{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TSIP47QH5R3EFBQZQAXWHHU4HZ","short_pith_number":"pith:TSIP47QH","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"},"canonical_sha256":"9c90fe7e07ec76428619802f639e9c3e72fba6bbeed9acb4cc2ae839306fd27e","source":{"kind":"arxiv","id":"2409.07267","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07267","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07267v5","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07267","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_12","alias_value":"TSIP47QH5R3E","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_16","alias_value":"TSIP47QH5R3EFBQZ","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_8","alias_value":"TSIP47QH","created_at":"2026-07-05T11:06:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TSIP47QH5R3EFBQZQAXWHHU4HZ","target":"record","payload":{"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"},"canonical_sha256":"9c90fe7e07ec76428619802f639e9c3e72fba6bbeed9acb4cc2ae839306fd27e","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"},"source_kind":"arxiv","source_id":"2409.07267","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U3Tl67W8ofj39zA9xSjOOP7E81CMtNoxTcGMO2nSfAzsj9kmtegqb5G+uFqndcktZ8zIwYCYuBRuOoV+jSMwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:02:18.620045Z"},"content_sha256":"dabff5a5636ad642bec2892eae9c26bb969b8863f513cc2a1befb3fe7e24ee8c","schema_version":"1.0","event_id":"sha256:dabff5a5636ad642bec2892eae9c26bb969b8863f513cc2a1befb3fe7e24ee8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TSIP47QH5R3EFBQZQAXWHHU4HZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Mp1c1ACFCAenfeC9tppCP2T6g4xokehYGBzk9ApTHRz6gTb8NdtgEQ4O/XI4fOjdd31k1VqKSzejA3aLruwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:02:18.620544Z"},"content_sha256":"76b4a3c659ec14c295f282cf3b77949ed22a2a29fdd7074174cd99f418fa94eb","schema_version":"1.0","event_id":"sha256:76b4a3c659ec14c295f282cf3b77949ed22a2a29fdd7074174cd99f418fa94eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/bundle.json","state_url":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:02:18Z","links":{"resolver":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ","bundle":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/bundle.json","state":"https://pith.science/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSIP47QH5R3EFBQZQAXWHHU4HZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TSIP47QH5R3EFBQZQAXWHHU4HZ","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":"be8217ceca9fef3b9af1cc87adcd00f81ba023746b950d64eea4f5eddf132a05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T13:43:01Z","title_canon_sha256":"9fe439e630a8410ca36ddf495b23b8b68512abf9dc9eded747624a5d51ecde51"},"schema_version":"1.0","source":{"id":"2409.07267","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07267","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07267v5","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07267","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_12","alias_value":"TSIP47QH5R3E","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_16","alias_value":"TSIP47QH5R3EFBQZ","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_8","alias_value":"TSIP47QH","created_at":"2026-07-05T11:06:23Z"}],"graph_snapshots":[{"event_id":"sha256:76b4a3c659ec14c295f282cf3b77949ed22a2a29fdd7074174cd99f418fa94eb","target":"graph","created_at":"2026-07-05T11:06:23Z","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/2409.07267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Enming Zhang, Min Huang, Qinghai Miao, Xingyuan Dai, Yisheng Lv","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T13:43:01Z","title":"MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07267","kind":"arxiv","version":5},"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:dabff5a5636ad642bec2892eae9c26bb969b8863f513cc2a1befb3fe7e24ee8c","target":"record","created_at":"2026-07-05T11:06:23Z","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":"be8217ceca9fef3b9af1cc87adcd00f81ba023746b950d64eea4f5eddf132a05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T13:43:01Z","title_canon_sha256":"9fe439e630a8410ca36ddf495b23b8b68512abf9dc9eded747624a5d51ecde51"},"schema_version":"1.0","source":{"id":"2409.07267","kind":"arxiv","version":5}},"canonical_sha256":"9c90fe7e07ec76428619802f639e9c3e72fba6bbeed9acb4cc2ae839306fd27e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c90fe7e07ec76428619802f639e9c3e72fba6bbeed9acb4cc2ae839306fd27e","first_computed_at":"2026-07-05T11:06:23.293720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:23.293720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sYDydU86XbTxX7EreYxyzpIEcSLTEwercr7gkw9Efs7A+lCGgeU4HCOvtTv0Xjla71AE0wKGDrWDs6NR2IIzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:23.294301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07267","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dabff5a5636ad642bec2892eae9c26bb969b8863f513cc2a1befb3fe7e24ee8c","sha256:76b4a3c659ec14c295f282cf3b77949ed22a2a29fdd7074174cd99f418fa94eb"],"state_sha256":"51f64d69c94f701a3726cb6db4e6700c34c1eef17f3cfdca801cde9e79a27394"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcFI+FAVovHzF4K8e0PI1PEiyp8RcFYhL0DjXbajAJoh8tlnX34t7UfD1WzRRPw5gqN30S7Z+UiMWOLwyx00DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:02:18.623761Z","bundle_sha256":"15cc2aa359966546a7e4b427b53f47c298b962e56c8939335807e94f124a9f3c"}}