{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6JM7MGYC7OT3CMRRJLH452B6OG","short_pith_number":"pith:6JM7MGYC","schema_version":"1.0","canonical_sha256":"f259f61b02fba7b132314acfcee83e71be83c594330bebaa737077f30fdf16ae","source":{"kind":"arxiv","id":"2605.18577","version":1},"attestation_state":"computed","paper":{"title":"OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyun Rao, Jie Yang, Jing Lyu, Ruixiang Zhao, Tianyi Wang, Xirong Li, Zijie Xin","submitted_at":"2026-05-18T15:55:22Z","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"},"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":"2605.18577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T15:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"0f1da4df0c9742c3a144eeec90934d4a023e34cbadc90de4d7b7452599ab231e","abstract_canon_sha256":"0595873f016a0cd33f97833fe4290f090c160fe230e7f5518be66ddb5d2ca4ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:08.601517Z","signature_b64":"CgGPivD93uyoilC8bG4kfirs4/STgvHeprvsOjnJBg+NdiCJXxfKtE9GVc2R5MVwqwjWYPKeQez08al6MFxTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f259f61b02fba7b132314acfcee83e71be83c594330bebaa737077f30fdf16ae","last_reissued_at":"2026-05-20T00:06:08.600779Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:08.600779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyun Rao, Jie Yang, Jing Lyu, Ruixiang Zhao, Tianyi Wang, Xirong Li, Zijie Xin","submitted_at":"2026-05-18T15:55:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18577","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/2605.18577/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.322245Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a446d362f07f96f597dcb61bdd36e64b0abb5fc95a785c11b045656cc1a22a07"},"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":"2605.18577","created_at":"2026-05-20T00:06:08.600883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18577v1","created_at":"2026-05-20T00:06:08.600883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18577","created_at":"2026-05-20T00:06:08.600883+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JM7MGYC7OT3","created_at":"2026-05-20T00:06:08.600883+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JM7MGYC7OT3CMRR","created_at":"2026-05-20T00:06:08.600883+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JM7MGYC","created_at":"2026-05-20T00:06:08.600883+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/6JM7MGYC7OT3CMRRJLH452B6OG","json":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG.json","graph_json":"https://pith.science/api/pith-number/6JM7MGYC7OT3CMRRJLH452B6OG/graph.json","events_json":"https://pith.science/api/pith-number/6JM7MGYC7OT3CMRRJLH452B6OG/events.json","paper":"https://pith.science/paper/6JM7MGYC"},"agent_actions":{"view_html":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG","download_json":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG.json","view_paper":"https://pith.science/paper/6JM7MGYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18577&json=true","fetch_graph":"https://pith.science/api/pith-number/6JM7MGYC7OT3CMRRJLH452B6OG/graph.json","fetch_events":"https://pith.science/api/pith-number/6JM7MGYC7OT3CMRRJLH452B6OG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/action/storage_attestation","attest_author":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/action/author_attestation","sign_citation":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/action/citation_signature","submit_replication":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/action/replication_record"}},"created_at":"2026-05-20T00:06:08.600883+00:00","updated_at":"2026-05-20T00:06:08.600883+00:00"}