{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OIJCI2MKJNB33HZXFE6MVCZABB","short_pith_number":"pith:OIJCI2MK","schema_version":"1.0","canonical_sha256":"721224698a4b43bd9f37293cca8b2008663f9e734c572e21fac4d580588ff6ee","source":{"kind":"arxiv","id":"2411.13628","version":1},"attestation_state":"computed","paper":{"title":"MambaDETR: Query-based Temporal Modeling using State Space Model for Multi-View 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Xue, Ke Lu, Tong Ning, Xirui Jiang","submitted_at":"2024-11-20T14:47:18Z","abstract_excerpt":"Utilizing temporal information to improve the performance of 3D detection has made great progress recently in the field of autonomous driving. Traditional transformer-based temporal fusion methods suffer from quadratic computational cost and information decay as the length of the frame sequence increases. In this paper, we propose a novel method called MambaDETR, whose main idea is to implement temporal fusion in the efficient state space. Moreover, we design a Motion Elimination module to remove the relatively static objects for temporal fusion. On the standard nuScenes benchmark, our propose"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.13628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T14:47:18Z","cross_cats_sorted":[],"title_canon_sha256":"8df12bb88157c5f6f1cd496babb92e42a9587f71b787038bb9bd86c7bfd9cb24","abstract_canon_sha256":"bba7ab452d3eed7c7e7a5b453848f8973cd7e76a85ba0f00e7c831bed8d7d6e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:34.721208Z","signature_b64":"IuIHPi0SWWxSozZwpEnBEC1Y1ArSs9uQbTZsimXV74Y/3EimZkXqCg0/RIaP/HexwdHiU4XQvXHv99BDkQAcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"721224698a4b43bd9f37293cca8b2008663f9e734c572e21fac4d580588ff6ee","last_reissued_at":"2026-07-05T09:38:34.720762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:34.720762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaDETR: Query-based Temporal Modeling using State Space Model for Multi-View 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Xue, Ke Lu, Tong Ning, Xirui Jiang","submitted_at":"2024-11-20T14:47:18Z","abstract_excerpt":"Utilizing temporal information to improve the performance of 3D detection has made great progress recently in the field of autonomous driving. Traditional transformer-based temporal fusion methods suffer from quadratic computational cost and information decay as the length of the frame sequence increases. In this paper, we propose a novel method called MambaDETR, whose main idea is to implement temporal fusion in the efficient state space. Moreover, we design a Motion Elimination module to remove the relatively static objects for temporal fusion. On the standard nuScenes benchmark, our propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13628","kind":"arxiv","version":1},"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/2411.13628/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.13628","created_at":"2026-07-05T09:38:34.720817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13628v1","created_at":"2026-07-05T09:38:34.720817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13628","created_at":"2026-07-05T09:38:34.720817+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIJCI2MKJNB3","created_at":"2026-07-05T09:38:34.720817+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIJCI2MKJNB33HZX","created_at":"2026-07-05T09:38:34.720817+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIJCI2MK","created_at":"2026-07-05T09:38:34.720817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07161","citing_title":"A Survey on Mamba Architecture for Vision Applications","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB","json":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB.json","graph_json":"https://pith.science/api/pith-number/OIJCI2MKJNB33HZXFE6MVCZABB/graph.json","events_json":"https://pith.science/api/pith-number/OIJCI2MKJNB33HZXFE6MVCZABB/events.json","paper":"https://pith.science/paper/OIJCI2MK"},"agent_actions":{"view_html":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB","download_json":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB.json","view_paper":"https://pith.science/paper/OIJCI2MK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13628&json=true","fetch_graph":"https://pith.science/api/pith-number/OIJCI2MKJNB33HZXFE6MVCZABB/graph.json","fetch_events":"https://pith.science/api/pith-number/OIJCI2MKJNB33HZXFE6MVCZABB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB/action/storage_attestation","attest_author":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB/action/author_attestation","sign_citation":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB/action/citation_signature","submit_replication":"https://pith.science/pith/OIJCI2MKJNB33HZXFE6MVCZABB/action/replication_record"}},"created_at":"2026-07-05T09:38:34.720817+00:00","updated_at":"2026-07-05T09:38:34.720817+00:00"}