{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:E7DCQXOHUTOCHIOG3QZOBCYNBL","short_pith_number":"pith:E7DCQXOH","canonical_record":{"source":{"id":"2208.05056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T22:00:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"339f5413001d251c6602ceb67c4762c69af5a5f3d08161c28d4286eb2df4651d","abstract_canon_sha256":"09ab835d35b2c672210106c9cbd9e0cbd80d35c83f8a821ab943362a91934f5d"},"schema_version":"1.0"},"canonical_sha256":"27c6285dc7a4dc23a1c6dc32e08b0d0ae794c62927f4787249b04a6c1b39e514","source":{"kind":"arxiv","id":"2208.05056","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.05056","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"2208.05056v2","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05056","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"E7DCQXOHUTOC","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"pith_short_16","alias_value":"E7DCQXOHUTOCHIOG","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"pith_short_8","alias_value":"E7DCQXOH","created_at":"2026-07-05T04:49:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:E7DCQXOHUTOCHIOG3QZOBCYNBL","target":"record","payload":{"canonical_record":{"source":{"id":"2208.05056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T22:00:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"339f5413001d251c6602ceb67c4762c69af5a5f3d08161c28d4286eb2df4651d","abstract_canon_sha256":"09ab835d35b2c672210106c9cbd9e0cbd80d35c83f8a821ab943362a91934f5d"},"schema_version":"1.0"},"canonical_sha256":"27c6285dc7a4dc23a1c6dc32e08b0d0ae794c62927f4787249b04a6c1b39e514","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:03.532286Z","signature_b64":"r8cV/ao+RZL0wLHq0LaXEfpsIXTzZO1nSgdg5hyeQl+SJ0GeF4g5hferSGA7x2Q1o8OugYdXRl3jkES6zmJNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27c6285dc7a4dc23a1c6dc32e08b0d0ae794c62927f4787249b04a6c1b39e514","last_reissued_at":"2026-07-05T04:49:03.531915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:03.531915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.05056","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGwK3L7sIKlCeUKb0zVXelIasqJi1WTxpYYnT+3g6Ay36WFohpO8caoeFVJ2oOfUsH/D8AqF8YqWT690Dss3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:01:51.928651Z"},"content_sha256":"7d8641e796b235e41d3de22985769d24bf1175dd9a4087e3a1ed5e5bf72c7624","schema_version":"1.0","event_id":"sha256:7d8641e796b235e41d3de22985769d24bf1175dd9a4087e3a1ed5e5bf72c7624"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:E7DCQXOHUTOCHIOG3QZOBCYNBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abrar Rahman, Ajay Divakaran, Aswin Raghavan, Indranil Sur, Jesse Hostetler, Michael Piacentino, Zachary Daniels","submitted_at":"2022-08-09T22:00:28Z","abstract_excerpt":"One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build internal meta-models (of the tasks, environments, agents, and world). Generative replay (GR) is a biologically inspired replay mechanism that augments learning experiences with self-labelled examples drawn from an internal generative model that is updated over time. We present a version of GR for LRL that satisfies two desiderata: (a) Introspective density modelling of the latent representations of policies learned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05056","kind":"arxiv","version":2},"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/2208.05056/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":"2026-07-05T04:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FA5W8QpHip2q5Sa5wrdhT5+dlrNrlgFbwVX4E+Vwx3HADraQdnjcIXAIq1ll6Z3D4IU4mUt9f1nW8Rils0WrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:01:51.929210Z"},"content_sha256":"849eb20569e0e4f14859c49e8ef3ef465843837a228c193e0ec52e8758c682d1","schema_version":"1.0","event_id":"sha256:849eb20569e0e4f14859c49e8ef3ef465843837a228c193e0ec52e8758c682d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL/bundle.json","state_url":"https://pith.science/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL/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":"2026-08-10T08:01:51Z","links":{"resolver":"https://pith.science/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL","bundle":"https://pith.science/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL/bundle.json","state":"https://pith.science/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7DCQXOHUTOCHIOG3QZOBCYNBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E7DCQXOHUTOCHIOG3QZOBCYNBL","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":"09ab835d35b2c672210106c9cbd9e0cbd80d35c83f8a821ab943362a91934f5d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T22:00:28Z","title_canon_sha256":"339f5413001d251c6602ceb67c4762c69af5a5f3d08161c28d4286eb2df4651d"},"schema_version":"1.0","source":{"id":"2208.05056","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.05056","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"2208.05056v2","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05056","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"E7DCQXOHUTOC","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"pith_short_16","alias_value":"E7DCQXOHUTOCHIOG","created_at":"2026-07-05T04:49:03Z"},{"alias_kind":"pith_short_8","alias_value":"E7DCQXOH","created_at":"2026-07-05T04:49:03Z"}],"graph_snapshots":[{"event_id":"sha256:849eb20569e0e4f14859c49e8ef3ef465843837a228c193e0ec52e8758c682d1","target":"graph","created_at":"2026-07-05T04:49:03Z","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/2208.05056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build internal meta-models (of the tasks, environments, agents, and world). Generative replay (GR) is a biologically inspired replay mechanism that augments learning experiences with self-labelled examples drawn from an internal generative model that is updated over time. We present a version of GR for LRL that satisfies two desiderata: (a) Introspective density modelling of the latent representations of policies learned ","authors_text":"Abrar Rahman, Ajay Divakaran, Aswin Raghavan, Indranil Sur, Jesse Hostetler, Michael Piacentino, Zachary Daniels","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T22:00:28Z","title":"Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05056","kind":"arxiv","version":2},"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":"sha256:7d8641e796b235e41d3de22985769d24bf1175dd9a4087e3a1ed5e5bf72c7624","target":"record","created_at":"2026-07-05T04:49:03Z","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":"09ab835d35b2c672210106c9cbd9e0cbd80d35c83f8a821ab943362a91934f5d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T22:00:28Z","title_canon_sha256":"339f5413001d251c6602ceb67c4762c69af5a5f3d08161c28d4286eb2df4651d"},"schema_version":"1.0","source":{"id":"2208.05056","kind":"arxiv","version":2}},"canonical_sha256":"27c6285dc7a4dc23a1c6dc32e08b0d0ae794c62927f4787249b04a6c1b39e514","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27c6285dc7a4dc23a1c6dc32e08b0d0ae794c62927f4787249b04a6c1b39e514","first_computed_at":"2026-07-05T04:49:03.531915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:49:03.531915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8cV/ao+RZL0wLHq0LaXEfpsIXTzZO1nSgdg5hyeQl+SJ0GeF4g5hferSGA7x2Q1o8OugYdXRl3jkES6zmJNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:49:03.532286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.05056","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d8641e796b235e41d3de22985769d24bf1175dd9a4087e3a1ed5e5bf72c7624","sha256:849eb20569e0e4f14859c49e8ef3ef465843837a228c193e0ec52e8758c682d1"],"state_sha256":"ead0e698427758dabba07daca8fc1d338ba7e184b680b8245c50fd1ee47cc3f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EhwiCVCcpzZDnbdHUMIm2pfvF1Ma8w2hTCz35Vvl4LElFTgeqUeDT/YKWkTA3WX/dgl3FLWED9zNrpeqyinmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:01:51.932623Z","bundle_sha256":"269ea44d87a917e57813f26e6874985bc707191508b75305a2b0069bbd706a31"}}