{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q3E7G5X5AEACPKJSFAAJTC4IMW","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":"275817da5089e670bee3c6f16e4e2dcc4d3727c852a2746a3756ba1f7a80d78d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T15:50:30Z","title_canon_sha256":"45c93eb6bb04c8966943a484d47bb02d28f63ed583d618024fc11384d86cc0f4"},"schema_version":"1.0","source":{"id":"2411.05898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05898","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05898v1","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05898","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"Q3E7G5X5AEAC","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"Q3E7G5X5AEACPKJS","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"Q3E7G5X5","created_at":"2026-07-05T09:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:43487ebd7f9de9f31b4e6e712236d2e060007dc09ecd9ded4c1e1f70835199e5","target":"graph","created_at":"2026-07-05T09:33:12Z","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/2411.05898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel framework for enhancing visual comprehension in autonomous driving systems by integrating visual language models (VLMs) with additional visual perception module specialised in object detection. We extend the Llama-Adapter architecture by incorporating a YOLOS-based detection network alongside the CLIP perception network, addressing limitations in object detection and localisation. Our approach introduces camera ID-separators to improve multi-view processing, crucial for comprehensive environmental awareness. Experiments on the DriveLM visual question answering","authors_text":"Jiaxu Liu, Linfeng He, Sihao Wu, Xiaowei Huang, Yiming Sun","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T15:50:30Z","title":"Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05898","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:a9558ee2b18722e7d0a2ace0880022c318c4b7610ba8bd5d53b7bcebf56de22e","target":"record","created_at":"2026-07-05T09:33:12Z","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":"275817da5089e670bee3c6f16e4e2dcc4d3727c852a2746a3756ba1f7a80d78d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T15:50:30Z","title_canon_sha256":"45c93eb6bb04c8966943a484d47bb02d28f63ed583d618024fc11384d86cc0f4"},"schema_version":"1.0","source":{"id":"2411.05898","kind":"arxiv","version":1}},"canonical_sha256":"86c9f376fd010027a9322800998b88658345f2ea27b625abfebe0ebeaca84c99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86c9f376fd010027a9322800998b88658345f2ea27b625abfebe0ebeaca84c99","first_computed_at":"2026-07-05T09:33:12.954780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:12.954780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gkGFbQPYmnNLOwbe9QyNLSLpY9CJiVvBGQlYVZAhIMePu6KAR8BRvrNHtyS4q3omPlIzrQAYlGhBPTQJB6kPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:12.955245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9558ee2b18722e7d0a2ace0880022c318c4b7610ba8bd5d53b7bcebf56de22e","sha256:43487ebd7f9de9f31b4e6e712236d2e060007dc09ecd9ded4c1e1f70835199e5"],"state_sha256":"dbe8f95b545cf21134b70d96004400234c9f5c1b3254bbabd2bdde1093530885"}