{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KT65RND5L5FMKFULJUFGALINQD","short_pith_number":"pith:KT65RND5","canonical_record":{"source":{"id":"2507.09177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T07:52:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3f76c68e2baac01c594e9a035d5e73ec3eebac53565ac08ece6327414feadec1","abstract_canon_sha256":"6c3b0298c0ea0200b5dcbf92eb949d981ec037fe6b1af39af6c3694ca65c0b77"},"schema_version":"1.0"},"canonical_sha256":"54fdd8b47d5f4ac5168b4d0a602d0d80c03015b3d8dc047d0bf4f2bc95d55a3a","source":{"kind":"arxiv","id":"2507.09177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09177","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09177v1","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09177","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"pith_short_12","alias_value":"KT65RND5L5FM","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"pith_short_16","alias_value":"KT65RND5L5FMKFUL","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"pith_short_8","alias_value":"KT65RND5","created_at":"2026-07-05T11:36:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KT65RND5L5FMKFULJUFGALINQD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T07:52:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3f76c68e2baac01c594e9a035d5e73ec3eebac53565ac08ece6327414feadec1","abstract_canon_sha256":"6c3b0298c0ea0200b5dcbf92eb949d981ec037fe6b1af39af6c3694ca65c0b77"},"schema_version":"1.0"},"canonical_sha256":"54fdd8b47d5f4ac5168b4d0a602d0d80c03015b3d8dc047d0bf4f2bc95d55a3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:05.054089Z","signature_b64":"xdb64QFYbSrx10M/7mw+PInIyYF8cUKyhBrgEmzsSx659E/EvrFpUuDXrcibJCgqaP7H5Xc2Q9t6DkKXK02+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54fdd8b47d5f4ac5168b4d0a602d0d80c03015b3d8dc047d0bf4f2bc95d55a3a","last_reissued_at":"2026-07-05T11:36:05.053691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:05.053691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09177","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":"2026-07-05T11:36:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lf4HXRuLk/yj4h4PhVpxxhJM4Q+KIYdjuSMqRR/Zld4T/FXDsJ51fEZdRaTNzpnUVFk0elstNxgkSswXhc/VAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:43:18.677726Z"},"content_sha256":"db653c736b91502049f130c73ec26f3ce7baaaf0ea71e9626a6974e1f3d387b5","schema_version":"1.0","event_id":"sha256:db653c736b91502049f130c73ec26f3ce7baaaf0ea71e9626a6974e1f3d387b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KT65RND5L5FMKFULJUFGALINQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Reinforcement Learning by Planning with Online World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Du, Guoji Fu, Min Lin, Wee Sun Lee, Zichen Liu","submitted_at":"2025-07-12T07:52:31Z","abstract_excerpt":"Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially. One of the largest obstacles to CRL is that the agent may forget how to solve previous tasks when learning a new task, known as catastrophic forgetting. In this paper, we propose to address this challenge by planning with online world models. Specifically, we learn a Follow-The-Leader shallow model online to capture the world dynamics, in which we plan using model predictive control to solve a set of tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09177","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/2507.09177/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":"2026-07-05T11:36:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rZAMSXfoNMxvJ3xU/qA/CtldpOh+YW8zzxK2zjZiXM/4vRDmzd351t9+iXrRV55VNNkMsIssSOUipDrjiCVVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:43:18.678237Z"},"content_sha256":"c48d1ffc298f4e6a6941e7326101cd5b6dedc2f815dd002ca8acc3f5c49178c2","schema_version":"1.0","event_id":"sha256:c48d1ffc298f4e6a6941e7326101cd5b6dedc2f815dd002ca8acc3f5c49178c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KT65RND5L5FMKFULJUFGALINQD/bundle.json","state_url":"https://pith.science/pith/KT65RND5L5FMKFULJUFGALINQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KT65RND5L5FMKFULJUFGALINQD/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":"2026-08-20T20:43:18Z","links":{"resolver":"https://pith.science/pith/KT65RND5L5FMKFULJUFGALINQD","bundle":"https://pith.science/pith/KT65RND5L5FMKFULJUFGALINQD/bundle.json","state":"https://pith.science/pith/KT65RND5L5FMKFULJUFGALINQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KT65RND5L5FMKFULJUFGALINQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KT65RND5L5FMKFULJUFGALINQD","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":"6c3b0298c0ea0200b5dcbf92eb949d981ec037fe6b1af39af6c3694ca65c0b77","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T07:52:31Z","title_canon_sha256":"3f76c68e2baac01c594e9a035d5e73ec3eebac53565ac08ece6327414feadec1"},"schema_version":"1.0","source":{"id":"2507.09177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09177","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09177v1","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09177","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"pith_short_12","alias_value":"KT65RND5L5FM","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"pith_short_16","alias_value":"KT65RND5L5FMKFUL","created_at":"2026-07-05T11:36:05Z"},{"alias_kind":"pith_short_8","alias_value":"KT65RND5","created_at":"2026-07-05T11:36:05Z"}],"graph_snapshots":[{"event_id":"sha256:c48d1ffc298f4e6a6941e7326101cd5b6dedc2f815dd002ca8acc3f5c49178c2","target":"graph","created_at":"2026-07-05T11:36:05Z","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/2507.09177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially. One of the largest obstacles to CRL is that the agent may forget how to solve previous tasks when learning a new task, known as catastrophic forgetting. In this paper, we propose to address this challenge by planning with online world models. Specifically, we learn a Follow-The-Leader shallow model online to capture the world dynamics, in which we plan using model predictive control to solve a set of tasks","authors_text":"Chao Du, Guoji Fu, Min Lin, Wee Sun Lee, Zichen Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T07:52:31Z","title":"Continual Reinforcement Learning by Planning with Online World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09177","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:db653c736b91502049f130c73ec26f3ce7baaaf0ea71e9626a6974e1f3d387b5","target":"record","created_at":"2026-07-05T11:36:05Z","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":"6c3b0298c0ea0200b5dcbf92eb949d981ec037fe6b1af39af6c3694ca65c0b77","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T07:52:31Z","title_canon_sha256":"3f76c68e2baac01c594e9a035d5e73ec3eebac53565ac08ece6327414feadec1"},"schema_version":"1.0","source":{"id":"2507.09177","kind":"arxiv","version":1}},"canonical_sha256":"54fdd8b47d5f4ac5168b4d0a602d0d80c03015b3d8dc047d0bf4f2bc95d55a3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54fdd8b47d5f4ac5168b4d0a602d0d80c03015b3d8dc047d0bf4f2bc95d55a3a","first_computed_at":"2026-07-05T11:36:05.053691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:05.053691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xdb64QFYbSrx10M/7mw+PInIyYF8cUKyhBrgEmzsSx659E/EvrFpUuDXrcibJCgqaP7H5Xc2Q9t6DkKXK02+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:05.054089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db653c736b91502049f130c73ec26f3ce7baaaf0ea71e9626a6974e1f3d387b5","sha256:c48d1ffc298f4e6a6941e7326101cd5b6dedc2f815dd002ca8acc3f5c49178c2"],"state_sha256":"1964c995b903b7df8fd710a6a9cf975389ccddf564f0ce975c82a5a3b5999425"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZq0IUwKWmDWyiHT8uQ9Xkz8RMLusNm13crK0BQJ2MhfvxQaf5hrmQKQlLCLW+wdhh+LYSd4PJaW5WZicvMECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:43:18.681884Z","bundle_sha256":"9cc2029f856321c80e28cce1fbbde5e56dd5256bce75b478ba82016b74676963"}}