{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OBXZSEUMMGQJLKQ3CONF3EC3V6","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":"42094772712af359664d4bf1bd100efce357fa17d15cb09a45ff3e2e2a332033","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T06:27:25Z","title_canon_sha256":"c0d75fd1a14a809fd07ab184ad8e693c6308fc873230b632a3f4aea664f7035e"},"schema_version":"1.0","source":{"id":"2309.05257","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05257","created_at":"2026-07-05T06:58:42Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05257v3","created_at":"2026-07-05T06:58:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05257","created_at":"2026-07-05T06:58:42Z"},{"alias_kind":"pith_short_12","alias_value":"OBXZSEUMMGQJ","created_at":"2026-07-05T06:58:42Z"},{"alias_kind":"pith_short_16","alias_value":"OBXZSEUMMGQJLKQ3","created_at":"2026-07-05T06:58:42Z"},{"alias_kind":"pith_short_8","alias_value":"OBXZSEUM","created_at":"2026-07-05T06:58:42Z"}],"graph_snapshots":[{"event_id":"sha256:7be24ebaecf3fcdc7c71833678ba4381e0cf34a1b11e222a9c5747f0d25677ee","target":"graph","created_at":"2026-07-05T06:58:42Z","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/2309.05257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-sensor modal fusion has demonstrated strong advantages in 3D object detection tasks. However, existing methods that fuse multi-modal features require transforming features into the bird's eye view space and may lose certain information on Z-axis, thus leading to inferior performance. To this end, we propose a novel end-to-end multi-modal fusion transformer-based framework, dubbed FusionFormer, that incorporates deformable attention and residual structures within the fusion encoding module. Specifically, by developing a uniform sampling strategy, our method can easily sample from 2D image","authors_text":"Chunyong Hu, Hang Zheng, Jianyun Xu, Kaicheng Yu, Kaixuan Liu, Kun Li, Lingxuan Wang, Maochun Luo, Mingxia Chen, Minzhe Liu, Peihan Hao, Qihao Peng, Weibo Mao, Yiru Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T06:27:25Z","title":"FusionFormer: A Multi-sensory Fusion in Bird's-Eye-View and Temporal Consistent Transformer for 3D Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05257","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":"sha256:57900629d631fa1afe3b20a38ea3db0d16e576c33c4ffc9585ae3e2a6cd1b6dd","target":"record","created_at":"2026-07-05T06:58:42Z","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":"42094772712af359664d4bf1bd100efce357fa17d15cb09a45ff3e2e2a332033","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T06:27:25Z","title_canon_sha256":"c0d75fd1a14a809fd07ab184ad8e693c6308fc873230b632a3f4aea664f7035e"},"schema_version":"1.0","source":{"id":"2309.05257","kind":"arxiv","version":3}},"canonical_sha256":"706f99128c61a095aa1b139a5d905bafa0bd42df115af4fe5d0084169e75243b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"706f99128c61a095aa1b139a5d905bafa0bd42df115af4fe5d0084169e75243b","first_computed_at":"2026-07-05T06:58:42.341511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:42.341511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pSVNIXic84iJEsXbPxZew7j695iqCWfQZuWtcQYgzUF+KNp2C+AcTGpg5Icn6s8j14j/w96XrAEv/VAJkEq8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:42.342077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05257","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57900629d631fa1afe3b20a38ea3db0d16e576c33c4ffc9585ae3e2a6cd1b6dd","sha256:7be24ebaecf3fcdc7c71833678ba4381e0cf34a1b11e222a9c5747f0d25677ee"],"state_sha256":"b4125687e03f85c04daf6ab998370348cf839e1f21e2bbc3de51b240bae13d93"}