{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CJPOKJUDKJPV2LBX43BQCQ2AR4","short_pith_number":"pith:CJPOKJUD","schema_version":"1.0","canonical_sha256":"125ee52683525f5d2c37e6c30143408f2cc5e959c22a4b0b9fe5465d05c25633","source":{"kind":"arxiv","id":"2403.09626","version":1},"attestation_state":"computed","paper":{"title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqi Pei, Guo Chen, Jiahao Wang, Jilan Xu, Kunchang Li, Limin Wang, Tong Lu, Yifei Huang, Zhe Chen, Zhiqi Li","submitted_at":"2024-03-14T17:57:07Z","abstract_excerpt":"Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.g., Mamba, shows promising traits to extend its success in long sequence modeling to video modeling. To assess whether Mamba can be a viable alternative to Transformers in the video understanding domain, in this work, we conduct a comprehensive set of studies, probing different roles Mamba can play in modeling videos, while investigating diverse ta"},"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":"2403.09626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T17:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"f34beacdc6ec5b762fc124f8809f0c3dd18ffa422db42c06fb094bc152bde16a","abstract_canon_sha256":"ad394b71f51381a440d293efa5fa3e3dab09ff7fdbbaeb5f604b6f4f9f0e1663"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:12.282763Z","signature_b64":"j7cOp+N+5Z7JN7pQ1ima3WANkORY/atia90HY5LN3EAbunyqXv5Pyk6HLm5yWB7cFkyjrsIi0wmfna/g9r0UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125ee52683525f5d2c37e6c30143408f2cc5e959c22a4b0b9fe5465d05c25633","last_reissued_at":"2026-07-05T07:56:12.282268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:12.282268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqi Pei, Guo Chen, Jiahao Wang, Jilan Xu, Kunchang Li, Limin Wang, Tong Lu, Yifei Huang, Zhe Chen, Zhiqi Li","submitted_at":"2024-03-14T17:57:07Z","abstract_excerpt":"Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.g., Mamba, shows promising traits to extend its success in long sequence modeling to video modeling. To assess whether Mamba can be a viable alternative to Transformers in the video understanding domain, in this work, we conduct a comprehensive set of studies, probing different roles Mamba can play in modeling videos, while investigating diverse ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09626","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/2403.09626/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":"2403.09626","created_at":"2026-07-05T07:56:12.282326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09626v1","created_at":"2026-07-05T07:56:12.282326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09626","created_at":"2026-07-05T07:56:12.282326+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJPOKJUDKJPV","created_at":"2026-07-05T07:56:12.282326+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJPOKJUDKJPV2LBX","created_at":"2026-07-05T07:56:12.282326+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJPOKJUD","created_at":"2026-07-05T07:56:12.282326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13795","citing_title":"Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27591","citing_title":"ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09164","citing_title":"Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4","json":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4.json","graph_json":"https://pith.science/api/pith-number/CJPOKJUDKJPV2LBX43BQCQ2AR4/graph.json","events_json":"https://pith.science/api/pith-number/CJPOKJUDKJPV2LBX43BQCQ2AR4/events.json","paper":"https://pith.science/paper/CJPOKJUD"},"agent_actions":{"view_html":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4","download_json":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4.json","view_paper":"https://pith.science/paper/CJPOKJUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09626&json=true","fetch_graph":"https://pith.science/api/pith-number/CJPOKJUDKJPV2LBX43BQCQ2AR4/graph.json","fetch_events":"https://pith.science/api/pith-number/CJPOKJUDKJPV2LBX43BQCQ2AR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4/action/storage_attestation","attest_author":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4/action/author_attestation","sign_citation":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4/action/citation_signature","submit_replication":"https://pith.science/pith/CJPOKJUDKJPV2LBX43BQCQ2AR4/action/replication_record"}},"created_at":"2026-07-05T07:56:12.282326+00:00","updated_at":"2026-07-05T07:56:12.282326+00:00"}