{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VUKF5JE7ALM55SHSNOOYXO4ZZJ","short_pith_number":"pith:VUKF5JE7","schema_version":"1.0","canonical_sha256":"ad145ea49f02d9dec8f26b9d8bbb99ca55c9c91ae5420f667c623d99fe88b5c3","source":{"kind":"arxiv","id":"2406.11161","version":2},"attestation_state":"computed","paper":{"title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.AI","authors_text":"Alexander Hauptmann, Jingdong Sun, Jun-Yan He, Kai Wang, Xiaojiang Peng, Yuxiang Lin, Zebang Cheng, Zheng Lian, Zhi-Qi Cheng","submitted_at":"2024-06-17T03:01:22Z","abstract_excerpt":"Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This datas"},"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":"2406.11161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T03:01:22Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"63b9b3cb0c166d590c2a669dff3209945ddda221e2ef48f124e533c6419b531d","abstract_canon_sha256":"cb84ef11df916050ee23a0c1ba7aef07d9337dff8f753df2b643869e5d6c1123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:17.295639Z","signature_b64":"zyNWEIsX7y37npOTWwN2Qjo49kzTb3Iw7lGTLS8p3edV9xEaItnS6pATwSdeX0dOZJgKhIK57b7o4dvnYUUBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad145ea49f02d9dec8f26b9d8bbb99ca55c9c91ae5420f667c623d99fe88b5c3","last_reissued_at":"2026-07-05T09:30:17.295120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:17.295120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.AI","authors_text":"Alexander Hauptmann, Jingdong Sun, Jun-Yan He, Kai Wang, Xiaojiang Peng, Yuxiang Lin, Zebang Cheng, Zheng Lian, Zhi-Qi Cheng","submitted_at":"2024-06-17T03:01:22Z","abstract_excerpt":"Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11161","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/2406.11161/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":"2406.11161","created_at":"2026-07-05T09:30:17.295186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11161v2","created_at":"2026-07-05T09:30:17.295186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11161","created_at":"2026-07-05T09:30:17.295186+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUKF5JE7ALM5","created_at":"2026-07-05T09:30:17.295186+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUKF5JE7ALM55SHS","created_at":"2026-07-05T09:30:17.295186+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUKF5JE7","created_at":"2026-07-05T09:30:17.295186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18228","citing_title":"MAJIC: Leveraging Articulatory Motion for Speech-based Emotion Recognition","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02089","citing_title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19950","citing_title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08847","citing_title":"EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ","json":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ.json","graph_json":"https://pith.science/api/pith-number/VUKF5JE7ALM55SHSNOOYXO4ZZJ/graph.json","events_json":"https://pith.science/api/pith-number/VUKF5JE7ALM55SHSNOOYXO4ZZJ/events.json","paper":"https://pith.science/paper/VUKF5JE7"},"agent_actions":{"view_html":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ","download_json":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ.json","view_paper":"https://pith.science/paper/VUKF5JE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11161&json=true","fetch_graph":"https://pith.science/api/pith-number/VUKF5JE7ALM55SHSNOOYXO4ZZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VUKF5JE7ALM55SHSNOOYXO4ZZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ/action/storage_attestation","attest_author":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ/action/author_attestation","sign_citation":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ/action/citation_signature","submit_replication":"https://pith.science/pith/VUKF5JE7ALM55SHSNOOYXO4ZZJ/action/replication_record"}},"created_at":"2026-07-05T09:30:17.295186+00:00","updated_at":"2026-07-05T09:30:17.295186+00:00"}