{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4VZQVU2HOFPPIEQAOJRHUASW72","short_pith_number":"pith:4VZQVU2H","schema_version":"1.0","canonical_sha256":"e5730ad347715ef4120072627a0256feb95de8a72f9f1ef06b9f9974a9712d6f","source":{"kind":"arxiv","id":"2601.21444","version":2},"attestation_state":"computed","paper":{"title":"APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Ao Sun, Chaojun Xiao, Fandong Meng, Hao Zhou, Mingye Li, Weilin Zhao, Xu Han, Yuxiang Huang, Zhiyuan Liu, Ziqi Yuan","submitted_at":"2026-01-29T09:23:13Z","abstract_excerpt":"The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention on a single GPU, yielding limited acceleration or degraded performance and restricting LMMs from handling longer, more complex videos. To overcome these issues, we propose APB-V, a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. By distributing approximate attention, APB-V reduces computation an"},"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":"2601.21444","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T09:23:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"30290f6fb046b98d64b313656f2668139de4786f6daf84f2d81b8de2daa79f70","abstract_canon_sha256":"5deef7efb8a998cb2ffa01cd8c5bd303610ff6a4582511efaacf3c3563292374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:50.254594Z","signature_b64":"M4B7AxeAEajJadttCvPzeO2HN3RzgCWff7/eLMTAhyiPNHfwWrD4Nrqpuh169iOpSHgOB8sAaKTjiDE6g9D9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5730ad347715ef4120072627a0256feb95de8a72f9f1ef06b9f9974a9712d6f","last_reissued_at":"2026-06-02T02:04:50.253833Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:50.253833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Ao Sun, Chaojun Xiao, Fandong Meng, Hao Zhou, Mingye Li, Weilin Zhao, Xu Han, Yuxiang Huang, Zhiyuan Liu, Ziqi Yuan","submitted_at":"2026-01-29T09:23:13Z","abstract_excerpt":"The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention on a single GPU, yielding limited acceleration or degraded performance and restricting LMMs from handling longer, more complex videos. To overcome these issues, we propose APB-V, a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. By distributing approximate attention, APB-V reduces computation an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21444","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/2601.21444/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":"2601.21444","created_at":"2026-06-02T02:04:50.253902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21444v2","created_at":"2026-06-02T02:04:50.253902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21444","created_at":"2026-06-02T02:04:50.253902+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VZQVU2HOFPP","created_at":"2026-06-02T02:04:50.253902+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VZQVU2HOFPPIEQA","created_at":"2026-06-02T02:04:50.253902+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VZQVU2H","created_at":"2026-06-02T02:04:50.253902+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/4VZQVU2HOFPPIEQAOJRHUASW72","json":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72.json","graph_json":"https://pith.science/api/pith-number/4VZQVU2HOFPPIEQAOJRHUASW72/graph.json","events_json":"https://pith.science/api/pith-number/4VZQVU2HOFPPIEQAOJRHUASW72/events.json","paper":"https://pith.science/paper/4VZQVU2H"},"agent_actions":{"view_html":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72","download_json":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72.json","view_paper":"https://pith.science/paper/4VZQVU2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21444&json=true","fetch_graph":"https://pith.science/api/pith-number/4VZQVU2HOFPPIEQAOJRHUASW72/graph.json","fetch_events":"https://pith.science/api/pith-number/4VZQVU2HOFPPIEQAOJRHUASW72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72/action/storage_attestation","attest_author":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72/action/author_attestation","sign_citation":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72/action/citation_signature","submit_replication":"https://pith.science/pith/4VZQVU2HOFPPIEQAOJRHUASW72/action/replication_record"}},"created_at":"2026-06-02T02:04:50.253902+00:00","updated_at":"2026-06-02T02:04:50.253902+00:00"}