{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FIRG5Y5GRIWWJTUCRQSZFTR2GI","short_pith_number":"pith:FIRG5Y5G","canonical_record":{"source":{"id":"2505.24317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T08:00:51Z","cross_cats_sorted":[],"title_canon_sha256":"e352465d2e33c452a9a80012b879a2a1896f8983cb26a47a9a0be92d2153baef","abstract_canon_sha256":"cc91e6cd545baa5ad7e979b7493c2d61465721f4f50264d314984b4b98514bd4"},"schema_version":"1.0"},"canonical_sha256":"2a226ee3a68a2d64ce828c2592ce3a321d8c7f5a39840c3ef8be6a86cfe3d783","source":{"kind":"arxiv","id":"2505.24317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24317","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24317v1","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24317","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"FIRG5Y5GRIWW","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"pith_short_16","alias_value":"FIRG5Y5GRIWWJTUC","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"pith_short_8","alias_value":"FIRG5Y5G","created_at":"2026-07-05T11:12:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FIRG5Y5GRIWWJTUCRQSZFTR2GI","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T08:00:51Z","cross_cats_sorted":[],"title_canon_sha256":"e352465d2e33c452a9a80012b879a2a1896f8983cb26a47a9a0be92d2153baef","abstract_canon_sha256":"cc91e6cd545baa5ad7e979b7493c2d61465721f4f50264d314984b4b98514bd4"},"schema_version":"1.0"},"canonical_sha256":"2a226ee3a68a2d64ce828c2592ce3a321d8c7f5a39840c3ef8be6a86cfe3d783","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:46.677246Z","signature_b64":"mJXybNcOTEaMtdwo0XzFf4VkSt3N54l2vgKjn6FyC3oz1s/EAX/lWtUzMui2ji2r54Vba6v+aM6oksDI1tA4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a226ee3a68a2d64ce828c2592ce3a321d8c7f5a39840c3ef8be6a86cfe3d783","last_reissued_at":"2026-07-05T11:12:46.676701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:46.676701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24317","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":"2026-07-05T11:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v0YUcd9yl9Br3Ve11SdHiEu8F9/oP+KhBn3yySuPivL2BqLwjkBdAopRED2utMpXSdJ62MBVOOuOxYHjBDmoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:35:04.974954Z"},"content_sha256":"e4da387d7ecad6b0daa31d866f83b8a6cc61c55adbdeed746c17520ffa08fb63","schema_version":"1.0","event_id":"sha256:e4da387d7ecad6b0daa31d866f83b8a6cc61c55adbdeed746c17520ffa08fb63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FIRG5Y5GRIWWJTUCRQSZFTR2GI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hengrui Zhang, Liewen Liao, Miner Chen, Mingyang Jiang, Songan Zhang, Xiang Zuo, Yongming Chen, Yuchen Xi","submitted_at":"2025-05-30T08:00:51Z","abstract_excerpt":"Reinforcement learning (RL) in autonomous driving employs a trial-and-error mechanism, enhancing robustness in unpredictable environments. However, crafting effective reward functions remains challenging, as conventional approaches rely heavily on manual design and demonstrate limited efficacy in complex scenarios. To address this issue, this study introduces a responsibility-oriented reward function that explicitly incorporates traffic regulations into the RL framework. Specifically, we introduced a Traffic Regulation Knowledge Graph and leveraged Vision-Language Models alongside Retrieval-Au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24317","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/2505.24317/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":"2026-07-05T11:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6KVSI6Ri0kswNDqEp9PNNCXCKpTQ6YdDZseosTAlahhgMQKNKKSPDdVjrNBEvfXzvrv/FPdvS6r+QxwRcGpNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:35:04.975929Z"},"content_sha256":"d4adc27716800ee10898dec220ef322d803549b273095c797092f44038a0bb5b","schema_version":"1.0","event_id":"sha256:d4adc27716800ee10898dec220ef322d803549b273095c797092f44038a0bb5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI/bundle.json","state_url":"https://pith.science/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI/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":"2026-08-09T06:35:04Z","links":{"resolver":"https://pith.science/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI","bundle":"https://pith.science/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI/bundle.json","state":"https://pith.science/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIRG5Y5GRIWWJTUCRQSZFTR2GI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FIRG5Y5GRIWWJTUCRQSZFTR2GI","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":"cc91e6cd545baa5ad7e979b7493c2d61465721f4f50264d314984b4b98514bd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T08:00:51Z","title_canon_sha256":"e352465d2e33c452a9a80012b879a2a1896f8983cb26a47a9a0be92d2153baef"},"schema_version":"1.0","source":{"id":"2505.24317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24317","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24317v1","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24317","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"FIRG5Y5GRIWW","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"pith_short_16","alias_value":"FIRG5Y5GRIWWJTUC","created_at":"2026-07-05T11:12:46Z"},{"alias_kind":"pith_short_8","alias_value":"FIRG5Y5G","created_at":"2026-07-05T11:12:46Z"}],"graph_snapshots":[{"event_id":"sha256:d4adc27716800ee10898dec220ef322d803549b273095c797092f44038a0bb5b","target":"graph","created_at":"2026-07-05T11:12:46Z","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/2505.24317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) in autonomous driving employs a trial-and-error mechanism, enhancing robustness in unpredictable environments. However, crafting effective reward functions remains challenging, as conventional approaches rely heavily on manual design and demonstrate limited efficacy in complex scenarios. To address this issue, this study introduces a responsibility-oriented reward function that explicitly incorporates traffic regulations into the RL framework. Specifically, we introduced a Traffic Regulation Knowledge Graph and leveraged Vision-Language Models alongside Retrieval-Au","authors_text":"Hengrui Zhang, Liewen Liao, Miner Chen, Mingyang Jiang, Songan Zhang, Xiang Zuo, Yongming Chen, Yuchen Xi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T08:00:51Z","title":"ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24317","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:e4da387d7ecad6b0daa31d866f83b8a6cc61c55adbdeed746c17520ffa08fb63","target":"record","created_at":"2026-07-05T11:12:46Z","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":"cc91e6cd545baa5ad7e979b7493c2d61465721f4f50264d314984b4b98514bd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T08:00:51Z","title_canon_sha256":"e352465d2e33c452a9a80012b879a2a1896f8983cb26a47a9a0be92d2153baef"},"schema_version":"1.0","source":{"id":"2505.24317","kind":"arxiv","version":1}},"canonical_sha256":"2a226ee3a68a2d64ce828c2592ce3a321d8c7f5a39840c3ef8be6a86cfe3d783","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a226ee3a68a2d64ce828c2592ce3a321d8c7f5a39840c3ef8be6a86cfe3d783","first_computed_at":"2026-07-05T11:12:46.676701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:46.676701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mJXybNcOTEaMtdwo0XzFf4VkSt3N54l2vgKjn6FyC3oz1s/EAX/lWtUzMui2ji2r54Vba6v+aM6oksDI1tA4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:46.677246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4da387d7ecad6b0daa31d866f83b8a6cc61c55adbdeed746c17520ffa08fb63","sha256:d4adc27716800ee10898dec220ef322d803549b273095c797092f44038a0bb5b"],"state_sha256":"1132e94454ea9e1517792909c1a27efd513605d40c414d246902feb99250bff2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwYeMYc3fGTWGeQSaeMa9bnSXc6jh4BzumhyrBMRrKlYMjwNgWZL1LnPlogOlwe4BhqtlqAa6T2T3uCQWf0/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:35:04.982689Z","bundle_sha256":"8a492b6522b4462a42a5250e4e0ea51bebc237803c3804e9163f0dcd75bec7d3"}}