{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C62LDUN5UHU4NTGYSLJUO2ZRUX","short_pith_number":"pith:C62LDUN5","schema_version":"1.0","canonical_sha256":"17b4b1d1bda1e9c6ccd892d3476b31a5f9a1611017a6d39b43c56ea6d6985d19","source":{"kind":"arxiv","id":"2605.30056","version":1},"attestation_state":"computed","paper":{"title":"Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bikang Pan, Jingya Wang, Ke Hu, Shutong Ding, Ye Shi, Zejia Zhong, Zhongyi Wang","submitted_at":"2026-05-28T15:07:50Z","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"},"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":"2605.30056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T15:07:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f6cc5ad708043636ab3b98f19b7ccec81015fcd71d835ad892b2939da6bfea9","abstract_canon_sha256":"f3c1db953691127a266c1fc3e8b0a5f48c05206a88183ac0612bd4600f229979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:08.713715Z","signature_b64":"CNJ9vzPZeKdwuEWH56QTMiF4ba91CFFsMI9QrdUm+9StafMOxUylrGUry4UT+M0NaIfsAEQCP53T77lVmAzoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17b4b1d1bda1e9c6ccd892d3476b31a5f9a1611017a6d39b43c56ea6d6985d19","last_reissued_at":"2026-05-29T02:06:08.713236Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:08.713236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bikang Pan, Jingya Wang, Ke Hu, Shutong Ding, Ye Shi, Zejia Zhong, Zhongyi Wang","submitted_at":"2026-05-28T15:07:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30056","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/2605.30056/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":"2605.30056","created_at":"2026-05-29T02:06:08.713296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30056v1","created_at":"2026-05-29T02:06:08.713296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30056","created_at":"2026-05-29T02:06:08.713296+00:00"},{"alias_kind":"pith_short_12","alias_value":"C62LDUN5UHU4","created_at":"2026-05-29T02:06:08.713296+00:00"},{"alias_kind":"pith_short_16","alias_value":"C62LDUN5UHU4NTGY","created_at":"2026-05-29T02:06:08.713296+00:00"},{"alias_kind":"pith_short_8","alias_value":"C62LDUN5","created_at":"2026-05-29T02:06:08.713296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX","json":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX.json","graph_json":"https://pith.science/api/pith-number/C62LDUN5UHU4NTGYSLJUO2ZRUX/graph.json","events_json":"https://pith.science/api/pith-number/C62LDUN5UHU4NTGYSLJUO2ZRUX/events.json","paper":"https://pith.science/paper/C62LDUN5"},"agent_actions":{"view_html":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX","download_json":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX.json","view_paper":"https://pith.science/paper/C62LDUN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30056&json=true","fetch_graph":"https://pith.science/api/pith-number/C62LDUN5UHU4NTGYSLJUO2ZRUX/graph.json","fetch_events":"https://pith.science/api/pith-number/C62LDUN5UHU4NTGYSLJUO2ZRUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX/action/storage_attestation","attest_author":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX/action/author_attestation","sign_citation":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX/action/citation_signature","submit_replication":"https://pith.science/pith/C62LDUN5UHU4NTGYSLJUO2ZRUX/action/replication_record"}},"created_at":"2026-05-29T02:06:08.713296+00:00","updated_at":"2026-05-29T02:06:08.713296+00:00"}