{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NO7H3SGJB47TEJF7YODUV5CS4O","short_pith_number":"pith:NO7H3SGJ","canonical_record":{"source":{"id":"2605.21282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:14:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d409a7ccd043e67f75a7086fb387826a9d1d41199caa3c8d132c129a227e3e45","abstract_canon_sha256":"19b0593c98e8f382ad47ceb91241530f89be7e3f992ff1bea6760837ff5ba755"},"schema_version":"1.0"},"canonical_sha256":"6bbe7dc8c90f3f3224bfc3874af452e3bc8f29a81a334c479d6457f9cc427d07","source":{"kind":"arxiv","id":"2605.21282","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21282","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21282v1","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21282","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"NO7H3SGJB47T","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"NO7H3SGJB47TEJF7","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"NO7H3SGJ","created_at":"2026-05-21T02:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NO7H3SGJB47TEJF7YODUV5CS4O","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:14:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d409a7ccd043e67f75a7086fb387826a9d1d41199caa3c8d132c129a227e3e45","abstract_canon_sha256":"19b0593c98e8f382ad47ceb91241530f89be7e3f992ff1bea6760837ff5ba755"},"schema_version":"1.0"},"canonical_sha256":"6bbe7dc8c90f3f3224bfc3874af452e3bc8f29a81a334c479d6457f9cc427d07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:26.963926Z","signature_b64":"nJEr/ZsD6vr3Tk1a297lQfxJg7W/BtOkNXknjgZyjlwXMWHtxPVrEkrCCr3gvKfGg1ZrndvQOzfeEZjfA0GcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bbe7dc8c90f3f3224bfc3874af452e3bc8f29a81a334c479d6457f9cc427d07","last_reissued_at":"2026-05-21T02:05:26.963047Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:26.963047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21282","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRpMg9AL9S0H0W/JazSQIMza/dspPlwNI9xFCPeg5mqdjPCzm3OMWNiw29Few/3zjJe2MG9TJacufOHBWve7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:06:42.957609Z"},"content_sha256":"ab8c3db2e0bb01f1d4cac34af4bd229879744e032b15ac512756f3cf98273693","schema_version":"1.0","event_id":"sha256:ab8c3db2e0bb01f1d4cac34af4bd229879744e032b15ac512756f3cf98273693"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NO7H3SGJB47TEJF7YODUV5CS4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\\textit{Stochastic} MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Da Li, Liang Bai, Tianyuan Yu, Yanming Guo, Yanwei Fu, Ye Shi, Yuehu Gong, Yulin Chen, Zeyuan Wang","submitted_at":"2026-05-20T15:14:14Z","abstract_excerpt":"Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative sampling or lack tractable entropy estimates. On the optimisation side, SAC-style soft policy improvement and mirror descent (MD) can be viewed as minimising different KL divergences: the former moves the policy towards a value-induced Boltzmann distribution, while the latter regularises each update agains"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21282","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/2605.21282/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dwSPdKP4I14GBX+LJLVxk0Nio80W17cySNHz/6j1YVHQiJhQTCrxyDTelxWIUhrQ91beAoDZGrzPNsYKPVEKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:06:42.958007Z"},"content_sha256":"2a5574590619b46317bd7c690bb9bcbcfcd8dbb6449238472ab928d2c57916e7","schema_version":"1.0","event_id":"sha256:2a5574590619b46317bd7c690bb9bcbcfcd8dbb6449238472ab928d2c57916e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NO7H3SGJB47TEJF7YODUV5CS4O/bundle.json","state_url":"https://pith.science/pith/NO7H3SGJB47TEJF7YODUV5CS4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NO7H3SGJB47TEJF7YODUV5CS4O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T18:06:42Z","links":{"resolver":"https://pith.science/pith/NO7H3SGJB47TEJF7YODUV5CS4O","bundle":"https://pith.science/pith/NO7H3SGJB47TEJF7YODUV5CS4O/bundle.json","state":"https://pith.science/pith/NO7H3SGJB47TEJF7YODUV5CS4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NO7H3SGJB47TEJF7YODUV5CS4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NO7H3SGJB47TEJF7YODUV5CS4O","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":"19b0593c98e8f382ad47ceb91241530f89be7e3f992ff1bea6760837ff5ba755","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:14:14Z","title_canon_sha256":"d409a7ccd043e67f75a7086fb387826a9d1d41199caa3c8d132c129a227e3e45"},"schema_version":"1.0","source":{"id":"2605.21282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21282","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21282v1","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21282","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"NO7H3SGJB47T","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"NO7H3SGJB47TEJF7","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"NO7H3SGJ","created_at":"2026-05-21T02:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:2a5574590619b46317bd7c690bb9bcbcfcd8dbb6449238472ab928d2c57916e7","target":"graph","created_at":"2026-05-21T02:05:26Z","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/2605.21282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative sampling or lack tractable entropy estimates. On the optimisation side, SAC-style soft policy improvement and mirror descent (MD) can be viewed as minimising different KL divergences: the former moves the policy towards a value-induced Boltzmann distribution, while the latter regularises each update agains","authors_text":"Da Li, Liang Bai, Tianyuan Yu, Yanming Guo, Yanwei Fu, Ye Shi, Yuehu Gong, Yulin Chen, Zeyuan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:14:14Z","title":"\\textit{Stochastic} MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21282","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:ab8c3db2e0bb01f1d4cac34af4bd229879744e032b15ac512756f3cf98273693","target":"record","created_at":"2026-05-21T02:05:26Z","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":"19b0593c98e8f382ad47ceb91241530f89be7e3f992ff1bea6760837ff5ba755","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:14:14Z","title_canon_sha256":"d409a7ccd043e67f75a7086fb387826a9d1d41199caa3c8d132c129a227e3e45"},"schema_version":"1.0","source":{"id":"2605.21282","kind":"arxiv","version":1}},"canonical_sha256":"6bbe7dc8c90f3f3224bfc3874af452e3bc8f29a81a334c479d6457f9cc427d07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bbe7dc8c90f3f3224bfc3874af452e3bc8f29a81a334c479d6457f9cc427d07","first_computed_at":"2026-05-21T02:05:26.963047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:26.963047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nJEr/ZsD6vr3Tk1a297lQfxJg7W/BtOkNXknjgZyjlwXMWHtxPVrEkrCCr3gvKfGg1ZrndvQOzfeEZjfA0GcDA==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:26.963926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab8c3db2e0bb01f1d4cac34af4bd229879744e032b15ac512756f3cf98273693","sha256:2a5574590619b46317bd7c690bb9bcbcfcd8dbb6449238472ab928d2c57916e7"],"state_sha256":"21ebc950c3b5194f0ae8f07705faa26c653461b2ad97db751b52ee1404e2ee8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZwPMI5Lj18o4jFJCK+VLobQzPTAmoHVlBTH6ansYDHWp34RMF1H9Ad+a0hYNK1F0lLFypW9js83YKCIeiJUiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:06:42.960650Z","bundle_sha256":"ee8e56a70fa00ece25ef74db688420e7333e8f45fee50425c9dcaafcf23a52cf"}}