{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LH3UPC5MQAOWWMYIIJ4X5ZRY52","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":"562fcf8d5db313547d08265b7cfab101ff2d83bab65961f1813c7b20e663b40b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T16:36:34Z","title_canon_sha256":"9a2cea8cf5ac5aab0772d3e168f0c6cd689394ea060ce041a4070424e7d97bd5"},"schema_version":"1.0","source":{"id":"2605.20082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20082","created_at":"2026-05-20T02:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20082v1","created_at":"2026-05-20T02:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20082","created_at":"2026-05-20T02:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"LH3UPC5MQAOW","created_at":"2026-05-20T02:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"LH3UPC5MQAOWWMYI","created_at":"2026-05-20T02:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"LH3UPC5M","created_at":"2026-05-20T02:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:90361da68a141db844f4a1fa3e3e8ebbf11462ec1785e99e066d8fd2ce0dc31b","target":"graph","created_at":"2026-05-20T02:06:01Z","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/2605.20082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standard imitation objective may not fully capture the complex nuances of human driving preferences. Meanwhile, recent advances in vision-language models (VLMs) have demonstrated impressive reasoning and commonsense understanding. Building on these capabilities, this paper presents VL-DPO, a vision-language-guided framework that aligns ego-vehicle motion forecasting models with human preferences. Our approach leverages a V","authors_text":"Ghassen Jerfel, Jeonhyung Kang, Khaled S. Refaat, Marina Haliem, Qi Zhao, Zhefan Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T16:36:34Z","title":"VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20082","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":"sha256:9626a0dae490a4b16fc2cf32bb1e7efade346a73015afce258f21d8ec1198110","target":"record","created_at":"2026-05-20T02:06:01Z","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":"562fcf8d5db313547d08265b7cfab101ff2d83bab65961f1813c7b20e663b40b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T16:36:34Z","title_canon_sha256":"9a2cea8cf5ac5aab0772d3e168f0c6cd689394ea060ce041a4070424e7d97bd5"},"schema_version":"1.0","source":{"id":"2605.20082","kind":"arxiv","version":1}},"canonical_sha256":"59f7478bac801d6b330842797ee638eea86c8722a8c34435631f3b14c89be7db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59f7478bac801d6b330842797ee638eea86c8722a8c34435631f3b14c89be7db","first_computed_at":"2026-05-20T02:06:01.426870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:06:01.426870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XLU7+mZ9bRQ2iRN8aYsz7gHtPxxsRgoqBoeS8vsrcob2BcGBwu9LoTn8mXqj5A+ovj/b/XtHkpNTmpg4dQ+qCw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:06:01.427582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9626a0dae490a4b16fc2cf32bb1e7efade346a73015afce258f21d8ec1198110","sha256:90361da68a141db844f4a1fa3e3e8ebbf11462ec1785e99e066d8fd2ce0dc31b"],"state_sha256":"3d49fa18e5473c9e89c37a11bd8d3212a69e23be79eabaac2b457bde66d8c299"}