{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VTWNUPGZ2KJNSLFVSYBF5XXCFR","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":"4d43bfefd7eee6e5e80b89591a2ef8e2eac71b5d3d56de6507b95cb0f207d9bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-03T18:36:52Z","title_canon_sha256":"65eed3b96a33005748b26e989a7e83ff9ea50215fa6d62084718efd4f4dece2f"},"schema_version":"1.0","source":{"id":"2301.01283","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01283","created_at":"2026-07-05T06:51:21Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01283v3","created_at":"2026-07-05T06:51:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01283","created_at":"2026-07-05T06:51:21Z"},{"alias_kind":"pith_short_12","alias_value":"VTWNUPGZ2KJN","created_at":"2026-07-05T06:51:21Z"},{"alias_kind":"pith_short_16","alias_value":"VTWNUPGZ2KJNSLFV","created_at":"2026-07-05T06:51:21Z"},{"alias_kind":"pith_short_8","alias_value":"VTWNUPGZ","created_at":"2026-07-05T06:51:21Z"}],"graph_snapshots":[{"event_id":"sha256:55dc78d2a55e0d4f47ed1fbd0b33be9056864501098a62dceb07b165d9b255ae","target":"graph","created_at":"2026-07-05T06:51:21Z","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/2301.01283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. It achieves 74.1\\% NDS (state-of-the-art with single model) on nuScenes test set while maintaining fast inference speed. Moreover, CMT has a strong","authors_text":"Fan Jia, Jianjian Sun, Junjie Yan, Shuailin Li, Tiancai Wang, Xiangyu Zhang, Yingfei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-03T18:36:52Z","title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01283","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":"sha256:6c3f47b732aa060823c356088ba65a89609060d42aadfa7dfc45ed8f2d9889a5","target":"record","created_at":"2026-07-05T06:51:21Z","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":"4d43bfefd7eee6e5e80b89591a2ef8e2eac71b5d3d56de6507b95cb0f207d9bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-03T18:36:52Z","title_canon_sha256":"65eed3b96a33005748b26e989a7e83ff9ea50215fa6d62084718efd4f4dece2f"},"schema_version":"1.0","source":{"id":"2301.01283","kind":"arxiv","version":3}},"canonical_sha256":"acecda3cd9d292d92cb596025edee22c4a105fe37fd37bde3dd56769a758e4c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acecda3cd9d292d92cb596025edee22c4a105fe37fd37bde3dd56769a758e4c4","first_computed_at":"2026-07-05T06:51:21.472902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:21.472902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IhhRdLayVwgv7KGtDx2paAaLstAIrrYXbmqwwM+/4mqiDR9Mpwz4YJvWzlw1QIPWknYKosP2EOOt5HnOXfd3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:21.473451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.01283","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c3f47b732aa060823c356088ba65a89609060d42aadfa7dfc45ed8f2d9889a5","sha256:55dc78d2a55e0d4f47ed1fbd0b33be9056864501098a62dceb07b165d9b255ae"],"state_sha256":"5fc1463e4540dbda7ea492c0127b566c27b08884d03ebc4c7dc971e42e53d41f"}