{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZK74M3OZ5KXSL3TUUNLPX3KKT6","short_pith_number":"pith:ZK74M3OZ","canonical_record":{"source":{"id":"1810.03880","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T09:42:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"40fe0dd34bf7a35a76f579b0961d4b7deecbea050296bdab8e6e15e3950b0140","abstract_canon_sha256":"bba134b9ae428522cfe24651b310612ef7d5b8858a27d7e59bce1401b901e9fc"},"schema_version":"1.0"},"canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","source":{"kind":"arxiv","id":"1810.03880","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03880","created_at":"2026-05-17T23:58:37Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03880v3","created_at":"2026-05-17T23:58:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03880","created_at":"2026-05-17T23:58:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZK74M3OZ5KXS","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZK74M3OZ5KXSL3TU","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZK74M3OZ","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZK74M3OZ5KXSL3TUUNLPX3KKT6","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03880","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T09:42:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"40fe0dd34bf7a35a76f579b0961d4b7deecbea050296bdab8e6e15e3950b0140","abstract_canon_sha256":"bba134b9ae428522cfe24651b310612ef7d5b8858a27d7e59bce1401b901e9fc"},"schema_version":"1.0"},"canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:37.265174Z","signature_b64":"Z2aveAxN7XLpjaG/W+InGERjt4tJh4mEOKUaF6O5ZEMcub/t4mf8F0EkpFTL/oVU68ZbcoTJ43ZnckEE5x5uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","last_reissued_at":"2026-05-17T23:58:37.264535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:37.264535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03880","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":"2026-05-17T23:58:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6Pc0rVRBOcru43SahE8t54weBYIvz+WmyAez4DoOXQESCEN/dmQZNgixrONbJayNTmLrEVgZURhwa8+J9VYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:56:09.555113Z"},"content_sha256":"c4a5e8ffd5591372470e08da478cdf253a9173365fd0d80f4b5ff446e346aed2","schema_version":"1.0","event_id":"sha256:c4a5e8ffd5591372470e08da478cdf253a9173365fd0d80f4b5ff446e346aed2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZK74M3OZ5KXSL3TUUNLPX3KKT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual State Representation Learning for Reinforcement Learning using Generative Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Filliat, Hugo Caselles-Dupr\\'e, Michael Garcia-Ortiz","submitted_at":"2018-10-09T09:42:53Z","abstract_excerpt":"We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to use Variational Auto-Encoders for state representation, and Generative Replay, i.e. the use of generated samples, to maintain past knowledge. We also provide a general and statistically sound method for automatic environment change detection. Our method provides efficient state r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03880","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":"2026-05-17T23:58:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/PI4wkmOfzFYVHS/HJHFrTlEUZnxYLW0lHMsLRQwOwsMv/eKLug5hATEL4mPckeWsXTQ56CZbZa9uh5P6M8kAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:56:09.555820Z"},"content_sha256":"2cae56333eedd5bd550c338410aa3d50762a34cde806491719d8fc8afd1271a7","schema_version":"1.0","event_id":"sha256:2cae56333eedd5bd550c338410aa3d50762a34cde806491719d8fc8afd1271a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/bundle.json","state_url":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/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":"2026-05-27T12:56:09Z","links":{"resolver":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6","bundle":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/bundle.json","state":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZK74M3OZ5KXSL3TUUNLPX3KKT6","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":"bba134b9ae428522cfe24651b310612ef7d5b8858a27d7e59bce1401b901e9fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T09:42:53Z","title_canon_sha256":"40fe0dd34bf7a35a76f579b0961d4b7deecbea050296bdab8e6e15e3950b0140"},"schema_version":"1.0","source":{"id":"1810.03880","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03880","created_at":"2026-05-17T23:58:37Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03880v3","created_at":"2026-05-17T23:58:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03880","created_at":"2026-05-17T23:58:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZK74M3OZ5KXS","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZK74M3OZ5KXSL3TU","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZK74M3OZ","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:2cae56333eedd5bd550c338410aa3d50762a34cde806491719d8fc8afd1271a7","target":"graph","created_at":"2026-05-17T23:58:37Z","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":"We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to use Variational Auto-Encoders for state representation, and Generative Replay, i.e. the use of generated samples, to maintain past knowledge. We also provide a general and statistically sound method for automatic environment change detection. Our method provides efficient state r","authors_text":"David Filliat, Hugo Caselles-Dupr\\'e, Michael Garcia-Ortiz","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T09:42:53Z","title":"Continual State Representation Learning for Reinforcement Learning using Generative Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03880","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:c4a5e8ffd5591372470e08da478cdf253a9173365fd0d80f4b5ff446e346aed2","target":"record","created_at":"2026-05-17T23:58:37Z","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":"bba134b9ae428522cfe24651b310612ef7d5b8858a27d7e59bce1401b901e9fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T09:42:53Z","title_canon_sha256":"40fe0dd34bf7a35a76f579b0961d4b7deecbea050296bdab8e6e15e3950b0140"},"schema_version":"1.0","source":{"id":"1810.03880","kind":"arxiv","version":3}},"canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","first_computed_at":"2026-05-17T23:58:37.264535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:37.264535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z2aveAxN7XLpjaG/W+InGERjt4tJh4mEOKUaF6O5ZEMcub/t4mf8F0EkpFTL/oVU68ZbcoTJ43ZnckEE5x5uAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:37.265174Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03880","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4a5e8ffd5591372470e08da478cdf253a9173365fd0d80f4b5ff446e346aed2","sha256:2cae56333eedd5bd550c338410aa3d50762a34cde806491719d8fc8afd1271a7"],"state_sha256":"544b13040304e073dd9da309e873b00cf2afb1621785d8ea39a5b3e9aba6cefe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cPq1L3wV802mmOEpbr9CylRlnH8psPEu96WNBewLPzkTFSQZfqseW+MzVV1VBesI9tw0LHiB5x9pAeI4LxqGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T12:56:09.559853Z","bundle_sha256":"b1bb9abac297e8673e6517b2aeec0a6722d6f0ecc3b9f479e8c7b5fb80d6756a"}}