{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BUWBBIVVIYZDT6UTAAFLSROKGC","short_pith_number":"pith:BUWBBIVV","canonical_record":{"source":{"id":"2503.04256","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T09:38:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d118c6925a017ccc5d52007be4d5a8de1c6c7f3f5eb13e9e5dac0b4dac2b8c5","abstract_canon_sha256":"a0add05ac37fb7fabdd497a1f196311b9340927c93a2c500c2411b9513c0cb1b"},"schema_version":"1.0"},"canonical_sha256":"0d2c10a2b5463239fa93000ab945ca3089a830fdc375c843d9b0478d45c9eced","source":{"kind":"arxiv","id":"2503.04256","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04256","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04256v4","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04256","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"BUWBBIVVIYZD","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"BUWBBIVVIYZDT6UT","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"BUWBBIVV","created_at":"2026-07-05T11:16:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BUWBBIVVIYZDT6UTAAFLSROKGC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04256","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T09:38:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d118c6925a017ccc5d52007be4d5a8de1c6c7f3f5eb13e9e5dac0b4dac2b8c5","abstract_canon_sha256":"a0add05ac37fb7fabdd497a1f196311b9340927c93a2c500c2411b9513c0cb1b"},"schema_version":"1.0"},"canonical_sha256":"0d2c10a2b5463239fa93000ab945ca3089a830fdc375c843d9b0478d45c9eced","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:56.366788Z","signature_b64":"spe+AXWeHvXfWWbcaNAAb9SLGnw3ZeXLwaspC6qUCfDyMrXfitmmCK00sKLoJW5eXICk91GDvpMOP0Tnd2OLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d2c10a2b5463239fa93000ab945ca3089a830fdc375c843d9b0478d45c9eced","last_reissued_at":"2026-07-05T11:16:56.366261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:56.366261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04256","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4cc2RFgVShDWjEqfWG3NlxLkNvYqrgvSevV5rbD1kG1fo83nGWzwKehvsPNAiAhn3MR0LwaXFQHvY9Mf5kjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:10:11.544438Z"},"content_sha256":"a755c98cd9687364240675c32c455b2e68e39a613a58da136a09990a78009976","schema_version":"1.0","event_id":"sha256:a755c98cd9687364240675c32c455b2e68e39a613a58da136a09990a78009976"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BUWBBIVVIYZDT6UTAAFLSROKGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Retention for Continual Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"George Konidaris, Haotian Fu, Michael Littman, Yixiang Sun","submitted_at":"2025-03-06T09:38:14Z","abstract_excerpt":"We propose DRAGO, a novel approach for continual model-based reinforcement learning aimed at improving the incremental development of world models across a sequence of tasks that differ in their reward functions but not the state space or dynamics. DRAGO comprises two key components: Synthetic Experience Rehearsal, which leverages generative models to create synthetic experiences from past tasks, allowing the agent to reinforce previously learned dynamics without storing data, and Regaining Memories Through Exploration, which introduces an intrinsic reward mechanism to guide the agent toward r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04256","kind":"arxiv","version":4},"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/2503.04256/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":"2026-07-05T11:16:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AjaFwqn+WGxx7JyxUJ/DykaMNHD18Y9VwpkFp3dTqNerkqI0TibMTFbiDS/Lkv22QoCrBeLrBjDpOj9cNwqLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:10:11.544978Z"},"content_sha256":"fc771be4ea40838696545fb36861ef4e1f7e91f5750a2e4137ea1bf39104f970","schema_version":"1.0","event_id":"sha256:fc771be4ea40838696545fb36861ef4e1f7e91f5750a2e4137ea1bf39104f970"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUWBBIVVIYZDT6UTAAFLSROKGC/bundle.json","state_url":"https://pith.science/pith/BUWBBIVVIYZDT6UTAAFLSROKGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUWBBIVVIYZDT6UTAAFLSROKGC/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":"2026-07-31T17:10:11Z","links":{"resolver":"https://pith.science/pith/BUWBBIVVIYZDT6UTAAFLSROKGC","bundle":"https://pith.science/pith/BUWBBIVVIYZDT6UTAAFLSROKGC/bundle.json","state":"https://pith.science/pith/BUWBBIVVIYZDT6UTAAFLSROKGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUWBBIVVIYZDT6UTAAFLSROKGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BUWBBIVVIYZDT6UTAAFLSROKGC","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":"a0add05ac37fb7fabdd497a1f196311b9340927c93a2c500c2411b9513c0cb1b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T09:38:14Z","title_canon_sha256":"0d118c6925a017ccc5d52007be4d5a8de1c6c7f3f5eb13e9e5dac0b4dac2b8c5"},"schema_version":"1.0","source":{"id":"2503.04256","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04256","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04256v4","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04256","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"BUWBBIVVIYZD","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"BUWBBIVVIYZDT6UT","created_at":"2026-07-05T11:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"BUWBBIVV","created_at":"2026-07-05T11:16:56Z"}],"graph_snapshots":[{"event_id":"sha256:fc771be4ea40838696545fb36861ef4e1f7e91f5750a2e4137ea1bf39104f970","target":"graph","created_at":"2026-07-05T11:16:56Z","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/2503.04256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose DRAGO, a novel approach for continual model-based reinforcement learning aimed at improving the incremental development of world models across a sequence of tasks that differ in their reward functions but not the state space or dynamics. DRAGO comprises two key components: Synthetic Experience Rehearsal, which leverages generative models to create synthetic experiences from past tasks, allowing the agent to reinforce previously learned dynamics without storing data, and Regaining Memories Through Exploration, which introduces an intrinsic reward mechanism to guide the agent toward r","authors_text":"George Konidaris, Haotian Fu, Michael Littman, Yixiang Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T09:38:14Z","title":"Knowledge Retention for Continual Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04256","kind":"arxiv","version":4},"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:a755c98cd9687364240675c32c455b2e68e39a613a58da136a09990a78009976","target":"record","created_at":"2026-07-05T11:16:56Z","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":"a0add05ac37fb7fabdd497a1f196311b9340927c93a2c500c2411b9513c0cb1b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T09:38:14Z","title_canon_sha256":"0d118c6925a017ccc5d52007be4d5a8de1c6c7f3f5eb13e9e5dac0b4dac2b8c5"},"schema_version":"1.0","source":{"id":"2503.04256","kind":"arxiv","version":4}},"canonical_sha256":"0d2c10a2b5463239fa93000ab945ca3089a830fdc375c843d9b0478d45c9eced","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d2c10a2b5463239fa93000ab945ca3089a830fdc375c843d9b0478d45c9eced","first_computed_at":"2026-07-05T11:16:56.366261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:56.366261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"spe+AXWeHvXfWWbcaNAAb9SLGnw3ZeXLwaspC6qUCfDyMrXfitmmCK00sKLoJW5eXICk91GDvpMOP0Tnd2OLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:56.366788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04256","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a755c98cd9687364240675c32c455b2e68e39a613a58da136a09990a78009976","sha256:fc771be4ea40838696545fb36861ef4e1f7e91f5750a2e4137ea1bf39104f970"],"state_sha256":"dc963189535dbc4e17c512fa7f5409ccba5272a2663a1a3bb7f6a29afa3fe5d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JokUOGJtyQgdyn7FJcmpWjtEUX4yCG54xjiS8F2bAGipcWo67/emsYSf4TNvKGp2oa3z16HGE3Bl7XZhz1IWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:10:11.550290Z","bundle_sha256":"ec6daa7fa14717e7c14bdf8ff0d8913ee2f2572d6c43e21e16dd422716a9f1c3"}}