{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GRI5P6UNAOGZ6CVTMA6JBJAMNR","short_pith_number":"pith:GRI5P6UN","canonical_record":{"source":{"id":"2603.16859","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-17T17:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"c0138d5d18aa4a757c5976c0cf53dd96e30a689e5846b65bc5dc1a0eb78e6aee","abstract_canon_sha256":"997a52369c5dd94605535f55c47bccc312be733f91d50b34f13dd5d590ac47fa"},"schema_version":"1.0"},"canonical_sha256":"3451d7fa8d038d9f0ab3603c90a40c6c6f9c79bf146a39c90f2c65752af9ba78","source":{"kind":"arxiv","id":"2603.16859","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16859","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16859v2","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16859","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"GRI5P6UNAOGZ","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"GRI5P6UNAOGZ6CVT","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"GRI5P6UN","created_at":"2026-07-02T01:17:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GRI5P6UNAOGZ6CVTMA6JBJAMNR","target":"record","payload":{"canonical_record":{"source":{"id":"2603.16859","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-17T17:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"c0138d5d18aa4a757c5976c0cf53dd96e30a689e5846b65bc5dc1a0eb78e6aee","abstract_canon_sha256":"997a52369c5dd94605535f55c47bccc312be733f91d50b34f13dd5d590ac47fa"},"schema_version":"1.0"},"canonical_sha256":"3451d7fa8d038d9f0ab3603c90a40c6c6f9c79bf146a39c90f2c65752af9ba78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:29.743674Z","signature_b64":"2AXFaaNFWBLfR8QdN7eqhHLqI0v2Xw0mW7y33DdcysjsLt2XZnuOTLjnLioeZjAByIxf0+InHux7/4WdLyO+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3451d7fa8d038d9f0ab3603c90a40c6c6f9c79bf146a39c90f2c65752af9ba78","last_reissued_at":"2026-07-02T01:17:29.743019Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:29.743019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.16859","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qvwe1IoNj4l/g/Z1hbvhGHTebThX/S2pqCbAC56gCvR2X7mojMHlHTw7+bb/Ar8Ycc6PpCoIlzaZm0pgRorHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:45:20.196494Z"},"content_sha256":"a54f9e40d35c843f72d4f55e15ff2c962d232684543b5cd07ee98436df13914d","schema_version":"1.0","event_id":"sha256:a54f9e40d35c843f72d4f55e15ff2c962d232684543b5cd07ee98436df13914d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GRI5P6UNAOGZ6CVTMA6JBJAMNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiebo Luo, Jinfa Huang, Qingchuan Ma, Rongfang Luo, Rongrong Ji, Ruize Fang, Tianyu Xie, Wang Chen, Xiawu Zheng, Yan Yang, Yixuan Zou, Yuexiao Ma, Yuhui Zeng, Zhiqiang Lu","submitted_at":"2026-03-17T17:58:44Z","abstract_excerpt":"Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16859","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/2603.16859/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1XcTm65CnGSNfuOcfyz6sBxQqsYKhwjJbXjnjz4Nn8N69dpCJ855WgDitpHNHdn7BcoEKy7iP5QNw26Sj6jTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:45:20.197132Z"},"content_sha256":"97046cfe416a9205989380fb7858fecc7498d38caffec56c599b563e51d4d668","schema_version":"1.0","event_id":"sha256:97046cfe416a9205989380fb7858fecc7498d38caffec56c599b563e51d4d668"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR/bundle.json","state_url":"https://pith.science/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR/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":"2026-07-05T15:45:20Z","links":{"resolver":"https://pith.science/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR","bundle":"https://pith.science/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR/bundle.json","state":"https://pith.science/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GRI5P6UNAOGZ6CVTMA6JBJAMNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GRI5P6UNAOGZ6CVTMA6JBJAMNR","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":"997a52369c5dd94605535f55c47bccc312be733f91d50b34f13dd5d590ac47fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-17T17:58:44Z","title_canon_sha256":"c0138d5d18aa4a757c5976c0cf53dd96e30a689e5846b65bc5dc1a0eb78e6aee"},"schema_version":"1.0","source":{"id":"2603.16859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16859","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16859v2","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16859","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"GRI5P6UNAOGZ","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"GRI5P6UNAOGZ6CVT","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"GRI5P6UN","created_at":"2026-07-02T01:17:29Z"}],"graph_snapshots":[{"event_id":"sha256:97046cfe416a9205989380fb7858fecc7498d38caffec56c599b563e51d4d668","target":"graph","created_at":"2026-07-02T01:17:29Z","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/2603.16859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (wh","authors_text":"Jiebo Luo, Jinfa Huang, Qingchuan Ma, Rongfang Luo, Rongrong Ji, Ruize Fang, Tianyu Xie, Wang Chen, Xiawu Zheng, Yan Yang, Yixuan Zou, Yuexiao Ma, Yuhui Zeng, Zhiqiang Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-17T17:58:44Z","title":"SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16859","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:a54f9e40d35c843f72d4f55e15ff2c962d232684543b5cd07ee98436df13914d","target":"record","created_at":"2026-07-02T01:17:29Z","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":"997a52369c5dd94605535f55c47bccc312be733f91d50b34f13dd5d590ac47fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-17T17:58:44Z","title_canon_sha256":"c0138d5d18aa4a757c5976c0cf53dd96e30a689e5846b65bc5dc1a0eb78e6aee"},"schema_version":"1.0","source":{"id":"2603.16859","kind":"arxiv","version":2}},"canonical_sha256":"3451d7fa8d038d9f0ab3603c90a40c6c6f9c79bf146a39c90f2c65752af9ba78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3451d7fa8d038d9f0ab3603c90a40c6c6f9c79bf146a39c90f2c65752af9ba78","first_computed_at":"2026-07-02T01:17:29.743019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:29.743019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AXFaaNFWBLfR8QdN7eqhHLqI0v2Xw0mW7y33DdcysjsLt2XZnuOTLjnLioeZjAByIxf0+InHux7/4WdLyO+Aw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:29.743674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a54f9e40d35c843f72d4f55e15ff2c962d232684543b5cd07ee98436df13914d","sha256:97046cfe416a9205989380fb7858fecc7498d38caffec56c599b563e51d4d668"],"state_sha256":"c04d3361a64dbe3a476d7be1aefc58808d69ae624cca07e2506f032fcd65d5aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQf9EP3bN7BQHnhPl6yZCCc/IYbikBbCGHMmRtAvlCH2hi+e2PisBbPU6GXJClnyEhX/Pe5neKgxxRCk08saAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:45:20.203272Z","bundle_sha256":"cfbb9e0e473d9e0e15b6a75a1babe0e39b94a380d16bd21d47baf2401baf56ce"}}