{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OVQLL2TMAKRB6VRL4JXJGUHFMD","short_pith_number":"pith:OVQLL2TM","schema_version":"1.0","canonical_sha256":"7560b5ea6c02a21f562be26e9350e560f8c2f6a03c902c3c00b7d9ca2f10152c","source":{"kind":"arxiv","id":"2407.02751","version":2},"attestation_state":"computed","paper":{"title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bj\\\"orn W. Schuller, Haizhou Li, Haolin Zuo, Rui Liu, Xiaofen Xing, Zheng Lian","submitted_at":"2024-07-03T01:56:00Z","abstract_excerpt":"Emotion and Intent Joint Understanding in Multimodal Conversation (MC-EIU) aims to decode the semantic information manifested in a multimodal conversational history, while inferring the emotions and intents simultaneously for the current utterance. MC-EIU is enabling technology for many human-computer interfaces. However, there is a lack of available datasets in terms of annotation, modality, language diversity, and accessibility. In this work, we propose an MC-EIU dataset, which features 7 emotion categories, 9 intent categories, 3 modalities, i.e., textual, acoustic, and visual content, and "},"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":"2407.02751","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T01:56:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90a8b2939463d3bb90fe35a3e2543d05621236a2e3d063f6ae5bf8992e8d7e82","abstract_canon_sha256":"cb3c8207cb5ae9714b2ca4675b955b11d22bf6bc15454623b0a341f80007cac6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:20.490176Z","signature_b64":"WZVd719KdWWW2q8TQZC9uprw0OHVv0twHU0KI4fciusE+9mLNHJv43wBiJhOoFAqZOzlYlKpQLLJ0V8KD0S7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7560b5ea6c02a21f562be26e9350e560f8c2f6a03c902c3c00b7d9ca2f10152c","last_reissued_at":"2026-07-05T08:40:20.489719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:20.489719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bj\\\"orn W. Schuller, Haizhou Li, Haolin Zuo, Rui Liu, Xiaofen Xing, Zheng Lian","submitted_at":"2024-07-03T01:56:00Z","abstract_excerpt":"Emotion and Intent Joint Understanding in Multimodal Conversation (MC-EIU) aims to decode the semantic information manifested in a multimodal conversational history, while inferring the emotions and intents simultaneously for the current utterance. MC-EIU is enabling technology for many human-computer interfaces. However, there is a lack of available datasets in terms of annotation, modality, language diversity, and accessibility. In this work, we propose an MC-EIU dataset, which features 7 emotion categories, 9 intent categories, 3 modalities, i.e., textual, acoustic, and visual content, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02751","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/2407.02751/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":"2407.02751","created_at":"2026-07-05T08:40:20.489774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02751v2","created_at":"2026-07-05T08:40:20.489774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02751","created_at":"2026-07-05T08:40:20.489774+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVQLL2TMAKRB","created_at":"2026-07-05T08:40:20.489774+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVQLL2TMAKRB6VRL","created_at":"2026-07-05T08:40:20.489774+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVQLL2TM","created_at":"2026-07-05T08:40:20.489774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12700","citing_title":"MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD","json":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD.json","graph_json":"https://pith.science/api/pith-number/OVQLL2TMAKRB6VRL4JXJGUHFMD/graph.json","events_json":"https://pith.science/api/pith-number/OVQLL2TMAKRB6VRL4JXJGUHFMD/events.json","paper":"https://pith.science/paper/OVQLL2TM"},"agent_actions":{"view_html":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD","download_json":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD.json","view_paper":"https://pith.science/paper/OVQLL2TM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02751&json=true","fetch_graph":"https://pith.science/api/pith-number/OVQLL2TMAKRB6VRL4JXJGUHFMD/graph.json","fetch_events":"https://pith.science/api/pith-number/OVQLL2TMAKRB6VRL4JXJGUHFMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD/action/storage_attestation","attest_author":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD/action/author_attestation","sign_citation":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD/action/citation_signature","submit_replication":"https://pith.science/pith/OVQLL2TMAKRB6VRL4JXJGUHFMD/action/replication_record"}},"created_at":"2026-07-05T08:40:20.489774+00:00","updated_at":"2026-07-05T08:40:20.489774+00:00"}