{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C6URTIU7XTWRUP74HULGFDONI5","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":"f9a6558dfa6fe7f2749d52e59ee0b6dd88f4da702edb9abdefb4957dc1749f45","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T00:14:13Z","title_canon_sha256":"5c23ac0bd88bd4484ed820bd4b912c8a9a8ad46c2455fa09aef5a0bd45a2cd71"},"schema_version":"1.0","source":{"id":"2411.10639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10639","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10639v2","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10639","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"C6URTIU7XTWR","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"C6URTIU7XTWRUP74","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"C6URTIU7","created_at":"2026-07-05T10:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:0b6ac65f6c34edbf35b9cc4f0a7aca28e7c5a599bea0f749a10822d09f2e2cc6","target":"graph","created_at":"2026-07-05T10:28:26Z","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/2411.10639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment. However, existing approaches treat perception and captioning as separate tasks, focusing on the performance of only one task and overlooking the potential benefits of multimodal alignment. To bridge this gap between modalities, we introduce MTA, a novel multimodal task alignment framework that boosts both BEV perception and captioning. MTA consists of two ke","authors_text":"Abhirup Mallik, Burhaneddin Yaman, Feng Tao, Jingru Luo, Liu Ren, Xin Ye, Yunsheng Ma, Ziran Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T00:14:13Z","title":"MTA: Multimodal Task Alignment for BEV Perception and Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10639","kind":"arxiv","version":2},"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":"sha256:5cf6c38b1d2926cb118cad34c60e7aaedf63947dd9a2a0e5136dbc6c6a828410","target":"record","created_at":"2026-07-05T10:28:26Z","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":"f9a6558dfa6fe7f2749d52e59ee0b6dd88f4da702edb9abdefb4957dc1749f45","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T00:14:13Z","title_canon_sha256":"5c23ac0bd88bd4484ed820bd4b912c8a9a8ad46c2455fa09aef5a0bd45a2cd71"},"schema_version":"1.0","source":{"id":"2411.10639","kind":"arxiv","version":2}},"canonical_sha256":"17a919a29fbced1a3ffc3d16628dcd477cfc70d50fdaa6db611bf8df1ec1fdbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17a919a29fbced1a3ffc3d16628dcd477cfc70d50fdaa6db611bf8df1ec1fdbb","first_computed_at":"2026-07-05T10:28:26.417142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:26.417142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XWqppsjqIQpjxnwCJFsg6fdEoj3zMqTStPbfoYjOaAO59R+NBHsLAxP9GaLU7m7umvSJhGEPUR2D3xbbLPOqDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:26.417746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cf6c38b1d2926cb118cad34c60e7aaedf63947dd9a2a0e5136dbc6c6a828410","sha256:0b6ac65f6c34edbf35b9cc4f0a7aca28e7c5a599bea0f749a10822d09f2e2cc6"],"state_sha256":"9c91cbf3c3e2eafbee3c70fb04ee5aa56802ff24383814400bd9c63571d532be"}