{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N644DWVLFS45GU57OH7GHCTN44","short_pith_number":"pith:N644DWVL","schema_version":"1.0","canonical_sha256":"6fb9c1daab2cb9d353bf71fe638a6de73adcf068880bbea38716259436b3457c","source":{"kind":"arxiv","id":"2603.12262","version":2},"attestation_state":"computed","paper":{"title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Jian Luan, Jianzhong Ju, Liang Yin, Xiang Bai, Yiran Guan, Yuliang Liu, Zhenbo Luo","submitted_at":"2026-03-12T17:59:51Z","abstract_excerpt":"Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying test-time scaling methods incurs unacceptable response latency. To address this trade-off, we propose Video Streaming Thinking (VST), a novel paradigm for streaming video understanding. It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming. This design improves timely comprehension and coherent"},"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":"2603.12262","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T17:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"00c2f1594d3b3d3c5496f500d5c3c76607dcbb6ae0f01d27ebdd4bcfe5f4e8a4","abstract_canon_sha256":"06f16f02b9ece1543f1d93034c6dffc3ff851a3f159d0ea781ab5b6f0b832464"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:18:28.900372Z","signature_b64":"Lz/IM70QZSs6sEMLM4o3yPqaeqvlgehntVQSu6BycMaNbmBJIofgV6b/AzzrJyQuJHuWMKyWecfOMNdNQaeGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb9c1daab2cb9d353bf71fe638a6de73adcf068880bbea38716259436b3457c","last_reissued_at":"2026-07-20T01:18:28.899407Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:18:28.899407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Jian Luan, Jianzhong Ju, Liang Yin, Xiang Bai, Yiran Guan, Yuliang Liu, Zhenbo Luo","submitted_at":"2026-03-12T17:59:51Z","abstract_excerpt":"Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying test-time scaling methods incurs unacceptable response latency. To address this trade-off, we propose Video Streaming Thinking (VST), a novel paradigm for streaming video understanding. It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming. This design improves timely comprehension and coherent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12262","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/2603.12262/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":"2603.12262","created_at":"2026-07-20T01:18:28.899853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.12262v2","created_at":"2026-07-20T01:18:28.899853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12262","created_at":"2026-07-20T01:18:28.899853+00:00"},{"alias_kind":"pith_short_12","alias_value":"N644DWVLFS45","created_at":"2026-07-20T01:18:28.899853+00:00"},{"alias_kind":"pith_short_16","alias_value":"N644DWVLFS45GU57","created_at":"2026-07-20T01:18:28.899853+00:00"},{"alias_kind":"pith_short_8","alias_value":"N644DWVL","created_at":"2026-07-20T01:18:28.899853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.25979","citing_title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44","json":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44.json","graph_json":"https://pith.science/api/pith-number/N644DWVLFS45GU57OH7GHCTN44/graph.json","events_json":"https://pith.science/api/pith-number/N644DWVLFS45GU57OH7GHCTN44/events.json","paper":"https://pith.science/paper/N644DWVL"},"agent_actions":{"view_html":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44","download_json":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44.json","view_paper":"https://pith.science/paper/N644DWVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.12262&json=true","fetch_graph":"https://pith.science/api/pith-number/N644DWVLFS45GU57OH7GHCTN44/graph.json","fetch_events":"https://pith.science/api/pith-number/N644DWVLFS45GU57OH7GHCTN44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44/action/storage_attestation","attest_author":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44/action/author_attestation","sign_citation":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44/action/citation_signature","submit_replication":"https://pith.science/pith/N644DWVLFS45GU57OH7GHCTN44/action/replication_record"}},"created_at":"2026-07-20T01:18:28.899853+00:00","updated_at":"2026-07-20T01:18:28.899853+00:00"}