{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJK2577A3FXVSDUDUYXEACXLKX","short_pith_number":"pith:ZJK2577A","schema_version":"1.0","canonical_sha256":"ca55aeffe0d96f590e83a62e400aeb55dfbdb50eda93b3493a0f1ebaa0811795","source":{"kind":"arxiv","id":"2507.09313","version":2},"attestation_state":"computed","paper":{"title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Huishuai Zhang, Xiaojun Meng, Yifan Wang, Yueqian Wang","submitted_at":"2025-07-12T15:11:50Z","abstract_excerpt":"With the growing research focus on multimodal dialogue systems, the capability for proactive interaction is gradually gaining recognition. As an alternative to conventional turn-by-turn dialogue, users increasingly expect multimodal systems to be more initiative, for example, by autonomously determining the timing of multi-turn responses in real time during video playback. To facilitate progress in this emerging area, we introduce ProactiveVideoQA, the first comprehensive benchmark to evaluate a system's ability to engage in proactive interaction. Since model responses are generated at varying"},"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":"2507.09313","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:11:50Z","cross_cats_sorted":[],"title_canon_sha256":"ad9aefd4f1199505c30d59c0e2fdc28f4d8f229db34b93942566428891b4760c","abstract_canon_sha256":"3e175b04acbc53b42689e0b0ff6b94d6a859234e5f1f3526613416d46d4054a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:26.098920Z","signature_b64":"m9/hHimSCYQRj84emhU3NutFFRCzcDHxhI8KhE2B/LdnIqpD4OzgJn5PlmAG7Z0Y9GEo+IWxCZDnw412H2MVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca55aeffe0d96f590e83a62e400aeb55dfbdb50eda93b3493a0f1ebaa0811795","last_reissued_at":"2026-07-05T11:37:26.098419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:26.098419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Huishuai Zhang, Xiaojun Meng, Yifan Wang, Yueqian Wang","submitted_at":"2025-07-12T15:11:50Z","abstract_excerpt":"With the growing research focus on multimodal dialogue systems, the capability for proactive interaction is gradually gaining recognition. As an alternative to conventional turn-by-turn dialogue, users increasingly expect multimodal systems to be more initiative, for example, by autonomously determining the timing of multi-turn responses in real time during video playback. To facilitate progress in this emerging area, we introduce ProactiveVideoQA, the first comprehensive benchmark to evaluate a system's ability to engage in proactive interaction. Since model responses are generated at varying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09313","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/2507.09313/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":"2507.09313","created_at":"2026-07-05T11:37:26.098479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09313v2","created_at":"2026-07-05T11:37:26.098479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09313","created_at":"2026-07-05T11:37:26.098479+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJK2577A3FXV","created_at":"2026-07-05T11:37:26.098479+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJK2577A3FXVSDUD","created_at":"2026-07-05T11:37:26.098479+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJK2577A","created_at":"2026-07-05T11:37:26.098479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17360","citing_title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02482","citing_title":"X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02482","citing_title":"X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27074","citing_title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16381","citing_title":"StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17360","citing_title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17921","citing_title":"An Efficient Streaming Video Understanding Framework with Agentic Control","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24317","citing_title":"Don't Pause! Every prediction matters in a streaming video","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15037","citing_title":"From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX","json":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX.json","graph_json":"https://pith.science/api/pith-number/ZJK2577A3FXVSDUDUYXEACXLKX/graph.json","events_json":"https://pith.science/api/pith-number/ZJK2577A3FXVSDUDUYXEACXLKX/events.json","paper":"https://pith.science/paper/ZJK2577A"},"agent_actions":{"view_html":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX","download_json":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX.json","view_paper":"https://pith.science/paper/ZJK2577A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09313&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJK2577A3FXVSDUDUYXEACXLKX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJK2577A3FXVSDUDUYXEACXLKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX/action/storage_attestation","attest_author":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX/action/author_attestation","sign_citation":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX/action/citation_signature","submit_replication":"https://pith.science/pith/ZJK2577A3FXVSDUDUYXEACXLKX/action/replication_record"}},"created_at":"2026-07-05T11:37:26.098479+00:00","updated_at":"2026-07-05T11:37:26.098479+00:00"}