{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2YEZWNAS5MHGWCBU6ZOTKMNV32","short_pith_number":"pith:2YEZWNAS","canonical_record":{"source":{"id":"1712.01169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T16:02:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fef0241160a752cb5c3758f918ce7dc722b8d422610208d1355db55b96628d15","abstract_canon_sha256":"3cf7185938e96727c647f96cb1dda70af39597b921e711016fc959b4d9c159d0"},"schema_version":"1.0"},"canonical_sha256":"d6099b3412eb0e6b0834f65d3531b5deb90505141fc156cc05c35ba001ea52a2","source":{"kind":"arxiv","id":"1712.01169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01169","created_at":"2026-05-18T00:28:57Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01169v1","created_at":"2026-05-18T00:28:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01169","created_at":"2026-05-18T00:28:57Z"},{"alias_kind":"pith_short_12","alias_value":"2YEZWNAS5MHG","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2YEZWNAS5MHGWCBU","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2YEZWNAS","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2YEZWNAS5MHGWCBU6ZOTKMNV32","target":"record","payload":{"canonical_record":{"source":{"id":"1712.01169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T16:02:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fef0241160a752cb5c3758f918ce7dc722b8d422610208d1355db55b96628d15","abstract_canon_sha256":"3cf7185938e96727c647f96cb1dda70af39597b921e711016fc959b4d9c159d0"},"schema_version":"1.0"},"canonical_sha256":"d6099b3412eb0e6b0834f65d3531b5deb90505141fc156cc05c35ba001ea52a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:57.737874Z","signature_b64":"pYfJUg4ze4SjBlJWzYkX+D1DvMu4YHUD/8eSfNQ6JBZ6TISEsV3o8GcEjYKR7/p4vNHT/JlpKlnFjhzf/pteDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6099b3412eb0e6b0834f65d3531b5deb90505141fc156cc05c35ba001ea52a2","last_reissued_at":"2026-05-18T00:28:57.737360Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:57.737360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.01169","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":"2026-05-18T00:28:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KizLHRwwYm1jR5PhUq7ersC+V17nzhmq47xpxa/5WmHmjIGgJYu1lxI/YMWBtED8Fibs5hh9UB5DqET6Ua+ZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T13:38:13.299522Z"},"content_sha256":"84a2a630d5f2bd70081489e8c2e72aeb60d99a29f73dad345ccdd24bc01031d5","schema_version":"1.0","event_id":"sha256:84a2a630d5f2bd70081489e8c2e72aeb60d99a29f73dad345ccdd24bc01031d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2YEZWNAS5MHGWCBU6ZOTKMNV32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Episodic memory for continual model learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David G. Nagy, Gerg\\H{o} Orb\\'an","submitted_at":"2017-12-04T16:02:36Z","abstract_excerpt":"Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the same posterior for both off-line (i.e. batch) and online learning. However, maintaining a parameter posterior for each model in parallel has in general an even higher memory cost than storing the entire data set and is consequently clearly unfeasible. Alternatively, maintaining only"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01169","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":"2026-05-18T00:28:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GH5Xk17JgHjYe52evrQbZQZJeTWeq3dTu+z6Tm7yBCPA6HEql0OXWLuj1q0agPrbFMyfSJ6bO0VUAGLBDv3SAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T13:38:13.299868Z"},"content_sha256":"4b00a1c686b7df524de3cad0c8604f76c339a9a42619e830037376178e98215b","schema_version":"1.0","event_id":"sha256:4b00a1c686b7df524de3cad0c8604f76c339a9a42619e830037376178e98215b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32/bundle.json","state_url":"https://pith.science/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32/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":"2026-07-04T13:38:13Z","links":{"resolver":"https://pith.science/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32","bundle":"https://pith.science/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32/bundle.json","state":"https://pith.science/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YEZWNAS5MHGWCBU6ZOTKMNV32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2YEZWNAS5MHGWCBU6ZOTKMNV32","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":"3cf7185938e96727c647f96cb1dda70af39597b921e711016fc959b4d9c159d0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T16:02:36Z","title_canon_sha256":"fef0241160a752cb5c3758f918ce7dc722b8d422610208d1355db55b96628d15"},"schema_version":"1.0","source":{"id":"1712.01169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01169","created_at":"2026-05-18T00:28:57Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01169v1","created_at":"2026-05-18T00:28:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01169","created_at":"2026-05-18T00:28:57Z"},{"alias_kind":"pith_short_12","alias_value":"2YEZWNAS5MHG","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2YEZWNAS5MHGWCBU","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2YEZWNAS","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:4b00a1c686b7df524de3cad0c8604f76c339a9a42619e830037376178e98215b","target":"graph","created_at":"2026-05-18T00:28:57Z","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":"Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the same posterior for both off-line (i.e. batch) and online learning. However, maintaining a parameter posterior for each model in parallel has in general an even higher memory cost than storing the entire data set and is consequently clearly unfeasible. Alternatively, maintaining only","authors_text":"David G. Nagy, Gerg\\H{o} Orb\\'an","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T16:02:36Z","title":"Episodic memory for continual model learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01169","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":"sha256:84a2a630d5f2bd70081489e8c2e72aeb60d99a29f73dad345ccdd24bc01031d5","target":"record","created_at":"2026-05-18T00:28:57Z","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":"3cf7185938e96727c647f96cb1dda70af39597b921e711016fc959b4d9c159d0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T16:02:36Z","title_canon_sha256":"fef0241160a752cb5c3758f918ce7dc722b8d422610208d1355db55b96628d15"},"schema_version":"1.0","source":{"id":"1712.01169","kind":"arxiv","version":1}},"canonical_sha256":"d6099b3412eb0e6b0834f65d3531b5deb90505141fc156cc05c35ba001ea52a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6099b3412eb0e6b0834f65d3531b5deb90505141fc156cc05c35ba001ea52a2","first_computed_at":"2026-05-18T00:28:57.737360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:57.737360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pYfJUg4ze4SjBlJWzYkX+D1DvMu4YHUD/8eSfNQ6JBZ6TISEsV3o8GcEjYKR7/p4vNHT/JlpKlnFjhzf/pteDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:57.737874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.01169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84a2a630d5f2bd70081489e8c2e72aeb60d99a29f73dad345ccdd24bc01031d5","sha256:4b00a1c686b7df524de3cad0c8604f76c339a9a42619e830037376178e98215b"],"state_sha256":"bf8578637decff7aa88a89577b6dd28178752d956b0a92eeb461d93bd669f880"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IY0cDG2OxdErLvTgj895U/9Ya1ah6+lWaFzMT9AswqBHzpF/1/zACV9DEqoKQPxlmha3Yt3z19hNm3Btcbr8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T13:38:13.301871Z","bundle_sha256":"d1ea2e2c0f58ebdba1335353b36ca6cea6f69e61b14d9450c60f3f0204277022"}}