{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WS2QA3VB5SBZORW2DZNEB2LJ6C","short_pith_number":"pith:WS2QA3VB","schema_version":"1.0","canonical_sha256":"b4b5006ea1ec839746da1e5a40e969f091ff80b448c6ecec7b38e64c79bc0651","source":{"kind":"arxiv","id":"2605.17921","version":1},"attestation_state":"computed","paper":{"title":"An Efficient Streaming Video Understanding Framework with Agentic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Jiahao Li, Jianguo Huang, Jinming Liu, Wenjun Zeng, Xiaoyi Zhang, Xin Jin, Yan Lu, Zhaoyang Jia, Zongyu Guo","submitted_at":"2026-05-18T06:29:44Z","abstract_excerpt":"Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, such as fixed memory compression or reliance on a single model, forcing a trade-off: fast models fail on complex queries, while always-on heavy models violate real-time constraints and overcomplicate simple queries. Rather than fixing these decisions upfront, we propose R3-Streaming (Remember, Respond, Reason), which formulates streaming video understanding as a cascaded control problem: for each query, the system compresses memory, judges respon"},"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":"2605.17921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T06:29:44Z","cross_cats_sorted":[],"title_canon_sha256":"f4f1dfe7dee616686ed56f061bd5199847e3255d5d9278e335c393c14aa922b1","abstract_canon_sha256":"d00e29c325f23134684d73bdd330b9af369a8ec367a749f0a24e0a2f6dc2b066"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:06.128749Z","signature_b64":"VYXbp3alLPeMNxlYQ2ntmIJXGsvZdDywg1qvy8iIYb5o8zsB3Y3vXHuRKyNJvBg5qlpee7G7vLapwfDiitElBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4b5006ea1ec839746da1e5a40e969f091ff80b448c6ecec7b38e64c79bc0651","last_reissued_at":"2026-05-20T00:05:06.127927Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:06.127927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Streaming Video Understanding Framework with Agentic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Jiahao Li, Jianguo Huang, Jinming Liu, Wenjun Zeng, Xiaoyi Zhang, Xin Jin, Yan Lu, Zhaoyang Jia, Zongyu Guo","submitted_at":"2026-05-18T06:29:44Z","abstract_excerpt":"Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, such as fixed memory compression or reliance on a single model, forcing a trade-off: fast models fail on complex queries, while always-on heavy models violate real-time constraints and overcomplicate simple queries. Rather than fixing these decisions upfront, we propose R3-Streaming (Remember, Respond, Reason), which formulates streaming video understanding as a cascaded control problem: for each query, the system compresses memory, judges respon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17921","kind":"arxiv","version":1},"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/2605.17921/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":"2605.17921","created_at":"2026-05-20T00:05:06.128070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17921v1","created_at":"2026-05-20T00:05:06.128070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17921","created_at":"2026-05-20T00:05:06.128070+00:00"},{"alias_kind":"pith_short_12","alias_value":"WS2QA3VB5SBZ","created_at":"2026-05-20T00:05:06.128070+00:00"},{"alias_kind":"pith_short_16","alias_value":"WS2QA3VB5SBZORW2","created_at":"2026-05-20T00:05:06.128070+00:00"},{"alias_kind":"pith_short_8","alias_value":"WS2QA3VB","created_at":"2026-05-20T00:05:06.128070+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/WS2QA3VB5SBZORW2DZNEB2LJ6C","json":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C.json","graph_json":"https://pith.science/api/pith-number/WS2QA3VB5SBZORW2DZNEB2LJ6C/graph.json","events_json":"https://pith.science/api/pith-number/WS2QA3VB5SBZORW2DZNEB2LJ6C/events.json","paper":"https://pith.science/paper/WS2QA3VB"},"agent_actions":{"view_html":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C","download_json":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C.json","view_paper":"https://pith.science/paper/WS2QA3VB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17921&json=true","fetch_graph":"https://pith.science/api/pith-number/WS2QA3VB5SBZORW2DZNEB2LJ6C/graph.json","fetch_events":"https://pith.science/api/pith-number/WS2QA3VB5SBZORW2DZNEB2LJ6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C/action/storage_attestation","attest_author":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C/action/author_attestation","sign_citation":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C/action/citation_signature","submit_replication":"https://pith.science/pith/WS2QA3VB5SBZORW2DZNEB2LJ6C/action/replication_record"}},"created_at":"2026-05-20T00:05:06.128070+00:00","updated_at":"2026-05-20T00:05:06.128070+00:00"}