2026-05-18T00:19:56Z","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":"1fcbd83e2af9021950d7b87f9f8e265e5252ad5550fb2ffe62a67e3a90d7bfec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-20T21:11:17Z","title_canon_sha256":"3fdd01cf77f1413127c81cf49a0a6c330cc0e7c40ad1c1fc9f866e09fe28d790"},"schema_version":"1.0","source":{"id":"1802.07329","kind":"arxiv","version":3}},"canonical_sha256":"d4c6c9172c52e85a003beda1fdbae45484bc68c2aa9a00b77e15c49f82c67063","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4c6c9172c52e85a003beda1fdbae45484bc68c2aa9a00b77e15c49f82c67063","first_computed_at":"2026-05-18T00:19:56.348362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:56.348362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NjVSIayyyx+iKxj1aK3tddeiTY78PyRO3oP/cOoAJJUdwOL1+FBwmNxuzO/uvGMTCF2ztNXvBE/nwQ9odLlNCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:56.349188Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07329","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d67d1f2eec8762cbcbcd0dd87bdce7c034ed52def4980cfe9d2e7aed1b215cf","sha256:4ccfd470d70d7ad71d1c9578559fc1f49bf8ffbad9a03b6e020acaff6ef14b89"],"state_sha256":"6e0fb6710ba123555f0b377b905da937605c6a00a67ef2ee2d81e61303956a56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CcJB4FV5jOj4ZSMjXdxPVnjLQP0uGt8Y3XRqfOxSysAqFPKqJMYcg0y317uXext8QM7+hkaoo9crNl6+KMr6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T15:32:29.540789Z","bundle_sha256":"a35c12f00830ba9e2af982fff5e522123bd3a92cca2c1fbfefd1e0545e3b91e0"}}