{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XUYN2KRVUQYPOO4OZZXGKPA3HM","short_pith_number":"pith:XUYN2KRV","canonical_record":{"source":{"id":"1810.11910","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T00:13:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1d03e3aee03af7475008f1ec7ba3cf37606b4ef74f2a10f1fd0a19fc49aa6cac","abstract_canon_sha256":"a920f6006eb329e7ada705dfa9c5fc0c991d1dcde088ae436c54b43fb0617780"},"schema_version":"1.0"},"canonical_sha256":"bd30dd2a35a430f73b8ece6e653c1b3b2b0435f7a2523e62c49462abb3ff4279","source":{"kind":"arxiv","id":"1810.11910","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11910","created_at":"2026-05-17T23:47:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11910v3","created_at":"2026-05-17T23:47:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11910","created_at":"2026-05-17T23:47:08Z"},{"alias_kind":"pith_short_12","alias_value":"XUYN2KRVUQYP","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XUYN2KRVUQYPOO4O","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XUYN2KRV","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XUYN2KRVUQYPOO4OZZXGKPA3HM","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11910","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T00:13:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1d03e3aee03af7475008f1ec7ba3cf37606b4ef74f2a10f1fd0a19fc49aa6cac","abstract_canon_sha256":"a920f6006eb329e7ada705dfa9c5fc0c991d1dcde088ae436c54b43fb0617780"},"schema_version":"1.0"},"canonical_sha256":"bd30dd2a35a430f73b8ece6e653c1b3b2b0435f7a2523e62c49462abb3ff4279","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:08.605656Z","signature_b64":"cWZqCNykVkS0J6AQUcyfUwMuduLTFOVfbxDegAT7tzUbokoGSFl3ZKdAQZhcClxJyy1ZAKCEULhpYMGMyf+ZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd30dd2a35a430f73b8ece6e653c1b3b2b0435f7a2523e62c49462abb3ff4279","last_reissued_at":"2026-05-17T23:47:08.605126Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:08.605126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11910","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":"2026-05-17T23:47:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Qh5OrQkp77txhzS0smR3Z/IHGcDtglJO9pLC+SZJq8fzf+YFtm//9MHvvUi2tBIc2AsfT5v5LUp2oqW8CvUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:14:54.450584Z"},"content_sha256":"4b66d3aff602c7ee8f4a1b3bdd6d0918ee30a06cb61450f10cf53c5c548cbb10","schema_version":"1.0","event_id":"sha256:4b66d3aff602c7ee8f4a1b3bdd6d0918ee30a06cb61450f10cf53c5c548cbb10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XUYN2KRVUQYPOO4OZZXGKPA3HM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gerald Tesauro, Ignacio Cases, Irina Rish, Matthew Riemer, Miao Liu, Robert Ajemian, Yuhai Tu","submitted_at":"2018-10-29T00:13:50Z","abstract_excerpt":"Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11910","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":"2026-05-17T23:47:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ck+317mBrS5xJzbuPQlt3mWB9HnUDlA5rl6BCLiFn6aBk3cv0+tbgLhwHk/Nib2fRjlzBhkjdNu9Q6LOBj/zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:14:54.451233Z"},"content_sha256":"5c20f3e2224fbdd05c6491283cef9092b167878a34396ec1cdf5a446008e274f","schema_version":"1.0","event_id":"sha256:5c20f3e2224fbdd05c6491283cef9092b167878a34396ec1cdf5a446008e274f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM/bundle.json","state_url":"https://pith.science/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM/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":"2026-05-27T05:14:54Z","links":{"resolver":"https://pith.science/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM","bundle":"https://pith.science/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM/bundle.json","state":"https://pith.science/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUYN2KRVUQYPOO4OZZXGKPA3HM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XUYN2KRVUQYPOO4OZZXGKPA3HM","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":"a920f6006eb329e7ada705dfa9c5fc0c991d1dcde088ae436c54b43fb0617780","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T00:13:50Z","title_canon_sha256":"1d03e3aee03af7475008f1ec7ba3cf37606b4ef74f2a10f1fd0a19fc49aa6cac"},"schema_version":"1.0","source":{"id":"1810.11910","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11910","created_at":"2026-05-17T23:47:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11910v3","created_at":"2026-05-17T23:47:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11910","created_at":"2026-05-17T23:47:08Z"},{"alias_kind":"pith_short_12","alias_value":"XUYN2KRVUQYP","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XUYN2KRVUQYPOO4O","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XUYN2KRV","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:5c20f3e2224fbdd05c6491283cef9092b167878a34396ec1cdf5a446008e274f","target":"graph","created_at":"2026-05-17T23:47:08Z","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":"Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This meth","authors_text":"Gerald Tesauro, Ignacio Cases, Irina Rish, Matthew Riemer, Miao Liu, Robert Ajemian, Yuhai Tu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T00:13:50Z","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11910","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":"sha256:4b66d3aff602c7ee8f4a1b3bdd6d0918ee30a06cb61450f10cf53c5c548cbb10","target":"record","created_at":"2026-05-17T23:47:08Z","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":"a920f6006eb329e7ada705dfa9c5fc0c991d1dcde088ae436c54b43fb0617780","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T00:13:50Z","title_canon_sha256":"1d03e3aee03af7475008f1ec7ba3cf37606b4ef74f2a10f1fd0a19fc49aa6cac"},"schema_version":"1.0","source":{"id":"1810.11910","kind":"arxiv","version":3}},"canonical_sha256":"bd30dd2a35a430f73b8ece6e653c1b3b2b0435f7a2523e62c49462abb3ff4279","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd30dd2a35a430f73b8ece6e653c1b3b2b0435f7a2523e62c49462abb3ff4279","first_computed_at":"2026-05-17T23:47:08.605126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:08.605126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cWZqCNykVkS0J6AQUcyfUwMuduLTFOVfbxDegAT7tzUbokoGSFl3ZKdAQZhcClxJyy1ZAKCEULhpYMGMyf+ZCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:08.605656Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11910","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b66d3aff602c7ee8f4a1b3bdd6d0918ee30a06cb61450f10cf53c5c548cbb10","sha256:5c20f3e2224fbdd05c6491283cef9092b167878a34396ec1cdf5a446008e274f"],"state_sha256":"9a62d91a5af58945b0418b3447888c768026752cb75ef974a9aa73f03bc62db6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOKaxfDTC+6+ZAYikb9h7QdgcN+96J3P3rNDx35uKLSrdOB19+NkgYDzjiO79xo7QnKQzivJBhUq03lMbBzcDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:14:54.454418Z","bundle_sha256":"fc0ecc05e373dcc4e4a32aadebcf452dd140240faa314b4876290e89c63fc799"}}