{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HNOTMUX4Z3MCZRA2C3I5L6HIFB","short_pith_number":"pith:HNOTMUX4","canonical_record":{"source":{"id":"2104.09240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T12:26:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a29ab215cb8a9ae34335d32eb27e6abd13a5f106a0d8e8d6dc80ce0aaf78656","abstract_canon_sha256":"b484608b27b4afc3ef628a9309d1d5222b3f12b2845d24923a2b8caae44d45a8"},"schema_version":"1.0"},"canonical_sha256":"3b5d3652fcced82cc41a16d1d5f8e8286f158f4b1e92d35764858cefd694a0db","source":{"kind":"arxiv","id":"2104.09240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09240","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09240v1","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09240","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"HNOTMUX4Z3MC","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"HNOTMUX4Z3MCZRA2","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"HNOTMUX4","created_at":"2026-07-05T02:33:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HNOTMUX4Z3MCZRA2C3I5L6HIFB","target":"record","payload":{"canonical_record":{"source":{"id":"2104.09240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T12:26:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a29ab215cb8a9ae34335d32eb27e6abd13a5f106a0d8e8d6dc80ce0aaf78656","abstract_canon_sha256":"b484608b27b4afc3ef628a9309d1d5222b3f12b2845d24923a2b8caae44d45a8"},"schema_version":"1.0"},"canonical_sha256":"3b5d3652fcced82cc41a16d1d5f8e8286f158f4b1e92d35764858cefd694a0db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:11.026608Z","signature_b64":"tlqxOf2//ZX1e8W2G3DeiqFeZArWI44iiLjw1v0WmGeN6Fs+MfvNvGUd6KCiTmTHUl5Ig1tJmdkYhwhxEkEJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5d3652fcced82cc41a16d1d5f8e8286f158f4b1e92d35764858cefd694a0db","last_reissued_at":"2026-07-05T02:33:11.026161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:11.026161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.09240","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":"2026-07-05T02:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LsWYsL/HVSJL/ITN3Jm6m03dxWSVUY/8P1eUm8yCTXUx2rkAWB2cSmkRWCQr4hPamfgIDwkSBxvsAj+UMw5yDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:53:49.572508Z"},"content_sha256":"fa56482771f88255f0f55146a782ae873adf93732c9d57210950fee2822c2e6b","schema_version":"1.0","event_id":"sha256:fa56482771f88255f0f55146a782ae873adf93732c9d57210950fee2822c2e6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HNOTMUX4Z3MCZRA2C3I5L6HIFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Learning with Fully Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Gepperth, Benedikt Bagus, Benedikt Pf\\\"ulb","submitted_at":"2021-04-19T12:26:26Z","abstract_excerpt":"We present an approach for continual learning (CL) that is based on fully probabilistic (or generative) models of machine learning. In contrast to, e.g., GANs that are \"generative\" in the sense that they can generate samples, fully probabilistic models aim at modeling the data distribution directly. Consequently, they provide functionalities that are highly relevant for continual learning, such as density estimation (outlier detection) and sample generation. As a concrete realization of generative continual learning, we propose Gaussian Mixture Replay (GMR). GMR is a pseudo-rehearsal approach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09240","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.09240/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":"2026-07-05T02:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/Edwr9nhQt6qHvugDd0oTg0LvVF/cCAZVY9Fasipc83b+8IqJtcyy75jAd+YQ3yhv8i4G9XxYoc92lvk/FACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:53:49.573019Z"},"content_sha256":"e33a16abd172d70aa94b32349b1a490d910fc93f254ba88bf98e59f9370077fa","schema_version":"1.0","event_id":"sha256:e33a16abd172d70aa94b32349b1a490d910fc93f254ba88bf98e59f9370077fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB/bundle.json","state_url":"https://pith.science/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB/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":"2026-08-07T10:53:49Z","links":{"resolver":"https://pith.science/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB","bundle":"https://pith.science/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB/bundle.json","state":"https://pith.science/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HNOTMUX4Z3MCZRA2C3I5L6HIFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HNOTMUX4Z3MCZRA2C3I5L6HIFB","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":"b484608b27b4afc3ef628a9309d1d5222b3f12b2845d24923a2b8caae44d45a8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T12:26:26Z","title_canon_sha256":"4a29ab215cb8a9ae34335d32eb27e6abd13a5f106a0d8e8d6dc80ce0aaf78656"},"schema_version":"1.0","source":{"id":"2104.09240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09240","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09240v1","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09240","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"HNOTMUX4Z3MC","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"HNOTMUX4Z3MCZRA2","created_at":"2026-07-05T02:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"HNOTMUX4","created_at":"2026-07-05T02:33:11Z"}],"graph_snapshots":[{"event_id":"sha256:e33a16abd172d70aa94b32349b1a490d910fc93f254ba88bf98e59f9370077fa","target":"graph","created_at":"2026-07-05T02:33:11Z","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/2104.09240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an approach for continual learning (CL) that is based on fully probabilistic (or generative) models of machine learning. In contrast to, e.g., GANs that are \"generative\" in the sense that they can generate samples, fully probabilistic models aim at modeling the data distribution directly. Consequently, they provide functionalities that are highly relevant for continual learning, such as density estimation (outlier detection) and sample generation. As a concrete realization of generative continual learning, we propose Gaussian Mixture Replay (GMR). GMR is a pseudo-rehearsal approach ","authors_text":"Alexander Gepperth, Benedikt Bagus, Benedikt Pf\\\"ulb","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T12:26:26Z","title":"Continual Learning with Fully Probabilistic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09240","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:fa56482771f88255f0f55146a782ae873adf93732c9d57210950fee2822c2e6b","target":"record","created_at":"2026-07-05T02:33:11Z","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":"b484608b27b4afc3ef628a9309d1d5222b3f12b2845d24923a2b8caae44d45a8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T12:26:26Z","title_canon_sha256":"4a29ab215cb8a9ae34335d32eb27e6abd13a5f106a0d8e8d6dc80ce0aaf78656"},"schema_version":"1.0","source":{"id":"2104.09240","kind":"arxiv","version":1}},"canonical_sha256":"3b5d3652fcced82cc41a16d1d5f8e8286f158f4b1e92d35764858cefd694a0db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b5d3652fcced82cc41a16d1d5f8e8286f158f4b1e92d35764858cefd694a0db","first_computed_at":"2026-07-05T02:33:11.026161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:11.026161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tlqxOf2//ZX1e8W2G3DeiqFeZArWI44iiLjw1v0WmGeN6Fs+MfvNvGUd6KCiTmTHUl5Ig1tJmdkYhwhxEkEJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:11.026608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa56482771f88255f0f55146a782ae873adf93732c9d57210950fee2822c2e6b","sha256:e33a16abd172d70aa94b32349b1a490d910fc93f254ba88bf98e59f9370077fa"],"state_sha256":"836896f5405b0e761f6b8dbfe3bb5c807a25b2a6ee6e835778fca5631d1a8679"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RaiJX4DrhczFm77o8gw5uXcAvBKPysYlCwbXz3XTjA6iq7bVe4X1TiTJAaGUEmVr7LK/e+nOXBXNftA5lQqLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:53:49.578697Z","bundle_sha256":"d820578c690594cdd851771f198b4be6e87145d812c1f99c5ffcb095925833ca"}}