{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5HPC52N6IQG4BZHKERIOCZ3NXN","short_pith_number":"pith:5HPC52N6","schema_version":"1.0","canonical_sha256":"e9de2ee9be440dc0e4ea2450e1676dbb5fe52bbdc82125c8ec898ae013ea994e","source":{"kind":"arxiv","id":"2606.26762","version":1},"attestation_state":"computed","paper":{"title":"ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongsu Han (KAIST), Jinyeong Lim (KAIST), Le Tu Ngoc Minh (KAIST)","submitted_at":"2026-06-25T08:47:15Z","abstract_excerpt":"Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A key challenge is delayed query: decisive cues may appear briefly, yet many subsequent updates occur before the query arrives, increasing the risk that those cues are evicted or diluted under bounded memory. We propose ProtoKV, a constant-footprint SVU memory that represents far history as a fixed-capacity summary state rather than retaining token instances. ProtoKV keeps an exact near-window KV cache and aggregates "},"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":"2606.26762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T08:47:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2fd2be19ca462c6a61f29dd39fd52397ddb19b5807395de17f584fcbca95e96","abstract_canon_sha256":"d59204f43e3d6605db3fb086c9438dc5ddee1da791b8fc7ba80f5e4860cfbc69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:59.051971Z","signature_b64":"LPCLBEemLLTveYTM8SAfEw0VxhEs5jG3pv3SRJ/EgoK+bpukEK12Kf86R9EPXF43AbrXprQl2vBmIFzg8b+ODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9de2ee9be440dc0e4ea2450e1676dbb5fe52bbdc82125c8ec898ae013ea994e","last_reissued_at":"2026-06-26T01:15:59.051571Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:59.051571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongsu Han (KAIST), Jinyeong Lim (KAIST), Le Tu Ngoc Minh (KAIST)","submitted_at":"2026-06-25T08:47:15Z","abstract_excerpt":"Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A key challenge is delayed query: decisive cues may appear briefly, yet many subsequent updates occur before the query arrives, increasing the risk that those cues are evicted or diluted under bounded memory. We propose ProtoKV, a constant-footprint SVU memory that represents far history as a fixed-capacity summary state rather than retaining token instances. ProtoKV keeps an exact near-window KV cache and aggregates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26762","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/2606.26762/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":"2606.26762","created_at":"2026-06-26T01:15:59.051627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26762v1","created_at":"2026-06-26T01:15:59.051627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26762","created_at":"2026-06-26T01:15:59.051627+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HPC52N6IQG4","created_at":"2026-06-26T01:15:59.051627+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HPC52N6IQG4BZHK","created_at":"2026-06-26T01:15:59.051627+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HPC52N6","created_at":"2026-06-26T01:15:59.051627+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/5HPC52N6IQG4BZHKERIOCZ3NXN","json":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN.json","graph_json":"https://pith.science/api/pith-number/5HPC52N6IQG4BZHKERIOCZ3NXN/graph.json","events_json":"https://pith.science/api/pith-number/5HPC52N6IQG4BZHKERIOCZ3NXN/events.json","paper":"https://pith.science/paper/5HPC52N6"},"agent_actions":{"view_html":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN","download_json":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN.json","view_paper":"https://pith.science/paper/5HPC52N6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26762&json=true","fetch_graph":"https://pith.science/api/pith-number/5HPC52N6IQG4BZHKERIOCZ3NXN/graph.json","fetch_events":"https://pith.science/api/pith-number/5HPC52N6IQG4BZHKERIOCZ3NXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN/action/storage_attestation","attest_author":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN/action/author_attestation","sign_citation":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN/action/citation_signature","submit_replication":"https://pith.science/pith/5HPC52N6IQG4BZHKERIOCZ3NXN/action/replication_record"}},"created_at":"2026-06-26T01:15:59.051627+00:00","updated_at":"2026-06-26T01:15:59.051627+00:00"}