{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V7WOGIYZP4HPULDFYFGD7WWZTH","short_pith_number":"pith:V7WOGIYZ","schema_version":"1.0","canonical_sha256":"afece323197f0efa2c65c14c3fdad999cdd284af8e227a191f428a356caa45d9","source":{"kind":"arxiv","id":"2306.15401","version":6},"attestation_state":"computed","paper":{"title":"Explainable Multimodal Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.MM","authors_text":"Bin Liu, Haiyang Sun, Hao Gu, Jiangyan Yi, Jianhua Tao, Kang Chen, Ke Xu, Lan Chen, Licai Sun, Mingyu Xu, Shan Liang, Shun Chen, Siyuan Zhang, Ya Li, Zheng Lian, Zhuofan Wen","submitted_at":"2023-06-27T11:54:57Z","abstract_excerpt":"Multimodal emotion recognition is an important research topic in artificial intelligence, whose main goal is to integrate multimodal clues to identify human emotional states. Current works generally assume accurate labels for benchmark datasets and focus on developing more effective architectures. However, emotion annotation relies on subjective judgment. To obtain more reliable labels, existing datasets usually restrict the label space to some basic categories, then hire plenty of annotators and use majority voting to select the most likely label. However, this process may result in some corr"},"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":"2306.15401","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-06-27T11:54:57Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"d7c736415b549284cd5064394c515466664d3091933f26c865923cc70654ef57","abstract_canon_sha256":"8cf02fbed72cafe146150d255a46214cf1f92059115ff1abc39b4010d0d7d627"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:39.708708Z","signature_b64":"440GosKAuXlLWGf2VoyJkOnYROCRAcC31Xk5s09jFxRKLfqbwTZyyM3/GOTk+fU0XDT/Fl+aq2FIcjYHGLNHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afece323197f0efa2c65c14c3fdad999cdd284af8e227a191f428a356caa45d9","last_reissued_at":"2026-07-05T08:21:39.708082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:39.708082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Multimodal Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.MM","authors_text":"Bin Liu, Haiyang Sun, Hao Gu, Jiangyan Yi, Jianhua Tao, Kang Chen, Ke Xu, Lan Chen, Licai Sun, Mingyu Xu, Shan Liang, Shun Chen, Siyuan Zhang, Ya Li, Zheng Lian, Zhuofan Wen","submitted_at":"2023-06-27T11:54:57Z","abstract_excerpt":"Multimodal emotion recognition is an important research topic in artificial intelligence, whose main goal is to integrate multimodal clues to identify human emotional states. Current works generally assume accurate labels for benchmark datasets and focus on developing more effective architectures. However, emotion annotation relies on subjective judgment. To obtain more reliable labels, existing datasets usually restrict the label space to some basic categories, then hire plenty of annotators and use majority voting to select the most likely label. However, this process may result in some corr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15401","kind":"arxiv","version":6},"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/2306.15401/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":"2306.15401","created_at":"2026-07-05T08:21:39.708157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15401v6","created_at":"2026-07-05T08:21:39.708157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15401","created_at":"2026-07-05T08:21:39.708157+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7WOGIYZP4HP","created_at":"2026-07-05T08:21:39.708157+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7WOGIYZP4HPULDF","created_at":"2026-07-05T08:21:39.708157+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7WOGIYZ","created_at":"2026-07-05T08:21:39.708157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19950","citing_title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02123","citing_title":"Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06126","citing_title":"AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19417","citing_title":"MER 2026: From Discriminative Emotion Recognition to Generative Emotion Understanding","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH","json":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH.json","graph_json":"https://pith.science/api/pith-number/V7WOGIYZP4HPULDFYFGD7WWZTH/graph.json","events_json":"https://pith.science/api/pith-number/V7WOGIYZP4HPULDFYFGD7WWZTH/events.json","paper":"https://pith.science/paper/V7WOGIYZ"},"agent_actions":{"view_html":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH","download_json":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH.json","view_paper":"https://pith.science/paper/V7WOGIYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15401&json=true","fetch_graph":"https://pith.science/api/pith-number/V7WOGIYZP4HPULDFYFGD7WWZTH/graph.json","fetch_events":"https://pith.science/api/pith-number/V7WOGIYZP4HPULDFYFGD7WWZTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH/action/storage_attestation","attest_author":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH/action/author_attestation","sign_citation":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH/action/citation_signature","submit_replication":"https://pith.science/pith/V7WOGIYZP4HPULDFYFGD7WWZTH/action/replication_record"}},"created_at":"2026-07-05T08:21:39.708157+00:00","updated_at":"2026-07-05T08:21:39.708157+00:00"}