{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YQDHX53Q43KIZ4HT5YV3YNOT6F","short_pith_number":"pith:YQDHX53Q","canonical_record":{"source":{"id":"2412.14446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T01:53:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b69c3b5ae8fdec6d92bfe52bfa0a5aa8c7ef630f6fecb7c3a644d0ae8e53821","abstract_canon_sha256":"061a997b0d7da33ba78b8a7a2f5aceefaf2038d277bd1792152de0ae272bb6b4"},"schema_version":"1.0"},"canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","source":{"kind":"arxiv","id":"2412.14446","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14446","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14446v2","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14446","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"YQDHX53Q43KI","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"YQDHX53Q43KIZ4HT","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"YQDHX53Q","created_at":"2026-07-05T12:01:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YQDHX53Q43KIZ4HT5YV3YNOT6F","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T01:53:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b69c3b5ae8fdec6d92bfe52bfa0a5aa8c7ef630f6fecb7c3a644d0ae8e53821","abstract_canon_sha256":"061a997b0d7da33ba78b8a7a2f5aceefaf2038d277bd1792152de0ae272bb6b4"},"schema_version":"1.0"},"canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:56.709106Z","signature_b64":"LxJgqrQ7ql8uQTmRw3RqbeEUFz45O4OV5QppaSXfpaPYxStng3ytZ51V4axqah47/OI8Lrg8OAnboueVruhXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","last_reissued_at":"2026-07-05T12:01:56.708613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:56.708613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14446","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZL/qEpAp2LmwVa76YW157UZHq2TaqpEiiK06GifDkaulsWWatxnQWViMykiu0ydlEOQH9tnyaBOprKL5FewBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:19:08.630195Z"},"content_sha256":"6351fa492de46def5ab58f8052d28be3ef38f1153f13597259425aa8f9cecddd","schema_version":"1.0","event_id":"sha256:6351fa492de46def5ab58f8052d28be3ef38f1153f13597259425aa8f9cecddd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YQDHX53Q43KIZ4HT5YV3YNOT6F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric M. Wolff, Gregory P. Meyer, Siddhartha Srinivasa, Siva Karthik Mustikovela, Xin Huang, Yi Xu, Yuxin Hu, Zaiwei Zhang","submitted_at":"2024-12-19T01:53:36Z","abstract_excerpt":"Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing the underlying reasoning processes. This limitation constrains their ability to handle challenging driving scenarios. To close this gap, we propose VLM-AD, a method that leverages vision-language models (VLMs) as teachers to enhance training by providing additional supervision that incorporates unstructured reasoning information and structured action labels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14446","kind":"arxiv","version":2},"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/2412.14446/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":"2026-07-05T12:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmHCitrQmAzM3BkIK92P0a1Q1wjo4YW4dhy66uKS556Ks0GpmCQolP8gT3zhmpgXgOXh4Q+knBN2pp8H9BdgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:19:08.630585Z"},"content_sha256":"8167591dae9bdc07ae5f051e9cf5bbeb32981c0ad52ab35aaf84840510a6f83a","schema_version":"1.0","event_id":"sha256:8167591dae9bdc07ae5f051e9cf5bbeb32981c0ad52ab35aaf84840510a6f83a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/bundle.json","state_url":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/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":"2026-07-06T16:19:08Z","links":{"resolver":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F","bundle":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/bundle.json","state":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YQDHX53Q43KIZ4HT5YV3YNOT6F","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":"061a997b0d7da33ba78b8a7a2f5aceefaf2038d277bd1792152de0ae272bb6b4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T01:53:36Z","title_canon_sha256":"0b69c3b5ae8fdec6d92bfe52bfa0a5aa8c7ef630f6fecb7c3a644d0ae8e53821"},"schema_version":"1.0","source":{"id":"2412.14446","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14446","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14446v2","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14446","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"YQDHX53Q43KI","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"YQDHX53Q43KIZ4HT","created_at":"2026-07-05T12:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"YQDHX53Q","created_at":"2026-07-05T12:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:8167591dae9bdc07ae5f051e9cf5bbeb32981c0ad52ab35aaf84840510a6f83a","target":"graph","created_at":"2026-07-05T12:01:56Z","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/2412.14446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing the underlying reasoning processes. This limitation constrains their ability to handle challenging driving scenarios. To close this gap, we propose VLM-AD, a method that leverages vision-language models (VLMs) as teachers to enhance training by providing additional supervision that incorporates unstructured reasoning information and structured action labels","authors_text":"Eric M. Wolff, Gregory P. Meyer, Siddhartha Srinivasa, Siva Karthik Mustikovela, Xin Huang, Yi Xu, Yuxin Hu, Zaiwei Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T01:53:36Z","title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14446","kind":"arxiv","version":2},"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":"sha256:6351fa492de46def5ab58f8052d28be3ef38f1153f13597259425aa8f9cecddd","target":"record","created_at":"2026-07-05T12:01:56Z","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":"061a997b0d7da33ba78b8a7a2f5aceefaf2038d277bd1792152de0ae272bb6b4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T01:53:36Z","title_canon_sha256":"0b69c3b5ae8fdec6d92bfe52bfa0a5aa8c7ef630f6fecb7c3a644d0ae8e53821"},"schema_version":"1.0","source":{"id":"2412.14446","kind":"arxiv","version":2}},"canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","first_computed_at":"2026-07-05T12:01:56.708613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:56.708613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LxJgqrQ7ql8uQTmRw3RqbeEUFz45O4OV5QppaSXfpaPYxStng3ytZ51V4axqah47/OI8Lrg8OAnboueVruhXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:56.709106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14446","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6351fa492de46def5ab58f8052d28be3ef38f1153f13597259425aa8f9cecddd","sha256:8167591dae9bdc07ae5f051e9cf5bbeb32981c0ad52ab35aaf84840510a6f83a"],"state_sha256":"dc5d3e6e2370e13ee397d78c5b365c84bf30e851389afee27bde41aa37b10ab9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w5jiFiXwXb74N1WI7jhILej9bouZV6L7F0G80sJuq30XsH1nn0+PxuPX6uX+NR27AH1ipRddK056HIRrMB6dDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:19:08.632645Z","bundle_sha256":"e2f2932232758d009ac8ce55b58d8da51007cb77addbdbc34e373439cbda1040"}}