{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OYKUWPRKFXC2KZJVY3EUZFXWCK","short_pith_number":"pith:OYKUWPRK","schema_version":"1.0","canonical_sha256":"76154b3e2a2dc5a56535c6c94c96f612a52ef2dc5e442ee4b0d4f54929cc2dae","source":{"kind":"arxiv","id":"2503.09387","version":2},"attestation_state":"computed","paper":{"title":"VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawei Shao, Ruanjun Li, Yuanming Shi, Yuedong Tan","submitted_at":"2025-03-12T13:30:40Z","abstract_excerpt":"This paper introduces VideoScan, an efficient vision-language model (VLM) inference framework designed for real-time video interaction that effectively comprehends and retains streamed video inputs while delivering rapid and accurate responses. A longstanding challenge in video understanding--particularly for long-term or real-time applications--stems from the substantial computational overhead caused by the extensive length of visual tokens. To address this, VideoScan employs a single semantic carrier token to represent each frame, progressively reducing computational and memory overhead duri"},"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":"2503.09387","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T13:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"8153cc1688b75911ff9d2c16451d89b497549a1a93db710a473e949831cf92ba","abstract_canon_sha256":"f7d32ae0d8b460d1f99be39c0e594532e651cbb5d3f41295e7ea41127058a6a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:41.238465Z","signature_b64":"WEQ+/azpPsBvkLeT6HTzZKHBk8NJ+u2CrZVPRoHjqwQKeZTiUSV+MRDBcTSgNf2umVxagyj+5t+nRRWk9cwGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76154b3e2a2dc5a56535c6c94c96f612a52ef2dc5e442ee4b0d4f54929cc2dae","last_reissued_at":"2026-07-05T10:32:41.237800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:41.237800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawei Shao, Ruanjun Li, Yuanming Shi, Yuedong Tan","submitted_at":"2025-03-12T13:30:40Z","abstract_excerpt":"This paper introduces VideoScan, an efficient vision-language model (VLM) inference framework designed for real-time video interaction that effectively comprehends and retains streamed video inputs while delivering rapid and accurate responses. A longstanding challenge in video understanding--particularly for long-term or real-time applications--stems from the substantial computational overhead caused by the extensive length of visual tokens. To address this, VideoScan employs a single semantic carrier token to represent each frame, progressively reducing computational and memory overhead duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09387","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/2503.09387/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":"2503.09387","created_at":"2026-07-05T10:32:41.237876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09387v2","created_at":"2026-07-05T10:32:41.237876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09387","created_at":"2026-07-05T10:32:41.237876+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYKUWPRKFXC2","created_at":"2026-07-05T10:32:41.237876+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYKUWPRKFXC2KZJV","created_at":"2026-07-05T10:32:41.237876+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYKUWPRK","created_at":"2026-07-05T10:32:41.237876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19849","citing_title":"ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06600","citing_title":"Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06600","citing_title":"Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK","json":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK.json","graph_json":"https://pith.science/api/pith-number/OYKUWPRKFXC2KZJVY3EUZFXWCK/graph.json","events_json":"https://pith.science/api/pith-number/OYKUWPRKFXC2KZJVY3EUZFXWCK/events.json","paper":"https://pith.science/paper/OYKUWPRK"},"agent_actions":{"view_html":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK","download_json":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK.json","view_paper":"https://pith.science/paper/OYKUWPRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09387&json=true","fetch_graph":"https://pith.science/api/pith-number/OYKUWPRKFXC2KZJVY3EUZFXWCK/graph.json","fetch_events":"https://pith.science/api/pith-number/OYKUWPRKFXC2KZJVY3EUZFXWCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK/action/storage_attestation","attest_author":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK/action/author_attestation","sign_citation":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK/action/citation_signature","submit_replication":"https://pith.science/pith/OYKUWPRKFXC2KZJVY3EUZFXWCK/action/replication_record"}},"created_at":"2026-07-05T10:32:41.237876+00:00","updated_at":"2026-07-05T10:32:41.237876+00:00"}