{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6MF5YWAGH72EEYBGXPVT5T5BTL","short_pith_number":"pith:6MF5YWAG","schema_version":"1.0","canonical_sha256":"f30bdc58063ff4426026bbeb3ecfa19aed61a35862976ae7b165de27ec06982e","source":{"kind":"arxiv","id":"2606.24231","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.24231","created_at":"2026-06-24T01:14:47.229843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24231v1","created_at":"2026-06-24T01:14:47.229843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24231","created_at":"2026-06-24T01:14:47.229843+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MF5YWAGH72E","created_at":"2026-06-24T01:14:47.229843+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MF5YWAGH72EEYBG","created_at":"2026-06-24T01:14:47.229843+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MF5YWAG","created_at":"2026-06-24T01:14:47.229843+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/6MF5YWAGH72EEYBGXPVT5T5BTL","json":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL.json","graph_json":"https://pith.science/api/pith-number/6MF5YWAGH72EEYBGXPVT5T5BTL/graph.json","events_json":"https://pith.science/api/pith-number/6MF5YWAGH72EEYBGXPVT5T5BTL/events.json","paper":"https://pith.science/paper/6MF5YWAG"},"agent_actions":{"view_html":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL","download_json":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL.json","view_paper":"https://pith.science/paper/6MF5YWAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24231&json=true","fetch_graph":"https://pith.science/api/pith-number/6MF5YWAGH72EEYBGXPVT5T5BTL/graph.json","fetch_events":"https://pith.science/api/pith-number/6MF5YWAGH72EEYBGXPVT5T5BTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/action/storage_attestation","attest_author":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/action/author_attestation","sign_citation":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/action/citation_signature","submit_replication":"https://pith.science/pith/6MF5YWAGH72EEYBGXPVT5T5BTL/action/replication_record"}},"created_at":"2026-06-24T01:14:47.229843+00:00","updated_at":"2026-06-24T01:14:47.229843+00:00"}