{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6JM7MGYC7OT3CMRRJLH452B6OG","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":"0595873f016a0cd33f97833fe4290f090c160fe230e7f5518be66ddb5d2ca4ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T15:55:22Z","title_canon_sha256":"0f1da4df0c9742c3a144eeec90934d4a023e34cbadc90de4d7b7452599ab231e"},"schema_version":"1.0","source":{"id":"2605.18577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18577","created_at":"2026-05-20T00:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18577v1","created_at":"2026-05-20T00:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18577","created_at":"2026-05-20T00:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"6JM7MGYC7OT3","created_at":"2026-05-20T00:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"6JM7MGYC7OT3CMRR","created_at":"2026-05-20T00:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"6JM7MGYC","created_at":"2026-05-20T00:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:02d73fe9fdf6cfa322249d6c9c5bf11de3d9a2123e9a5d615e6e3308c7055edc","target":"graph","created_at":"2026-05-20T00:06:08Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.322245Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18577/integrity.json","findings":[],"snapshot_sha256":"a446d362f07f96f597dcb61bdd36e64b0abb5fc95a785c11b045656cc1a22a07","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Omni-proactive streaming video understanding, i.e., autonomously deciding when to speak and what to say from continuous audio-visual streams, is an emerging capability of omni-modal large language models. Existing benchmarks fall short in three key aspects: they rely primarily on visual signals, adopt polling or fixed-timestamp protocols instead of true proactive evaluation, and cover only a limited range of tasks, preventing reliable assessment and differentiation of omni-proactive streaming models. We present OmniPro, the first benchmark to jointly evaluate omni-modal perception, proactive r","authors_text":"Fengyun Rao, Jie Yang, Jing Lyu, Ruixiang Zhao, Tianyi Wang, Xirong Li, Zijie Xin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T15:55:22Z","title":"OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18577","kind":"arxiv","version":1},"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:f82c642d6d3c7e7f88c10983357aea03aeeb4be585e34fedb347e6ce3976ad34","target":"record","created_at":"2026-05-20T00:06:08Z","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":"0595873f016a0cd33f97833fe4290f090c160fe230e7f5518be66ddb5d2ca4ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T15:55:22Z","title_canon_sha256":"0f1da4df0c9742c3a144eeec90934d4a023e34cbadc90de4d7b7452599ab231e"},"schema_version":"1.0","source":{"id":"2605.18577","kind":"arxiv","version":1}},"canonical_sha256":"f259f61b02fba7b132314acfcee83e71be83c594330bebaa737077f30fdf16ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f259f61b02fba7b132314acfcee83e71be83c594330bebaa737077f30fdf16ae","first_computed_at":"2026-05-20T00:06:08.600779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:08.600779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CgGPivD93uyoilC8bG4kfirs4/STgvHeprvsOjnJBg+NdiCJXxfKtE9GVc2R5MVwqwjWYPKeQez08al6MFxTBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:08.601517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f82c642d6d3c7e7f88c10983357aea03aeeb4be585e34fedb347e6ce3976ad34","sha256:02d73fe9fdf6cfa322249d6c9c5bf11de3d9a2123e9a5d615e6e3308c7055edc"],"state_sha256":"96cb184537080e13f8ad3ae83da601b8be6fd529677cbaffaa81ded6a716a1e6"}