{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O2HFSJPRRCS7Z2J3XYVVNQYEC7","short_pith_number":"pith:O2HFSJPR","canonical_record":{"source":{"id":"2412.15544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-20T04:08:11Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"223bcf781c5a300ccaf24d5f461d55db0d39c38a4c6969aa6912b8a3fdcf3c8f","abstract_canon_sha256":"6ce149aeac15d97d7156549c891310031a7a5ad6f1e271f98beb33c8a2fe6b67"},"schema_version":"1.0"},"canonical_sha256":"768e5925f188a5fce93bbe2b56c30417ea58bd6768c5bc3fea94ff502e04fa4f","source":{"kind":"arxiv","id":"2412.15544","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15544","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15544v1","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15544","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"O2HFSJPRRCS7","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"pith_short_16","alias_value":"O2HFSJPRRCS7Z2J3","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"pith_short_8","alias_value":"O2HFSJPR","created_at":"2026-07-05T09:52:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O2HFSJPRRCS7Z2J3XYVVNQYEC7","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-20T04:08:11Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"223bcf781c5a300ccaf24d5f461d55db0d39c38a4c6969aa6912b8a3fdcf3c8f","abstract_canon_sha256":"6ce149aeac15d97d7156549c891310031a7a5ad6f1e271f98beb33c8a2fe6b67"},"schema_version":"1.0"},"canonical_sha256":"768e5925f188a5fce93bbe2b56c30417ea58bd6768c5bc3fea94ff502e04fa4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:25.030830Z","signature_b64":"c8YnWGuihVwgwxGnF6UlCNQzC9z2YKx60NuKq/ww10kkdKAzusCwC08MXSafv4NN2cGshrir+SisHC7zhqU9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"768e5925f188a5fce93bbe2b56c30417ea58bd6768c5bc3fea94ff502e04fa4f","last_reissued_at":"2026-07-05T09:52:25.030391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:25.030391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15544","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":"2026-07-05T09:52:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lbf5W3QfFh/s43LstTEUkIVtSCxwQWtCnW9f2UL3BqnJ/2y4yd53f8EBL0EdGgr6iNcNtNAgEC8iS+MqPO/pAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:04:46.433209Z"},"content_sha256":"250a5ae9ab1e8f12468513f1a78d6ae61648fdf073e7f4909da234ea727880b1","schema_version":"1.0","event_id":"sha256:250a5ae9ab1e8f12468513f1a78d6ae61648fdf073e7f4909da234ea727880b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O2HFSJPRRCS7Z2J3XYVVNQYEC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Junwei You, Sikai Chen, Yansong Qu, Zihao Sheng, Zilin Huang","submitted_at":"2024-12-20T04:08:11Z","abstract_excerpt":"In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However, traditional RL approaches rely on manually engineered rewards, which require extensive human effort and often lack generalizability. To address these limitations, we propose \\textbf{VLM-RL}, a unified framework that integrates pre-trained Vision-Language Models (VLMs) with RL to generate reward signals using image observation and natural language goals. The core "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15544","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/2412.15544/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":"2026-07-05T09:52:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ttC7lGVA2lkjcx6U4s1KmZLWaNzZJa5CYeQDMO33RqJ9LJ2/sa/xcHvg7qOZdb3xhYrsKalBOUYF9rxzPrNuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:04:46.433779Z"},"content_sha256":"75ac0f1a5cc39f033df206405df7ebe627c347d6e5b9c119034264d130234a53","schema_version":"1.0","event_id":"sha256:75ac0f1a5cc39f033df206405df7ebe627c347d6e5b9c119034264d130234a53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7/bundle.json","state_url":"https://pith.science/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7/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":"2026-08-07T13:04:46Z","links":{"resolver":"https://pith.science/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7","bundle":"https://pith.science/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7/bundle.json","state":"https://pith.science/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2HFSJPRRCS7Z2J3XYVVNQYEC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O2HFSJPRRCS7Z2J3XYVVNQYEC7","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":"6ce149aeac15d97d7156549c891310031a7a5ad6f1e271f98beb33c8a2fe6b67","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-20T04:08:11Z","title_canon_sha256":"223bcf781c5a300ccaf24d5f461d55db0d39c38a4c6969aa6912b8a3fdcf3c8f"},"schema_version":"1.0","source":{"id":"2412.15544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15544","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15544v1","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15544","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"O2HFSJPRRCS7","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"pith_short_16","alias_value":"O2HFSJPRRCS7Z2J3","created_at":"2026-07-05T09:52:25Z"},{"alias_kind":"pith_short_8","alias_value":"O2HFSJPR","created_at":"2026-07-05T09:52:25Z"}],"graph_snapshots":[{"event_id":"sha256:75ac0f1a5cc39f033df206405df7ebe627c347d6e5b9c119034264d130234a53","target":"graph","created_at":"2026-07-05T09:52:25Z","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/2412.15544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However, traditional RL approaches rely on manually engineered rewards, which require extensive human effort and often lack generalizability. To address these limitations, we propose \\textbf{VLM-RL}, a unified framework that integrates pre-trained Vision-Language Models (VLMs) with RL to generate reward signals using image observation and natural language goals. The core ","authors_text":"Junwei You, Sikai Chen, Yansong Qu, Zihao Sheng, Zilin Huang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-20T04:08:11Z","title":"VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15544","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":"sha256:250a5ae9ab1e8f12468513f1a78d6ae61648fdf073e7f4909da234ea727880b1","target":"record","created_at":"2026-07-05T09:52:25Z","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":"6ce149aeac15d97d7156549c891310031a7a5ad6f1e271f98beb33c8a2fe6b67","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-20T04:08:11Z","title_canon_sha256":"223bcf781c5a300ccaf24d5f461d55db0d39c38a4c6969aa6912b8a3fdcf3c8f"},"schema_version":"1.0","source":{"id":"2412.15544","kind":"arxiv","version":1}},"canonical_sha256":"768e5925f188a5fce93bbe2b56c30417ea58bd6768c5bc3fea94ff502e04fa4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"768e5925f188a5fce93bbe2b56c30417ea58bd6768c5bc3fea94ff502e04fa4f","first_computed_at":"2026-07-05T09:52:25.030391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:25.030391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8YnWGuihVwgwxGnF6UlCNQzC9z2YKx60NuKq/ww10kkdKAzusCwC08MXSafv4NN2cGshrir+SisHC7zhqU9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:25.030830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:250a5ae9ab1e8f12468513f1a78d6ae61648fdf073e7f4909da234ea727880b1","sha256:75ac0f1a5cc39f033df206405df7ebe627c347d6e5b9c119034264d130234a53"],"state_sha256":"2f509dcc3b27ed34606f31885b5af91221d6374291f0e3977da1dc22749c4313"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/abV9D8u5KsNGDlWsYp81fC0wK3FC97Y8SsBnHJGNiSk5vlRo8K7ADQ5YVTxUA/VGNX4i8QtFeIsdiK9W/3qAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T13:04:46.439637Z","bundle_sha256":"5fbbbde424fe955ab287d2c6a0d10d0cd83506983b51d7f6a2bfe52fb54cf614"}}