{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MWZITRRCRMTRF3SDS3DPFARO7R","short_pith_number":"pith:MWZITRRC","schema_version":"1.0","canonical_sha256":"65b289c6228b2712ee4396c6f2822efc6c932a1bdecbb98962086b6a31e1bd30","source":{"kind":"arxiv","id":"2607.14711","version":1},"attestation_state":"computed","paper":{"title":"VideoSEMA: a scalable and efficient Mamba-like attention for video understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fanghui Xue andShuai Zhang, Jack Xin, Jiancheng Lyu, Nhat Thanh Tran, Yingyong Qi, Yunling Zheng","submitted_at":"2026-07-16T08:22:08Z","abstract_excerpt":"We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time. In each frame, SEMA attention applies a local window attention in parallel with a global averaging in a Mamba macro-architecture, which is called Mamba-like. Under certain rank conditions, we prove that the computationally cheaper split space-time attention is equivalent to full space-time attention. On benchmark K400 data sets, VideoSEMA out-performs heavier vision transfor"},"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":"2607.14711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T08:22:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85bc34fc5759954d101b3a057444d4a0b4c5a7e68b4cba30f8b69292f3fe9668","abstract_canon_sha256":"b38a75ecd8539717f96d715c003585e909f7a72745bc26e48955c648a191a47e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:26.969969Z","signature_b64":"rxPM1FinaM28brA7qG7Agot292nOtKSnarzLMHVtslz5qIiEwW1/ASTQH/CQtmv6N7H5v7mg7ZrpEWmwqZVrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65b289c6228b2712ee4396c6f2822efc6c932a1bdecbb98962086b6a31e1bd30","last_reissued_at":"2026-07-17T01:21:26.969095Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:26.969095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoSEMA: a scalable and efficient Mamba-like attention for video understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fanghui Xue andShuai Zhang, Jack Xin, Jiancheng Lyu, Nhat Thanh Tran, Yingyong Qi, Yunling Zheng","submitted_at":"2026-07-16T08:22:08Z","abstract_excerpt":"We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time. In each frame, SEMA attention applies a local window attention in parallel with a global averaging in a Mamba macro-architecture, which is called Mamba-like. Under certain rank conditions, we prove that the computationally cheaper split space-time attention is equivalent to full space-time attention. On benchmark K400 data sets, VideoSEMA out-performs heavier vision transfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14711","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/2607.14711/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":"2607.14711","created_at":"2026-07-17T01:21:26.969565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14711v1","created_at":"2026-07-17T01:21:26.969565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14711","created_at":"2026-07-17T01:21:26.969565+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWZITRRCRMTR","created_at":"2026-07-17T01:21:26.969565+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWZITRRCRMTRF3SD","created_at":"2026-07-17T01:21:26.969565+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWZITRRC","created_at":"2026-07-17T01:21:26.969565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R","json":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R.json","graph_json":"https://pith.science/api/pith-number/MWZITRRCRMTRF3SDS3DPFARO7R/graph.json","events_json":"https://pith.science/api/pith-number/MWZITRRCRMTRF3SDS3DPFARO7R/events.json","paper":"https://pith.science/paper/MWZITRRC"},"agent_actions":{"view_html":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R","download_json":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R.json","view_paper":"https://pith.science/paper/MWZITRRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14711&json=true","fetch_graph":"https://pith.science/api/pith-number/MWZITRRCRMTRF3SDS3DPFARO7R/graph.json","fetch_events":"https://pith.science/api/pith-number/MWZITRRCRMTRF3SDS3DPFARO7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R/action/storage_attestation","attest_author":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R/action/author_attestation","sign_citation":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R/action/citation_signature","submit_replication":"https://pith.science/pith/MWZITRRCRMTRF3SDS3DPFARO7R/action/replication_record"}},"created_at":"2026-07-17T01:21:26.969565+00:00","updated_at":"2026-07-17T01:21:26.969565+00:00"}