{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJK2577A3FXVSDUDUYXEACXLKX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3e175b04acbc53b42689e0b0ff6b94d6a859234e5f1f3526613416d46d4054a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:11:50Z","title_canon_sha256":"ad9aefd4f1199505c30d59c0e2fdc28f4d8f229db34b93942566428891b4760c"},"schema_version":"1.0","source":{"id":"2507.09313","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09313","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09313v2","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09313","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZJK2577A3FXV","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZJK2577A3FXVSDUD","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZJK2577A","created_at":"2026-07-05T11:37:26Z"}],"graph_snapshots":[{"event_id":"sha256:0f399e0332f6d1f565698ded59b4d2cec62ace8e06fad34b596a027b61a4eb57","target":"graph","created_at":"2026-07-05T11:37:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.09313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongyan Zhao, Huishuai Zhang, Xiaojun Meng, Yifan Wang, Yueqian Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:11:50Z","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09313","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:97d7aadbd70b170196027e292fec9ecf52c8f86027f6be9a91223bbd58abb3ea","target":"record","created_at":"2026-07-05T11:37:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3e175b04acbc53b42689e0b0ff6b94d6a859234e5f1f3526613416d46d4054a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:11:50Z","title_canon_sha256":"ad9aefd4f1199505c30d59c0e2fdc28f4d8f229db34b93942566428891b4760c"},"schema_version":"1.0","source":{"id":"2507.09313","kind":"arxiv","version":2}},"canonical_sha256":"ca55aeffe0d96f590e83a62e400aeb55dfbdb50eda93b3493a0f1ebaa0811795","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca55aeffe0d96f590e83a62e400aeb55dfbdb50eda93b3493a0f1ebaa0811795","first_computed_at":"2026-07-05T11:37:26.098419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:26.098419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m9/hHimSCYQRj84emhU3NutFFRCzcDHxhI8KhE2B/LdnIqpD4OzgJn5PlmAG7Z0Y9GEo+IWxCZDnw412H2MVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:26.098920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09313","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97d7aadbd70b170196027e292fec9ecf52c8f86027f6be9a91223bbd58abb3ea","sha256:0f399e0332f6d1f565698ded59b4d2cec62ace8e06fad34b596a027b61a4eb57"],"state_sha256":"c247c9c75596c56cfe66626a9a62eccfdc6e91344fc2ed2ea93a5711cf956dcb"}