{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DHHI2GTCXKW4AJGTECUGD57GY7","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":"b31f3019b246ca084991f13ed207c8194d27ed5ef76864488f7c830af288b998","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T16:35:47Z","title_canon_sha256":"2004ab7caade1527d78d72d5957cec67ee0252b6e1cd61a746398c88a322c397"},"schema_version":"1.0","source":{"id":"2406.10165","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10165","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10165v1","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10165","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"pith_short_12","alias_value":"DHHI2GTCXKW4","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"pith_short_16","alias_value":"DHHI2GTCXKW4AJGT","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"pith_short_8","alias_value":"DHHI2GTC","created_at":"2026-07-05T08:32:06Z"}],"graph_snapshots":[{"event_id":"sha256:d04f154e2780443e6e3359e9620d1483b71dcb3d4f18b135aae27b4cca9f8b5a","target":"graph","created_at":"2026-07-05T08:32:06Z","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/2406.10165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this technical report, we present CarLLaVA, a Vision Language Model (VLM) for autonomous driving, developed for the CARLA Autonomous Driving Challenge 2.0. CarLLaVA uses the vision encoder of the LLaVA VLM and the LLaMA architecture as backbone, achieving state-of-the-art closed-loop driving performance with only camera input and without the need for complex or expensive labels. Additionally, we show preliminary results on predicting language commentary alongside the driving output. CarLLaVA uses a semi-disentangled output representation of both path predictions and waypoints, getting the a","authors_text":"Alice Karnsund, Ana-Maria Marcu, Benoit Hanotte, Elahe Arani, Jamie Shotton, Jan H\\\"unermann, Katrin Renz, Long Chen, Oleg Sinavski","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T16:35:47Z","title":"CarLLaVA: Vision language models for camera-only closed-loop driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10165","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:fd74cfb9c45c99f68387d1cf20a2fb09246a940e252bd37d1f6354cd534bec0f","target":"record","created_at":"2026-07-05T08:32:06Z","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":"b31f3019b246ca084991f13ed207c8194d27ed5ef76864488f7c830af288b998","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T16:35:47Z","title_canon_sha256":"2004ab7caade1527d78d72d5957cec67ee0252b6e1cd61a746398c88a322c397"},"schema_version":"1.0","source":{"id":"2406.10165","kind":"arxiv","version":1}},"canonical_sha256":"19ce8d1a62baadc024d320a861f7e6c7daa8e71f39a06eaa01998758f3883e32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19ce8d1a62baadc024d320a861f7e6c7daa8e71f39a06eaa01998758f3883e32","first_computed_at":"2026-07-05T08:32:06.350780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:06.350780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c2nlb+PKXsdk6RRBl5iO9JMtBNGtShMo4/qpwM4vdPFLv9KXF0k7jjyS40Iv2EverjrQy8Ynuz+PpgoKEQSVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:06.351416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10165","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd74cfb9c45c99f68387d1cf20a2fb09246a940e252bd37d1f6354cd534bec0f","sha256:d04f154e2780443e6e3359e9620d1483b71dcb3d4f18b135aae27b4cca9f8b5a"],"state_sha256":"4247d231645dfcc03c5bc77fc3422e8fbdba48b0f446c2a46c7d5bb5760daf78"}