{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NXALNU6EY5JF3UNXGQQAP62PEY","short_pith_number":"pith:NXALNU6E","schema_version":"1.0","canonical_sha256":"6dc0b6d3c4c7525dd1b7342007fb4f2631f95c83013dde6b56c0d0972bcedb88","source":{"kind":"arxiv","id":"2409.02512","version":2},"attestation_state":"computed","paper":{"title":"Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Hechang Chen, Jifeng Hu, Lichao Sun, Li Shen, Sili Huang, Yi Chang, Zhejian Yang","submitted_at":"2024-09-04T08:21:47Z","abstract_excerpt":"Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world applications, such as robotic control of reinforcement learning (RL), the tasks are changing, and new tasks arise in a sequential order. This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge. In view of this, we propose a rehearsal-based continual diffusion model, called Continual"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.02512","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-04T08:21:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b78f64c0872f58dc1f5a681b7d54fb39f269de9fdc2ed3d2d524c66a91feb924","abstract_canon_sha256":"10098a19a58d346afcb42155187fdb32511db2ae2d6b5fbe4d88e5c1e2ef3971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:15.891706Z","signature_b64":"H7nK61+hrHAihjb8HP1nuc5I0oVkMtlczIjjlIk0OJ8lwiEW+NfiKVWwyyjdx/vPRKY5mA5b734LUiIc64WiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dc0b6d3c4c7525dd1b7342007fb4f2631f95c83013dde6b56c0d0972bcedb88","last_reissued_at":"2026-07-05T10:01:15.891192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:15.891192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Hechang Chen, Jifeng Hu, Lichao Sun, Li Shen, Sili Huang, Yi Chang, Zhejian Yang","submitted_at":"2024-09-04T08:21:47Z","abstract_excerpt":"Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world applications, such as robotic control of reinforcement learning (RL), the tasks are changing, and new tasks arise in a sequential order. This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge. In view of this, we propose a rehearsal-based continual diffusion model, called Continual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02512","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/2409.02512/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.02512","created_at":"2026-07-05T10:01:15.891266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02512v2","created_at":"2026-07-05T10:01:15.891266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02512","created_at":"2026-07-05T10:01:15.891266+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXALNU6EY5JF","created_at":"2026-07-05T10:01:15.891266+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXALNU6EY5JF3UNX","created_at":"2026-07-05T10:01:15.891266+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXALNU6E","created_at":"2026-07-05T10:01:15.891266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11364","citing_title":"Continual Task Learning through Adaptive Policy Self-Composition","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY","json":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY.json","graph_json":"https://pith.science/api/pith-number/NXALNU6EY5JF3UNXGQQAP62PEY/graph.json","events_json":"https://pith.science/api/pith-number/NXALNU6EY5JF3UNXGQQAP62PEY/events.json","paper":"https://pith.science/paper/NXALNU6E"},"agent_actions":{"view_html":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY","download_json":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY.json","view_paper":"https://pith.science/paper/NXALNU6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02512&json=true","fetch_graph":"https://pith.science/api/pith-number/NXALNU6EY5JF3UNXGQQAP62PEY/graph.json","fetch_events":"https://pith.science/api/pith-number/NXALNU6EY5JF3UNXGQQAP62PEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY/action/storage_attestation","attest_author":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY/action/author_attestation","sign_citation":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY/action/citation_signature","submit_replication":"https://pith.science/pith/NXALNU6EY5JF3UNXGQQAP62PEY/action/replication_record"}},"created_at":"2026-07-05T10:01:15.891266+00:00","updated_at":"2026-07-05T10:01:15.891266+00:00"}