{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C7BIGHQRUWKU66J6P2BL2EOI2N","short_pith_number":"pith:C7BIGHQR","schema_version":"1.0","canonical_sha256":"17c2831e11a5954f793e7e82bd11c8d34f4aa241492477bfa37f0037616115a5","source":{"kind":"arxiv","id":"2403.06977","version":2},"attestation_state":"computed","paper":{"title":"VideoMamba: State Space Model for Efficient Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Limin Wang, Xinhao Li, Yali Wang, Yinan He, Yi Wang, Yu Qiao","submitted_at":"2024-03-11T17:59:34Z","abstract_excerpt":"Addressing the dual challenges of local redundancy and global dependencies in video understanding, this work innovatively adapts the Mamba to the video domain. The proposed VideoMamba overcomes the limitations of existing 3D convolution neural networks and video transformers. Its linear-complexity operator enables efficient long-term modeling, which is crucial for high-resolution long video understanding. Extensive evaluations reveal VideoMamba's four core abilities: (1) Scalability in the visual domain without extensive dataset pretraining, thanks to a novel self-distillation technique; (2) S"},"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":"2403.06977","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"9b931b17f33b4714b435456e026663ec44770555fcb0398ffecffa046c7771a5","abstract_canon_sha256":"58bf23d5b2ee37082adb88700ced7c11d91e14b5cf2e0187a7042821ab1ece4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:14.806931Z","signature_b64":"5ShV0SRs1Za/cn8Oucr1+hr2lkXD1fpGR8n2bPRD1xiDXTBQuHxtWK/5gzjbBsaCyVoYJVod8Xr34usG8eVUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17c2831e11a5954f793e7e82bd11c8d34f4aa241492477bfa37f0037616115a5","last_reissued_at":"2026-07-05T07:55:14.806433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:14.806433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMamba: State Space Model for Efficient Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Limin Wang, Xinhao Li, Yali Wang, Yinan He, Yi Wang, Yu Qiao","submitted_at":"2024-03-11T17:59:34Z","abstract_excerpt":"Addressing the dual challenges of local redundancy and global dependencies in video understanding, this work innovatively adapts the Mamba to the video domain. The proposed VideoMamba overcomes the limitations of existing 3D convolution neural networks and video transformers. Its linear-complexity operator enables efficient long-term modeling, which is crucial for high-resolution long video understanding. Extensive evaluations reveal VideoMamba's four core abilities: (1) Scalability in the visual domain without extensive dataset pretraining, thanks to a novel self-distillation technique; (2) S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06977","kind":"arxiv","version":2},"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/2403.06977/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":"2403.06977","created_at":"2026-07-05T07:55:14.806493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06977v2","created_at":"2026-07-05T07:55:14.806493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06977","created_at":"2026-07-05T07:55:14.806493+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7BIGHQRUWKU","created_at":"2026-07-05T07:55:14.806493+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7BIGHQRUWKU66J6","created_at":"2026-07-05T07:55:14.806493+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7BIGHQR","created_at":"2026-07-05T07:55:14.806493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25324","citing_title":"Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N","json":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N.json","graph_json":"https://pith.science/api/pith-number/C7BIGHQRUWKU66J6P2BL2EOI2N/graph.json","events_json":"https://pith.science/api/pith-number/C7BIGHQRUWKU66J6P2BL2EOI2N/events.json","paper":"https://pith.science/paper/C7BIGHQR"},"agent_actions":{"view_html":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N","download_json":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N.json","view_paper":"https://pith.science/paper/C7BIGHQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06977&json=true","fetch_graph":"https://pith.science/api/pith-number/C7BIGHQRUWKU66J6P2BL2EOI2N/graph.json","fetch_events":"https://pith.science/api/pith-number/C7BIGHQRUWKU66J6P2BL2EOI2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N/action/storage_attestation","attest_author":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N/action/author_attestation","sign_citation":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N/action/citation_signature","submit_replication":"https://pith.science/pith/C7BIGHQRUWKU66J6P2BL2EOI2N/action/replication_record"}},"created_at":"2026-07-05T07:55:14.806493+00:00","updated_at":"2026-07-05T07:55:14.806493+00:00"}