{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6JM7MGYC7OT3CMRRJLH452B6OG","short_pith_number":"pith:6JM7MGYC","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"},"canonical_sha256":"f259f61b02fba7b132314acfcee83e71be83c594330bebaa737077f30fdf16ae","source":{"kind":"arxiv","id":"2605.18577","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6JM7MGYC7OT3CMRRJLH452B6OG","target":"record","payload":{"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"},"canonical_sha256":"f259f61b02fba7b132314acfcee83e71be83c594330bebaa737077f30fdf16ae","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"},"source_kind":"arxiv","source_id":"2605.18577","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nh3rDPoZe1noNhW2pc4B9b7zB0ckdpcbHA03icHWmnMuoLwwCXteQfirUWAYt9exVbYavVNcV93BgJgTf6VeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:57:19.808330Z"},"content_sha256":"f82c642d6d3c7e7f88c10983357aea03aeeb4be585e34fedb347e6ce3976ad34","schema_version":"1.0","event_id":"sha256:f82c642d6d3c7e7f88c10983357aea03aeeb4be585e34fedb347e6ce3976ad34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6JM7MGYC7OT3CMRRJLH452B6OG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrNRrfB+p9PUUiTjNpFG0I3JH9VCi6mn2/9+z5Pwo2qgV5n2CKvpBBJu0HhvS1rE7/JFyxeLpFL3C6qx42XOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:57:19.809145Z"},"content_sha256":"02d73fe9fdf6cfa322249d6c9c5bf11de3d9a2123e9a5d615e6e3308c7055edc","schema_version":"1.0","event_id":"sha256:02d73fe9fdf6cfa322249d6c9c5bf11de3d9a2123e9a5d615e6e3308c7055edc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/bundle.json","state_url":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JM7MGYC7OT3CMRRJLH452B6OG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T02:57:19Z","links":{"resolver":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG","bundle":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/bundle.json","state":"https://pith.science/pith/6JM7MGYC7OT3CMRRJLH452B6OG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JM7MGYC7OT3CMRRJLH452B6OG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5DgHuuBW8x/A2F2iy5tYBRbgW8ToD2bWvFMx/8gkDxGrlhOkxN42ZlXQmVkeebrmTTBd6seCwxqVjNHXPIdqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:57:19.812711Z","bundle_sha256":"b3c3fe2605f9a2f2f4a5b53dc0f91a88f82907314604610e65094332b141d99e"}}