{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6L6PHWV7GF5LYRG4T7E3RTSFUI","short_pith_number":"pith:6L6PHWV7","schema_version":"1.0","canonical_sha256":"f2fcf3dabf317abc44dc9fc9b8ce45a221f315c4315a513a3a709ec8aacd0251","source":{"kind":"arxiv","id":"2405.03025","version":2},"attestation_state":"computed","paper":{"title":"Matten: Video Generation with Mamba-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancheng Huang, Lin Ma, Xiaopeng Sun, Yu Gao, Yujie Zhong, Zequn Jie","submitted_at":"2024-05-05T18:36:45Z","abstract_excerpt":"In this paper, we introduce Matten, a cutting-edge latent diffusion model with Mamba-Attention architecture for video generation. With minimal computational cost, Matten employs spatial-temporal attention for local video content modeling and bidirectional Mamba for global video content modeling. Our comprehensive experimental evaluation demonstrates that Matten has competitive performance with the current Transformer-based and GAN-based models in benchmark performance, achieving superior FVD scores and efficiency. Additionally, we observe a direct positive correlation between the complexity of"},"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":"2405.03025","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T18:36:45Z","cross_cats_sorted":[],"title_canon_sha256":"0332a1b34cc06b8fedb6796e25333f83e598849bab6aad94a6b1f65340613134","abstract_canon_sha256":"364d4d5aad3ad6dcc278ef7db79c99a678ce95f7cba617e14a44c80751a1f86c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:32.917941Z","signature_b64":"m1RauG6ctsrkSUlshK4ifWYrmFA3D21HofkmpbpcPfOu87bqCKuUv92pTMjJzdP191tr4d0saXGGjDv5NxuLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2fcf3dabf317abc44dc9fc9b8ce45a221f315c4315a513a3a709ec8aacd0251","last_reissued_at":"2026-07-05T08:17:32.917403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:32.917403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matten: Video Generation with Mamba-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancheng Huang, Lin Ma, Xiaopeng Sun, Yu Gao, Yujie Zhong, Zequn Jie","submitted_at":"2024-05-05T18:36:45Z","abstract_excerpt":"In this paper, we introduce Matten, a cutting-edge latent diffusion model with Mamba-Attention architecture for video generation. With minimal computational cost, Matten employs spatial-temporal attention for local video content modeling and bidirectional Mamba for global video content modeling. Our comprehensive experimental evaluation demonstrates that Matten has competitive performance with the current Transformer-based and GAN-based models in benchmark performance, achieving superior FVD scores and efficiency. Additionally, we observe a direct positive correlation between the complexity of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03025","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/2405.03025/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":"2405.03025","created_at":"2026-07-05T08:17:32.917465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03025v2","created_at":"2026-07-05T08:17:32.917465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03025","created_at":"2026-07-05T08:17:32.917465+00:00"},{"alias_kind":"pith_short_12","alias_value":"6L6PHWV7GF5L","created_at":"2026-07-05T08:17:32.917465+00:00"},{"alias_kind":"pith_short_16","alias_value":"6L6PHWV7GF5LYRG4","created_at":"2026-07-05T08:17:32.917465+00:00"},{"alias_kind":"pith_short_8","alias_value":"6L6PHWV7","created_at":"2026-07-05T08:17:32.917465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI","json":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI.json","graph_json":"https://pith.science/api/pith-number/6L6PHWV7GF5LYRG4T7E3RTSFUI/graph.json","events_json":"https://pith.science/api/pith-number/6L6PHWV7GF5LYRG4T7E3RTSFUI/events.json","paper":"https://pith.science/paper/6L6PHWV7"},"agent_actions":{"view_html":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI","download_json":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI.json","view_paper":"https://pith.science/paper/6L6PHWV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03025&json=true","fetch_graph":"https://pith.science/api/pith-number/6L6PHWV7GF5LYRG4T7E3RTSFUI/graph.json","fetch_events":"https://pith.science/api/pith-number/6L6PHWV7GF5LYRG4T7E3RTSFUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI/action/storage_attestation","attest_author":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI/action/author_attestation","sign_citation":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI/action/citation_signature","submit_replication":"https://pith.science/pith/6L6PHWV7GF5LYRG4T7E3RTSFUI/action/replication_record"}},"created_at":"2026-07-05T08:17:32.917465+00:00","updated_at":"2026-07-05T08:17:32.917465+00:00"}