{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C62LDUN5UHU4NTGYSLJUO2ZRUX","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":"f3c1db953691127a266c1fc3e8b0a5f48c05206a88183ac0612bd4600f229979","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T15:07:50Z","title_canon_sha256":"6f6cc5ad708043636ab3b98f19b7ccec81015fcd71d835ad892b2939da6bfea9"},"schema_version":"1.0","source":{"id":"2605.30056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30056","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30056v1","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30056","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"C62LDUN5UHU4","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"C62LDUN5UHU4NTGY","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"C62LDUN5","created_at":"2026-05-29T02:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:e9083155427744d71328112da25d10b9a1cedcc5644f331f4f19041e39a1601a","target":"graph","created_at":"2026-05-29T02:06:08Z","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/2605.30056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based policy optimization. This design enables better exploration capability of the diffusion model, particularly at the beginning of training, but suffer from low exploitation in Q-value information, resulting in a slow policy convergence. Another branch pays attention to gradient-based policy optimization, which sufficiently exploits the gradient of the Q functio","authors_text":"Bikang Pan, Jingya Wang, Ke Hu, Shutong Ding, Ye Shi, Zejia Zhong, Zhongyi Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T15:07:50Z","title":"Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30056","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":"sha256:79e593d72fd6c640c6f3bc8036168afc1b6f8889825a5163e8463c79f04c4905","target":"record","created_at":"2026-05-29T02:06:08Z","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":"f3c1db953691127a266c1fc3e8b0a5f48c05206a88183ac0612bd4600f229979","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T15:07:50Z","title_canon_sha256":"6f6cc5ad708043636ab3b98f19b7ccec81015fcd71d835ad892b2939da6bfea9"},"schema_version":"1.0","source":{"id":"2605.30056","kind":"arxiv","version":1}},"canonical_sha256":"17b4b1d1bda1e9c6ccd892d3476b31a5f9a1611017a6d39b43c56ea6d6985d19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17b4b1d1bda1e9c6ccd892d3476b31a5f9a1611017a6d39b43c56ea6d6985d19","first_computed_at":"2026-05-29T02:06:08.713236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:08.713236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CNJ9vzPZeKdwuEWH56QTMiF4ba91CFFsMI9QrdUm+9StafMOxUylrGUry4UT+M0NaIfsAEQCP53T77lVmAzoDQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:08.713715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79e593d72fd6c640c6f3bc8036168afc1b6f8889825a5163e8463c79f04c4905","sha256:e9083155427744d71328112da25d10b9a1cedcc5644f331f4f19041e39a1601a"],"state_sha256":"08c5d13e064948f69913f7b070c5a77176f8e3618c5aa6e53d36d5e8c5e1dd27"}