{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C5R3VTGXTWBZ7P33DDANC3CVRC","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":"bab80b74b9628bd6539a417b7fd8d5c11935966d46b9ffbffaf3afc691682c07","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T08:20:21Z","title_canon_sha256":"6b1a868b625861c2bb142a29129608d1025c0acb13bcf066dbe8ff5375382f04"},"schema_version":"1.0","source":{"id":"2411.11364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11364","created_at":"2026-07-05T09:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11364v1","created_at":"2026-07-05T09:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11364","created_at":"2026-07-05T09:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"C5R3VTGXTWBZ","created_at":"2026-07-05T09:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"C5R3VTGXTWBZ7P33","created_at":"2026-07-05T09:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"C5R3VTGX","created_at":"2026-07-05T09:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:5ce3567d5e3a1fd3fa436c2bbf50d6c7f072763e03307a30ed84b8c6b290c460","target":"graph","created_at":"2026-07-05T09:36:55Z","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/2411.11364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a generalizable agent to continually learn a sequence of tasks from offline trajectories is a natural requirement for long-lived agents, yet remains a significant challenge for current offline reinforcement learning (RL) algorithms. Specifically, an agent must be able to rapidly adapt to new tasks using newly collected trajectories (plasticity), while retaining knowledge from previously learned tasks (stability). However, systematic analyses of this setting are scarce, and it remains unclear whether conventional continual learning (CL) methods are effective in continual offline RL (CO","authors_text":"Dacheng Tao, Jifeng Hu, Li Shen, Shengchao Hu, Ya Zhang, Yuhang Zhou, Ziqing Fan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T08:20:21Z","title":"Continual Task Learning through Adaptive Policy Self-Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11364","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":"sha256:7208b2c218f1cfdc147f143105c72316223367880036bfe2f5ecb86a55da4f4f","target":"record","created_at":"2026-07-05T09:36:55Z","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":"bab80b74b9628bd6539a417b7fd8d5c11935966d46b9ffbffaf3afc691682c07","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T08:20:21Z","title_canon_sha256":"6b1a868b625861c2bb142a29129608d1025c0acb13bcf066dbe8ff5375382f04"},"schema_version":"1.0","source":{"id":"2411.11364","kind":"arxiv","version":1}},"canonical_sha256":"1763baccd79d839fbf7b18c0d16c5588a527ca9f4d47f3be112dc385d50fed62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1763baccd79d839fbf7b18c0d16c5588a527ca9f4d47f3be112dc385d50fed62","first_computed_at":"2026-07-05T09:36:55.328376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:55.328376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P894hCWBAJFTP6Sw645Rfcgl3YO3Y3UOgp/f/xfjGTZpZfQ3b9C33ro5eV/nCDIW9DCSD38XclBJOCXC8i+xDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:55.328845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7208b2c218f1cfdc147f143105c72316223367880036bfe2f5ecb86a55da4f4f","sha256:5ce3567d5e3a1fd3fa436c2bbf50d6c7f072763e03307a30ed84b8c6b290c460"],"state_sha256":"7c888ccf637fada370dd493d71b4c9c4cafd08a5b425c48874d17b44e7a49ab9"}