{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U3OICSDASST4RF3TPF3VV6HHUI","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":"9fce7be1c4f7ffdd4b3df1692d5feaef39c9c118d748320b7a5924608921a757","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T15:01:38Z","title_canon_sha256":"788bdc1c9b111d41fe1810dc6e1eccecb91351dba485ae467bd08d84b8cb65c0"},"schema_version":"1.0","source":{"id":"2305.19923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19923","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19923v1","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19923","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"U3OICSDASST4","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"U3OICSDASST4RF3T","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"U3OICSDA","created_at":"2026-07-05T06:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:917c3796cfc40519e9c2c7d9f97e3c21e6cad1eb7d413ba6c1c9e3566291dabd","target":"graph","created_at":"2026-07-05T06:16:04Z","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/2305.19923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, diffusion model shines as a promising backbone for the sequence modeling paradigm in offline reinforcement learning(RL). However, these works mostly lack the generalization ability across tasks with reward or dynamics change. To tackle this challenge, in this paper we propose a task-oriented conditioned diffusion planner for offline meta-RL(MetaDiffuser), which considers the generalization problem as conditional trajectory generation task with contextual representation. The key is to learn a context conditioned diffusion model which can generate task-oriented trajectories for plannin","authors_text":"Bin Wang, Fei Ni, Jianye Hao, Yan Zheng, Yao Mu, Yifu Yuan, Zhixuan Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T15:01:38Z","title":"MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19923","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:df144cd040d8a2114c5331222034260d865941c74b15d3c64300b0e002e741c3","target":"record","created_at":"2026-07-05T06:16:04Z","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":"9fce7be1c4f7ffdd4b3df1692d5feaef39c9c118d748320b7a5924608921a757","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T15:01:38Z","title_canon_sha256":"788bdc1c9b111d41fe1810dc6e1eccecb91351dba485ae467bd08d84b8cb65c0"},"schema_version":"1.0","source":{"id":"2305.19923","kind":"arxiv","version":1}},"canonical_sha256":"a6dc81486094a7c8977379775af8e7a20d4b45d1b8636371810842223b6db18b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6dc81486094a7c8977379775af8e7a20d4b45d1b8636371810842223b6db18b","first_computed_at":"2026-07-05T06:16:04.966486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:04.966486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dLfjgPEt9sDkCe8X0GjyoHiA+XpyZ63Zyahh58mphRN6j6R8D+cUsiNhtAGH6L6mvrrK250GRwKxSUYDrmnjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:04.966980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df144cd040d8a2114c5331222034260d865941c74b15d3c64300b0e002e741c3","sha256:917c3796cfc40519e9c2c7d9f97e3c21e6cad1eb7d413ba6c1c9e3566291dabd"],"state_sha256":"b9c1f19d5bcf3a1731845c427dbb21302449cc626618dc86ea693c9d6c5aad92"}