{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TSIP47QH5R3EFBQZQAXWHHU4HZ","short_pith_number":"pith:TSIP47QH","schema_version":"1.0","canonical_sha256":"9c90fe7e07ec76428619802f639e9c3e72fba6bbeed9acb4cc2ae839306fd27e","source":{"kind":"arxiv","id":"2409.07267","version":5},"attestation_state":"computed","paper":{"title":"MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enming Zhang, Min Huang, Qinghai Miao, Xingyuan Dai, Yisheng Lv","submitted_at":"2024-09-11T13:43:01Z","abstract_excerpt":"Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely on computationally expensive visual encoders and large language models (LLMs), making them difficult to deploy in real-world scenarios and real-time applications. Meanwhile, most existing VLMs lack the ability to process multiple images, making it difficult to adapt to multi-camera perception in autonomous driving. To address these issues, we propose a novel "},"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":"2409.07267","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T13:43:01Z","cross_cats_sorted":[],"title_canon_sha256":"9fe439e630a8410ca36ddf495b23b8b68512abf9dc9eded747624a5d51ecde51","abstract_canon_sha256":"be8217ceca9fef3b9af1cc87adcd00f81ba023746b950d64eea4f5eddf132a05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:23.294301Z","signature_b64":"sYDydU86XbTxX7EreYxyzpIEcSLTEwercr7gkw9Efs7A+lCGgeU4HCOvtTv0Xjla71AE0wKGDrWDs6NR2IIzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c90fe7e07ec76428619802f639e9c3e72fba6bbeed9acb4cc2ae839306fd27e","last_reissued_at":"2026-07-05T11:06:23.293720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:23.293720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enming Zhang, Min Huang, Qinghai Miao, Xingyuan Dai, Yisheng Lv","submitted_at":"2024-09-11T13:43:01Z","abstract_excerpt":"Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely on computationally expensive visual encoders and large language models (LLMs), making them difficult to deploy in real-world scenarios and real-time applications. Meanwhile, most existing VLMs lack the ability to process multiple images, making it difficult to adapt to multi-camera perception in autonomous driving. To address these issues, we propose a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07267","kind":"arxiv","version":5},"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/2409.07267/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":"2409.07267","created_at":"2026-07-05T11:06:23.293785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07267v5","created_at":"2026-07-05T11:06:23.293785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07267","created_at":"2026-07-05T11:06:23.293785+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSIP47QH5R3E","created_at":"2026-07-05T11:06:23.293785+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSIP47QH5R3EFBQZ","created_at":"2026-07-05T11:06:23.293785+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSIP47QH","created_at":"2026-07-05T11:06:23.293785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.16518","citing_title":"MiMo-Embodied: X-Embodied Foundation Model Technical Report","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ","json":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ.json","graph_json":"https://pith.science/api/pith-number/TSIP47QH5R3EFBQZQAXWHHU4HZ/graph.json","events_json":"https://pith.science/api/pith-number/TSIP47QH5R3EFBQZQAXWHHU4HZ/events.json","paper":"https://pith.science/paper/TSIP47QH"},"agent_actions":{"view_html":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ","download_json":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ.json","view_paper":"https://pith.science/paper/TSIP47QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07267&json=true","fetch_graph":"https://pith.science/api/pith-number/TSIP47QH5R3EFBQZQAXWHHU4HZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TSIP47QH5R3EFBQZQAXWHHU4HZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/action/storage_attestation","attest_author":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/action/author_attestation","sign_citation":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/action/citation_signature","submit_replication":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/action/replication_record"}},"created_at":"2026-07-05T11:06:23.293785+00:00","updated_at":"2026-07-05T11:06:23.293785+00:00"}