{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WIQZNWVAAFJIQ6GTKUDFMITANU","short_pith_number":"pith:WIQZNWVA","schema_version":"1.0","canonical_sha256":"b22196daa001528878d355065622606d3ed8d45bd134c3850dbf23754a987524","source":{"kind":"arxiv","id":"2407.21293","version":1},"attestation_state":"computed","paper":{"title":"SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hong Zhu, Peiru Zheng, Shaohua Wu, Yun Zhao, Zhan Gong","submitted_at":"2024-07-31T02:35:33Z","abstract_excerpt":"Many fields could benefit from the rapid development of the large language models (LLMs). The end-to-end autonomous driving (e2eAD) is one of the typically fields facing new opportunities as the LLMs have supported more and more modalities. Here, by utilizing vision-language model (VLM), we proposed an e2eAD method called SimpleLLM4AD. In our method, the e2eAD task are divided into four stages, which are perception, prediction, planning, and behavior. Each stage consists of several visual question answering (VQA) pairs and VQA pairs interconnect with each other constructing a graph called Grap"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.21293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T02:35:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e124e0ecb3a0fa3c2c461fe67d89c3c25cf583597fe743b157b01081f24fd91","abstract_canon_sha256":"6dbf66c43be79b0c69011fd8dd09721cf7d02395e62c3efef53a0b69a8017c67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:37.219654Z","signature_b64":"8waDYZNBk9X/qVWP6HnwZuMf9ZtGjMAHkFE9hFKh6Gw2a95ZZZFgXf2MkogfbQi1GWyWueNQzNfmOVkrqc6rBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22196daa001528878d355065622606d3ed8d45bd134c3850dbf23754a987524","last_reissued_at":"2026-07-05T08:50:37.219234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:37.219234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hong Zhu, Peiru Zheng, Shaohua Wu, Yun Zhao, Zhan Gong","submitted_at":"2024-07-31T02:35:33Z","abstract_excerpt":"Many fields could benefit from the rapid development of the large language models (LLMs). The end-to-end autonomous driving (e2eAD) is one of the typically fields facing new opportunities as the LLMs have supported more and more modalities. Here, by utilizing vision-language model (VLM), we proposed an e2eAD method called SimpleLLM4AD. In our method, the e2eAD task are divided into four stages, which are perception, prediction, planning, and behavior. Each stage consists of several visual question answering (VQA) pairs and VQA pairs interconnect with each other constructing a graph called Grap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21293","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/2407.21293/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.21293","created_at":"2026-07-05T08:50:37.219297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21293v1","created_at":"2026-07-05T08:50:37.219297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21293","created_at":"2026-07-05T08:50:37.219297+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIQZNWVAAFJI","created_at":"2026-07-05T08:50:37.219297+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIQZNWVAAFJIQ6GT","created_at":"2026-07-05T08:50:37.219297+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIQZNWVA","created_at":"2026-07-05T08:50:37.219297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08170","citing_title":"Learning from Human Driving: A Human-in-the-Loop Online Behavior Cloning Framework for Autonomous Driving","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17685","citing_title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU","json":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU.json","graph_json":"https://pith.science/api/pith-number/WIQZNWVAAFJIQ6GTKUDFMITANU/graph.json","events_json":"https://pith.science/api/pith-number/WIQZNWVAAFJIQ6GTKUDFMITANU/events.json","paper":"https://pith.science/paper/WIQZNWVA"},"agent_actions":{"view_html":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU","download_json":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU.json","view_paper":"https://pith.science/paper/WIQZNWVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21293&json=true","fetch_graph":"https://pith.science/api/pith-number/WIQZNWVAAFJIQ6GTKUDFMITANU/graph.json","fetch_events":"https://pith.science/api/pith-number/WIQZNWVAAFJIQ6GTKUDFMITANU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU/action/storage_attestation","attest_author":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU/action/author_attestation","sign_citation":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU/action/citation_signature","submit_replication":"https://pith.science/pith/WIQZNWVAAFJIQ6GTKUDFMITANU/action/replication_record"}},"created_at":"2026-07-05T08:50:37.219297+00:00","updated_at":"2026-07-05T08:50:37.219297+00:00"}