{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G3QNB57AYHE4AVDYM2EETUJMFP","short_pith_number":"pith:G3QNB57A","schema_version":"1.0","canonical_sha256":"36e0d0f7e0c1c9c05478668849d12c2be8845b0a47465fbfb572511228e90c31","source":{"kind":"arxiv","id":"2510.07355","version":2},"attestation_state":"computed","paper":{"title":"AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.MM","authors_text":"Ajay Kankipati, Akshaj Gupta, Dingkun Zhou, Gopala Anumanchipalli, Grace Wang, Guan-Ting Lin, Huang-Cheng Chou, Jiachen Lian, Kan Jen Cheng, Krish Patel, Mohul Shukla, Sara Kofman, Tingle Li, Vibhor Narang, Xiaoyu Shi, Zeyi Austin Li, Zongli Ye","submitted_at":"2025-10-08T14:13:28Z","abstract_excerpt":"Emotions conveyed through voice and face shape engagement and context in human AI interaction. Despite rapid progress in omni modal large language models, the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV EMO Reasoning, a benchmark designed to systematically assess emotional reasoning abilities in large language models. The framework uses a curated audiovisual corpus comprising synthetic single turn and multi turn dialogues and a real world subset, together with emotion perception and interaction reasoning metrics, to eva"},"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":"2510.07355","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-10-08T14:13:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1daf042234aefa71e5b08d7421f8bed21d0b37699bf8764b5b4a785b79c38c74","abstract_canon_sha256":"26a70eb0250430683651456396c5e93858eca4189c06edc8c4f362cfa3bebb50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:36.928346Z","signature_b64":"KUkvCzdXk+seWTSLm3/Tj8j8/X2UH+mRA3bBgSbhBJxyjx3kBkxAZaBnuuvF4Px1MXOOfeW9MxNZzTETzCbLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e0d0f7e0c1c9c05478668849d12c2be8845b0a47465fbfb572511228e90c31","last_reissued_at":"2026-05-29T02:05:36.927858Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:36.927858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.MM","authors_text":"Ajay Kankipati, Akshaj Gupta, Dingkun Zhou, Gopala Anumanchipalli, Grace Wang, Guan-Ting Lin, Huang-Cheng Chou, Jiachen Lian, Kan Jen Cheng, Krish Patel, Mohul Shukla, Sara Kofman, Tingle Li, Vibhor Narang, Xiaoyu Shi, Zeyi Austin Li, Zongli Ye","submitted_at":"2025-10-08T14:13:28Z","abstract_excerpt":"Emotions conveyed through voice and face shape engagement and context in human AI interaction. Despite rapid progress in omni modal large language models, the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV EMO Reasoning, a benchmark designed to systematically assess emotional reasoning abilities in large language models. The framework uses a curated audiovisual corpus comprising synthetic single turn and multi turn dialogues and a real world subset, together with emotion perception and interaction reasoning metrics, to eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.07355","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/2510.07355/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.07355","created_at":"2026-05-29T02:05:36.927917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.07355v2","created_at":"2026-05-29T02:05:36.927917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.07355","created_at":"2026-05-29T02:05:36.927917+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3QNB57AYHE4","created_at":"2026-05-29T02:05:36.927917+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3QNB57AYHE4AVDY","created_at":"2026-05-29T02:05:36.927917+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3QNB57A","created_at":"2026-05-29T02:05:36.927917+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/G3QNB57AYHE4AVDYM2EETUJMFP","json":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP.json","graph_json":"https://pith.science/api/pith-number/G3QNB57AYHE4AVDYM2EETUJMFP/graph.json","events_json":"https://pith.science/api/pith-number/G3QNB57AYHE4AVDYM2EETUJMFP/events.json","paper":"https://pith.science/paper/G3QNB57A"},"agent_actions":{"view_html":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP","download_json":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP.json","view_paper":"https://pith.science/paper/G3QNB57A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.07355&json=true","fetch_graph":"https://pith.science/api/pith-number/G3QNB57AYHE4AVDYM2EETUJMFP/graph.json","fetch_events":"https://pith.science/api/pith-number/G3QNB57AYHE4AVDYM2EETUJMFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP/action/storage_attestation","attest_author":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP/action/author_attestation","sign_citation":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP/action/citation_signature","submit_replication":"https://pith.science/pith/G3QNB57AYHE4AVDYM2EETUJMFP/action/replication_record"}},"created_at":"2026-05-29T02:05:36.927917+00:00","updated_at":"2026-05-29T02:05:36.927917+00:00"}