{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TD5NMUP6WKCRFJ3Z67FNV5WTQK","short_pith_number":"pith:TD5NMUP6","canonical_record":{"source":{"id":"2411.12980","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T02:14:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"beb8684cdf739e945c54551144b28d83885d0ed4c6dfebc0e3ec6416b57b32e7","abstract_canon_sha256":"7c80386e2ab5ab1a5e964fce0e0e6387610b1f5588ca487d924bf26d9d3562fc"},"schema_version":"1.0"},"canonical_sha256":"98fad651feb28512a779f7cadaf6d382b75a391ac05b5dede39688213297d486","source":{"kind":"arxiv","id":"2411.12980","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12980","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12980v3","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12980","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"TD5NMUP6WKCR","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"TD5NMUP6WKCRFJ3Z","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"TD5NMUP6","created_at":"2026-07-05T10:18:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TD5NMUP6WKCRFJ3Z67FNV5WTQK","target":"record","payload":{"canonical_record":{"source":{"id":"2411.12980","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T02:14:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"beb8684cdf739e945c54551144b28d83885d0ed4c6dfebc0e3ec6416b57b32e7","abstract_canon_sha256":"7c80386e2ab5ab1a5e964fce0e0e6387610b1f5588ca487d924bf26d9d3562fc"},"schema_version":"1.0"},"canonical_sha256":"98fad651feb28512a779f7cadaf6d382b75a391ac05b5dede39688213297d486","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:11.111257Z","signature_b64":"imgJIWLfgZcI4QhkOe49SiWySByE2zYQrJ84KQntZ/NMxfbeV8Yg4qfN23xc6/+JvoNBRvsTiSgIgRg3ursJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98fad651feb28512a779f7cadaf6d382b75a391ac05b5dede39688213297d486","last_reissued_at":"2026-07-05T10:18:11.110804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:11.110804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.12980","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4a/V9xEB+UKP1FxYk1Sjrw0xJ41sALIjT3+vNXX9ZSem5Bp605YjTnPFmY/KKcz57BxLH2uo2FZkBxJUfPlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:09:25.466687Z"},"content_sha256":"f87a81f2665a8d2529e015f980c69bead824150e5a790bca86ee776407463234","schema_version":"1.0","event_id":"sha256:f87a81f2665a8d2529e015f980c69bead824150e5a790bca86ee776407463234"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TD5NMUP6WKCRFJ3Z67FNV5WTQK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baoyun Peng, Bharadwaj Veeravalli, Siwen Jiao, Wangqun Chen, Yangyi Fang","submitted_at":"2024-11-20T02:14:07Z","abstract_excerpt":"Recent advancements in Visual Language Models (VLMs) have made them crucial for visual question answering (VQA) in autonomous driving, enabling natural human-vehicle interactions. However, existing methods often struggle in dynamic driving environments, as they usually focus on static images or videos and rely on downsampling to manage computational costs. This results in the loss of critical details and the difficulty in effectively integrating spatial and temporal information, undermining fine-grained perception and temporal coherence essential for effective decision-making. To tackle these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12980","kind":"arxiv","version":3},"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/2411.12980/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":"2026-07-05T10:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQ/LQXmoXnVXBR9CPdPS3+e7sK8yAnna77YdYtoNNs/jD+TOj4PEDXhzelqZZL/iEMkGuNeh1Th0RV4k5UgiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:09:25.467429Z"},"content_sha256":"71597c11d6ad8fd453a8360a73b0ddbf504c2765fd856d962a9042e653571356","schema_version":"1.0","event_id":"sha256:71597c11d6ad8fd453a8360a73b0ddbf504c2765fd856d962a9042e653571356"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK/bundle.json","state_url":"https://pith.science/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK/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":"2026-08-19T15:09:25Z","links":{"resolver":"https://pith.science/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK","bundle":"https://pith.science/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK/bundle.json","state":"https://pith.science/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TD5NMUP6WKCRFJ3Z67FNV5WTQK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TD5NMUP6WKCRFJ3Z67FNV5WTQK","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":"7c80386e2ab5ab1a5e964fce0e0e6387610b1f5588ca487d924bf26d9d3562fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T02:14:07Z","title_canon_sha256":"beb8684cdf739e945c54551144b28d83885d0ed4c6dfebc0e3ec6416b57b32e7"},"schema_version":"1.0","source":{"id":"2411.12980","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12980","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12980v3","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12980","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"TD5NMUP6WKCR","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"TD5NMUP6WKCRFJ3Z","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"TD5NMUP6","created_at":"2026-07-05T10:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:71597c11d6ad8fd453a8360a73b0ddbf504c2765fd856d962a9042e653571356","target":"graph","created_at":"2026-07-05T10:18:11Z","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/2411.12980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Visual Language Models (VLMs) have made them crucial for visual question answering (VQA) in autonomous driving, enabling natural human-vehicle interactions. However, existing methods often struggle in dynamic driving environments, as they usually focus on static images or videos and rely on downsampling to manage computational costs. This results in the loss of critical details and the difficulty in effectively integrating spatial and temporal information, undermining fine-grained perception and temporal coherence essential for effective decision-making. To tackle these ","authors_text":"Baoyun Peng, Bharadwaj Veeravalli, Siwen Jiao, Wangqun Chen, Yangyi Fang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T02:14:07Z","title":"LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12980","kind":"arxiv","version":3},"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:f87a81f2665a8d2529e015f980c69bead824150e5a790bca86ee776407463234","target":"record","created_at":"2026-07-05T10:18:11Z","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":"7c80386e2ab5ab1a5e964fce0e0e6387610b1f5588ca487d924bf26d9d3562fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T02:14:07Z","title_canon_sha256":"beb8684cdf739e945c54551144b28d83885d0ed4c6dfebc0e3ec6416b57b32e7"},"schema_version":"1.0","source":{"id":"2411.12980","kind":"arxiv","version":3}},"canonical_sha256":"98fad651feb28512a779f7cadaf6d382b75a391ac05b5dede39688213297d486","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98fad651feb28512a779f7cadaf6d382b75a391ac05b5dede39688213297d486","first_computed_at":"2026-07-05T10:18:11.110804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:11.110804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"imgJIWLfgZcI4QhkOe49SiWySByE2zYQrJ84KQntZ/NMxfbeV8Yg4qfN23xc6/+JvoNBRvsTiSgIgRg3ursJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:11.111257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12980","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f87a81f2665a8d2529e015f980c69bead824150e5a790bca86ee776407463234","sha256:71597c11d6ad8fd453a8360a73b0ddbf504c2765fd856d962a9042e653571356"],"state_sha256":"aab3a8e42090511ff832db805298538a7679aebfa586b8ebbd05be4b62c61cff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D9JPRVOgIlNXOOs+hGA0FSX6gKhyt2OY6Z8qrzB+9GUoeKHTtFzXdkQNkg0eEFc3GIXdxB9N2TENlxvBWjG2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:09:25.474015Z","bundle_sha256":"4a572680d47f678b834e0e089ad382ee3b52cb0a23c3b387dc73620bc5e4bb22"}}