{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YTUTNSHTOEQWHXRSYAG3JGBHZP","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":"a1c27c29a0741b0397ba4b52a9d5a3c9ae9c5b61fbf8e3fc805d86a5c05b2366","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-08T22:42:29Z","title_canon_sha256":"dcbdfb580b70d7f3637e350c5fc961f7b31d1808556934195b83c5d761f84d51"},"schema_version":"1.0","source":{"id":"2607.07967","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07967","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07967v1","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07967","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"YTUTNSHTOEQW","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"YTUTNSHTOEQWHXRS","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"YTUTNSHT","created_at":"2026-07-10T00:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:9d766327086ae5737af149c50b009b276761074d02dca5df2393903ff925395d","target":"graph","created_at":"2026-07-10T00:19:06Z","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/2607.07967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action distributions as terminal laws of diffusion processes with parameterized drifts. This terminal-law representation has shown substantial expressive flexibility in practice, enabling diffusion policies to model complex, multimodal, and highly non-Gaussian action distributions; however, it remains unclear what mathematically drives this expressivity and how to fully exploit it when the policy is learned from finite data. In this paper, we identify t","authors_text":"Jiacheng Zhang, Renyuan Xu, Viet Vu, Yufei Zhang","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-08T22:42:29Z","title":"Expressivity and Statistical Trade-offs in Diffusion Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07967","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:f815a267d693648be1a82ac11e6739f09d47d2db11edcbd5364aa0c8cde125cf","target":"record","created_at":"2026-07-10T00:19:06Z","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":"a1c27c29a0741b0397ba4b52a9d5a3c9ae9c5b61fbf8e3fc805d86a5c05b2366","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-08T22:42:29Z","title_canon_sha256":"dcbdfb580b70d7f3637e350c5fc961f7b31d1808556934195b83c5d761f84d51"},"schema_version":"1.0","source":{"id":"2607.07967","kind":"arxiv","version":1}},"canonical_sha256":"c4e936c8f3712163de32c00db49827cbdaad7695b2841aae8f91f5d34e14a681","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4e936c8f3712163de32c00db49827cbdaad7695b2841aae8f91f5d34e14a681","first_computed_at":"2026-07-10T00:19:06.094728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T00:19:06.094728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+a8nEJXFGcCn6HTKQE4v0KKgBaulFbWTXYykkw50zWqzic39J7PCzIg5Y+Hd9zxxAuWw/neOWtipt/duGYQDw==","signature_status":"signed_v1","signed_at":"2026-07-10T00:19:06.095087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07967","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f815a267d693648be1a82ac11e6739f09d47d2db11edcbd5364aa0c8cde125cf","sha256:9d766327086ae5737af149c50b009b276761074d02dca5df2393903ff925395d"],"state_sha256":"f4628ef294a28b8128d5ab64f06a2e047793eb97635d48b4dfc304665920243c"}