{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LLQRKOVXMIAOAUKLBUBM3DQYC6","short_pith_number":"pith:LLQRKOVX","schema_version":"1.0","canonical_sha256":"5ae1153ab76200e0514b0d02cd8e1817bb6eb37d9d7ad130526101aa7afc5d02","source":{"kind":"arxiv","id":"2505.16175","version":2},"attestation_state":"computed","paper":{"title":"QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Schneider, Chao Du, Dongfu Jiang, Tianyu Pang, Wenhu Chen","submitted_at":"2025-05-22T03:26:50Z","abstract_excerpt":"Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports broadcasting. However, it remains computationally prohibitive for VideoLLMs, primarily due to two bottlenecks: 1) sequential video decoding, the process of converting the raw bit stream to RGB frames can take up to a minute for hour-long video inputs, and 2) costly prefilling of up to several million tokens for LLM inference, resulting in high latency and memory use. To address these challenges, we propose QuickVideo"},"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":"2505.16175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T03:26:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f83e4361ea693650fc4a13439f0a6dfc3d8b36f735f7b80d2bdc61c08cac9f83","abstract_canon_sha256":"c8601001e75ebb0455b76e9e5cb35f8b00e416ee2d78eb6ac266b8d22a7de620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:26.220494Z","signature_b64":"3Jt2mNi/fJtxgsCFWRjSmpgNH495kWtfCbUlfniOEuwgvaDA/THqoVb9WHASENjkRAoeI9AUCoY81zpxGzJ6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ae1153ab76200e0514b0d02cd8e1817bb6eb37d9d7ad130526101aa7afc5d02","last_reissued_at":"2026-07-05T11:13:26.220052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:26.220052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Schneider, Chao Du, Dongfu Jiang, Tianyu Pang, Wenhu Chen","submitted_at":"2025-05-22T03:26:50Z","abstract_excerpt":"Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports broadcasting. However, it remains computationally prohibitive for VideoLLMs, primarily due to two bottlenecks: 1) sequential video decoding, the process of converting the raw bit stream to RGB frames can take up to a minute for hour-long video inputs, and 2) costly prefilling of up to several million tokens for LLM inference, resulting in high latency and memory use. To address these challenges, we propose QuickVideo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16175","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/2505.16175/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":"2505.16175","created_at":"2026-07-05T11:13:26.220111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16175v2","created_at":"2026-07-05T11:13:26.220111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16175","created_at":"2026-07-05T11:13:26.220111+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLQRKOVXMIAO","created_at":"2026-07-05T11:13:26.220111+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLQRKOVXMIAOAUKL","created_at":"2026-07-05T11:13:26.220111+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLQRKOVX","created_at":"2026-07-05T11:13:26.220111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03351","citing_title":"VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06036","citing_title":"CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10060","citing_title":"Mosaic: Cross-Modal Clustering for Efficient Video Understanding","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6","json":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6.json","graph_json":"https://pith.science/api/pith-number/LLQRKOVXMIAOAUKLBUBM3DQYC6/graph.json","events_json":"https://pith.science/api/pith-number/LLQRKOVXMIAOAUKLBUBM3DQYC6/events.json","paper":"https://pith.science/paper/LLQRKOVX"},"agent_actions":{"view_html":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6","download_json":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6.json","view_paper":"https://pith.science/paper/LLQRKOVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16175&json=true","fetch_graph":"https://pith.science/api/pith-number/LLQRKOVXMIAOAUKLBUBM3DQYC6/graph.json","fetch_events":"https://pith.science/api/pith-number/LLQRKOVXMIAOAUKLBUBM3DQYC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6/action/storage_attestation","attest_author":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6/action/author_attestation","sign_citation":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6/action/citation_signature","submit_replication":"https://pith.science/pith/LLQRKOVXMIAOAUKLBUBM3DQYC6/action/replication_record"}},"created_at":"2026-07-05T11:13:26.220111+00:00","updated_at":"2026-07-05T11:13:26.220111+00:00"}