{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6MF5YWAGH72EEYBGXPVT5T5BTL","short_pith_number":"pith:6MF5YWAG","canonical_record":{"source":{"id":"2606.24231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T07:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"2673dbf7f51833ea7a38792eeff14e6b01c520d2a90165270cd5a562e38e8be4","abstract_canon_sha256":"8dc27a3074e0866bd18b16a0e581b52f17901b365ee50b7c24132282a1908591"},"schema_version":"1.0"},"canonical_sha256":"f30bdc58063ff4426026bbeb3ecfa19aed61a35862976ae7b165de27ec06982e","source":{"kind":"arxiv","id":"2606.24231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24231","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24231v1","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24231","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"6MF5YWAGH72E","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"6MF5YWAGH72EEYBG","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"6MF5YWAG","created_at":"2026-06-24T01:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6MF5YWAGH72EEYBGXPVT5T5BTL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T07:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"2673dbf7f51833ea7a38792eeff14e6b01c520d2a90165270cd5a562e38e8be4","abstract_canon_sha256":"8dc27a3074e0866bd18b16a0e581b52f17901b365ee50b7c24132282a1908591"},"schema_version":"1.0"},"canonical_sha256":"f30bdc58063ff4426026bbeb3ecfa19aed61a35862976ae7b165de27ec06982e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:47.230286Z","signature_b64":"rMYkUemY1j681BJau1Vwx4T4WVCUMS1mZgVp3ATD0TmJdwBPQDZ/30I8aWy41G7eRWrgwq7Ta7GMSlrr28ORCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f30bdc58063ff4426026bbeb3ecfa19aed61a35862976ae7b165de27ec06982e","last_reissued_at":"2026-06-24T01:14:47.229776Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:47.229776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24231","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":"2026-06-24T01:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ljR5rcU/hDgB0M1hx1Mg3wTFX6g8ZStJLbgHptqYCK47zEj5u1ZhvRqw+a1/9tx3I2LZEOjV05shr445R18HCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:14:00.951968Z"},"content_sha256":"f9e2893f82b48fef5e0a6688cb4c15dd5e9be4940add84061f692f805dd1e244","schema_version":"1.0","event_id":"sha256:f9e2893f82b48fef5e0a6688cb4c15dd5e9be4940add84061f692f805dd1e244"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6MF5YWAGH72EEYBGXPVT5T5BTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hengshuang Zhao, Junyu Han, Wenhua Han, Xiaoqing Ye, Xirui Li, Yifeng Pan, Zhe Liu","submitted_at":"2026-06-23T07:21:36Z","abstract_excerpt":"Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframing simulation-based rewards from discriminative targets into generative conditions. By learning the reward-conditioned action distribution from dense trajectory-reward pairs with a flow-matching dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24231","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/2606.24231/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":"2026-06-24T01:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sDoEIRtuDEYIqugMHsUF27P/nIHrP3bnLiOt/GgufZ6E2MT+UTtuDbBlyVfTBmqiYUTjtDGB3Kf+aVedttPWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:14:00.952354Z"},"content_sha256":"d06a3a77f0b5d6fce572e3837fea135f613287d514ef455dc6a6fa0f21fa8ca0","schema_version":"1.0","event_id":"sha256:d06a3a77f0b5d6fce572e3837fea135f613287d514ef455dc6a6fa0f21fa8ca0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/bundle.json","state_url":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/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":"2026-07-02T08:14:00Z","links":{"resolver":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL","bundle":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/bundle.json","state":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6MF5YWAGH72EEYBGXPVT5T5BTL","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":"8dc27a3074e0866bd18b16a0e581b52f17901b365ee50b7c24132282a1908591","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T07:21:36Z","title_canon_sha256":"2673dbf7f51833ea7a38792eeff14e6b01c520d2a90165270cd5a562e38e8be4"},"schema_version":"1.0","source":{"id":"2606.24231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24231","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24231v1","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24231","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"6MF5YWAGH72E","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"6MF5YWAGH72EEYBG","created_at":"2026-06-24T01:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"6MF5YWAG","created_at":"2026-06-24T01:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:d06a3a77f0b5d6fce572e3837fea135f613287d514ef455dc6a6fa0f21fa8ca0","target":"graph","created_at":"2026-06-24T01:14:47Z","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/2606.24231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframing simulation-based rewards from discriminative targets into generative conditions. By learning the reward-conditioned action distribution from dense trajectory-reward pairs with a flow-matching dec","authors_text":"Hengshuang Zhao, Junyu Han, Wenhua Han, Xiaoqing Ye, Xirui Li, Yifeng Pan, Zhe Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T07:21:36Z","title":"FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24231","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:f9e2893f82b48fef5e0a6688cb4c15dd5e9be4940add84061f692f805dd1e244","target":"record","created_at":"2026-06-24T01:14:47Z","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":"8dc27a3074e0866bd18b16a0e581b52f17901b365ee50b7c24132282a1908591","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T07:21:36Z","title_canon_sha256":"2673dbf7f51833ea7a38792eeff14e6b01c520d2a90165270cd5a562e38e8be4"},"schema_version":"1.0","source":{"id":"2606.24231","kind":"arxiv","version":1}},"canonical_sha256":"f30bdc58063ff4426026bbeb3ecfa19aed61a35862976ae7b165de27ec06982e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f30bdc58063ff4426026bbeb3ecfa19aed61a35862976ae7b165de27ec06982e","first_computed_at":"2026-06-24T01:14:47.229776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:47.229776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rMYkUemY1j681BJau1Vwx4T4WVCUMS1mZgVp3ATD0TmJdwBPQDZ/30I8aWy41G7eRWrgwq7Ta7GMSlrr28ORCg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:47.230286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9e2893f82b48fef5e0a6688cb4c15dd5e9be4940add84061f692f805dd1e244","sha256:d06a3a77f0b5d6fce572e3837fea135f613287d514ef455dc6a6fa0f21fa8ca0"],"state_sha256":"6acb4025ec12f7c4482368b1e9eb3632e4ac2b3148af7995b03df6e8e2942f17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h7LM5bSkK2qdeMdTMeeN/kzBaPMyD5A5avwznTR8V9IxZvkRTeAqbwHuOSUzTn+o93nIfTJINmruxof6anshDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T08:14:00.954388Z","bundle_sha256":"7c4e6b73e05f7bf6aa1afbb2b6412a30aa184c6f22e600b120d9babc2457ccc8"}}