{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3YMGADYDAKTANJD5CZSMW3RHLK","short_pith_number":"pith:3YMGADYD","canonical_record":{"source":{"id":"2605.23365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:28:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48e2021c62bd3f1e1bf05b1bdba7f183d8b6e3c2e8c46eccd0247d7974c52064","abstract_canon_sha256":"48bba68335f50a1a3b8b0ba51cb8de854ff7043d9f4cd8bdc4532d2cb73847d5"},"schema_version":"1.0"},"canonical_sha256":"de18600f0302a606a47d1664cb6e275ab66f889013f2dab1dbd4ceae3f3f80e2","source":{"kind":"arxiv","id":"2605.23365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23365","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23365v1","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23365","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"3YMGADYDAKTA","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"3YMGADYDAKTANJD5","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"3YMGADYD","created_at":"2026-05-25T02:01:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3YMGADYDAKTANJD5CZSMW3RHLK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:28:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48e2021c62bd3f1e1bf05b1bdba7f183d8b6e3c2e8c46eccd0247d7974c52064","abstract_canon_sha256":"48bba68335f50a1a3b8b0ba51cb8de854ff7043d9f4cd8bdc4532d2cb73847d5"},"schema_version":"1.0"},"canonical_sha256":"de18600f0302a606a47d1664cb6e275ab66f889013f2dab1dbd4ceae3f3f80e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:51.035994Z","signature_b64":"myf10uZg+W4zTZrR3Z7jQK4iErKkZqOsmx2VPN5Z372gotsHZz49SupT1rbbi5vi/QflwZWBZS2wgEHT9B+vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de18600f0302a606a47d1664cb6e275ab66f889013f2dab1dbd4ceae3f3f80e2","last_reissued_at":"2026-05-25T02:01:51.035299Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:51.035299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23365","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":"2026-05-25T02:01:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5gggPGAla1N+13Qg+jNACGeualFsJKUtBNi0pEiTkGojF579zMJPeRlz2ZWa8fYrIBGFSizZFlIQQSAlfL7ODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:11:33.778158Z"},"content_sha256":"92a27bc0f784e4522be252e28a8293fd6d287f5d24b3049e7201fe7a1fb70860","schema_version":"1.0","event_id":"sha256:92a27bc0f784e4522be252e28a8293fd6d287f5d24b3049e7201fe7a1fb70860"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3YMGADYDAKTANJD5CZSMW3RHLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Score-Based One-step MeanFlow Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Donghyeon Ki, Hee-Jun Ahn, Kyungyoon Kim","submitted_at":"2026-05-22T08:28:51Z","abstract_excerpt":"Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in online RL. MeanFlow offers a promising alternative by learning an average velocity field that maps noise to data in a single network evaluation. However, MeanFlow typically requires samples from the target distribution to construct its target velocity field, which are unavailable in online RL. We propose Score-Based One-step MeanFlow Policy Optimization (SOM)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23365","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/2605.23365/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":"2026-05-25T02:01:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"if2E5+XC5GvMkVT8NmBfRF2UF+/wUOwXyfeYyVCBArd3ngAhU4Lhcb8KKUbGA4tJkNlCsVPbbCc+VxpgQU0oBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:11:33.778558Z"},"content_sha256":"509d42daf1c82f9aaf8226d5099df4a5f18ae7a24647b6fc3460b734f9f6e3d1","schema_version":"1.0","event_id":"sha256:509d42daf1c82f9aaf8226d5099df4a5f18ae7a24647b6fc3460b734f9f6e3d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YMGADYDAKTANJD5CZSMW3RHLK/bundle.json","state_url":"https://pith.science/pith/3YMGADYDAKTANJD5CZSMW3RHLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YMGADYDAKTANJD5CZSMW3RHLK/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":"2026-05-29T18:11:33Z","links":{"resolver":"https://pith.science/pith/3YMGADYDAKTANJD5CZSMW3RHLK","bundle":"https://pith.science/pith/3YMGADYDAKTANJD5CZSMW3RHLK/bundle.json","state":"https://pith.science/pith/3YMGADYDAKTANJD5CZSMW3RHLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YMGADYDAKTANJD5CZSMW3RHLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3YMGADYDAKTANJD5CZSMW3RHLK","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":"48bba68335f50a1a3b8b0ba51cb8de854ff7043d9f4cd8bdc4532d2cb73847d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:28:51Z","title_canon_sha256":"48e2021c62bd3f1e1bf05b1bdba7f183d8b6e3c2e8c46eccd0247d7974c52064"},"schema_version":"1.0","source":{"id":"2605.23365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23365","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23365v1","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23365","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"3YMGADYDAKTA","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"3YMGADYDAKTANJD5","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"3YMGADYD","created_at":"2026-05-25T02:01:51Z"}],"graph_snapshots":[{"event_id":"sha256:509d42daf1c82f9aaf8226d5099df4a5f18ae7a24647b6fc3460b734f9f6e3d1","target":"graph","created_at":"2026-05-25T02:01:51Z","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/2605.23365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in online RL. MeanFlow offers a promising alternative by learning an average velocity field that maps noise to data in a single network evaluation. However, MeanFlow typically requires samples from the target distribution to construct its target velocity field, which are unavailable in online RL. We propose Score-Based One-step MeanFlow Policy Optimization (SOM)","authors_text":"Byung-Jun Lee, Donghyeon Ki, Hee-Jun Ahn, Kyungyoon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:28:51Z","title":"Score-Based One-step MeanFlow Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23365","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":"sha256:92a27bc0f784e4522be252e28a8293fd6d287f5d24b3049e7201fe7a1fb70860","target":"record","created_at":"2026-05-25T02:01:51Z","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":"48bba68335f50a1a3b8b0ba51cb8de854ff7043d9f4cd8bdc4532d2cb73847d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:28:51Z","title_canon_sha256":"48e2021c62bd3f1e1bf05b1bdba7f183d8b6e3c2e8c46eccd0247d7974c52064"},"schema_version":"1.0","source":{"id":"2605.23365","kind":"arxiv","version":1}},"canonical_sha256":"de18600f0302a606a47d1664cb6e275ab66f889013f2dab1dbd4ceae3f3f80e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de18600f0302a606a47d1664cb6e275ab66f889013f2dab1dbd4ceae3f3f80e2","first_computed_at":"2026-05-25T02:01:51.035299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:51.035299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"myf10uZg+W4zTZrR3Z7jQK4iErKkZqOsmx2VPN5Z372gotsHZz49SupT1rbbi5vi/QflwZWBZS2wgEHT9B+vBQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:51.035994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92a27bc0f784e4522be252e28a8293fd6d287f5d24b3049e7201fe7a1fb70860","sha256:509d42daf1c82f9aaf8226d5099df4a5f18ae7a24647b6fc3460b734f9f6e3d1"],"state_sha256":"b69cdacfc4a037ff6ff4785bc7919b0aa91843806ada053dc9280a2d9586bc8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QA2iU++F9ul0PMkq4PfaUMfbR5YMDMDNbFVkIqfZeqKd8W0zFKfwWvMkI70ZWtZqp9/YG/r6zgKtqMj/l4ANDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:11:33.780622Z","bundle_sha256":"1de1cb925f74579c6e9243b1229a7727d364ac4c62c569e97f3c243787df9709"}}