{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C5VS42FPCBOHJGCUV6SJ33MOFP","short_pith_number":"pith:C5VS42FP","schema_version":"1.0","canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","source":{"kind":"arxiv","id":"2506.23825","version":2},"attestation_state":"computed","paper":{"title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoji Zhang, Jiashi Feng, Xiaojie Jin, Yansong Tang, Yiqin Wang, Yong Liu","submitted_at":"2025-06-30T13:17:49Z","abstract_excerpt":"Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model"},"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":"2506.23825","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"15077eaf6dd854a3bf042534c461f3bc9aaf86cbaba3eff2034002f53f72d0ee","abstract_canon_sha256":"7190bacdf89f3dd685a49cfe4ddcff52eb10f16247fd4d57ee9e67ea18f282e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:31.309613Z","signature_b64":"rWJIFwTYfbMVh0LTEYPVR0HKg8M1FDnuB9msmFW3jEdEfufyR0hmwnMj1MBG4aJd6Q+PCMgXnorWPhMSadU8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","last_reissued_at":"2026-07-05T11:42:31.309047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:31.309047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoji Zhang, Jiashi Feng, Xiaojie Jin, Yansong Tang, Yiqin Wang, Yong Liu","submitted_at":"2025-06-30T13:17:49Z","abstract_excerpt":"Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23825","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/2506.23825/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":"2506.23825","created_at":"2026-07-05T11:42:31.309108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23825v2","created_at":"2026-07-05T11:42:31.309108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23825","created_at":"2026-07-05T11:42:31.309108+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5VS42FPCBOH","created_at":"2026-07-05T11:42:31.309108+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5VS42FPCBOHJGCU","created_at":"2026-07-05T11:42:31.309108+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5VS42FP","created_at":"2026-07-05T11:42:31.309108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08615","citing_title":"Harnessing Streaming Video in the Wild","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05917","citing_title":"MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07575","citing_title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07575","citing_title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10060","citing_title":"Mosaic: Cross-Modal Clustering for Efficient Video Understanding","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17052","citing_title":"OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP","json":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP.json","graph_json":"https://pith.science/api/pith-number/C5VS42FPCBOHJGCUV6SJ33MOFP/graph.json","events_json":"https://pith.science/api/pith-number/C5VS42FPCBOHJGCUV6SJ33MOFP/events.json","paper":"https://pith.science/paper/C5VS42FP"},"agent_actions":{"view_html":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP","download_json":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP.json","view_paper":"https://pith.science/paper/C5VS42FP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23825&json=true","fetch_graph":"https://pith.science/api/pith-number/C5VS42FPCBOHJGCUV6SJ33MOFP/graph.json","fetch_events":"https://pith.science/api/pith-number/C5VS42FPCBOHJGCUV6SJ33MOFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/action/storage_attestation","attest_author":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/action/author_attestation","sign_citation":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/action/citation_signature","submit_replication":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/action/replication_record"}},"created_at":"2026-07-05T11:42:31.309108+00:00","updated_at":"2026-07-05T11:42:31.309108+00:00"}