{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3KYQ6B2S2HFG5V2C54MM347FW","short_pith_number":"pith:K3KYQ6B2","schema_version":"1.0","canonical_sha256":"56d588783a968e5376ba1778c66f9f2d824ec07d3f0c5033ae0dba188ac2eb3e","source":{"kind":"arxiv","id":"2501.16566","version":2},"attestation_state":"computed","paper":{"title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Bin Liu, Haiyang Sun, Haoyu Chen, Jiangyan Yi, Jianhua Tao, Lan Chen, Licai Sun, Rui Liu, Xiaojiang Peng, Yong Ren, Zebang Cheng, Zheng Lian","submitted_at":"2025-01-27T23:18:39Z","abstract_excerpt":"The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level, from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description. However, the current community suffers from a lack of large-scale datasets with intensive, descriptive emotion annotations, as well as a multimodal-centric framework to maximize the potential of MLLMs for emotion understanding. To address this, we establish a new benchmark for MLLM-based emotion understanding with a novel dataset (M"},"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":"2501.16566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-27T23:18:39Z","cross_cats_sorted":[],"title_canon_sha256":"0d9b9377186294ecd7f33168ec67fbb64da609175f215063266c1f280c107dc2","abstract_canon_sha256":"ee85b030f1ed56b81fd860b0e87a0bdbea789faa39e8c0c62f6fd1833f49e25b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:48.965469Z","signature_b64":"H59kzJNeiOjZi025fzbzUJN6AWARvd7nwDK/vLsB+XXb+f96r/n55bFUyqUB4MLZbwO0Mv6/Etg0kqhlPS19Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56d588783a968e5376ba1778c66f9f2d824ec07d3f0c5033ae0dba188ac2eb3e","last_reissued_at":"2026-07-05T10:59:48.964974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:48.964974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Bin Liu, Haiyang Sun, Haoyu Chen, Jiangyan Yi, Jianhua Tao, Lan Chen, Licai Sun, Rui Liu, Xiaojiang Peng, Yong Ren, Zebang Cheng, Zheng Lian","submitted_at":"2025-01-27T23:18:39Z","abstract_excerpt":"The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level, from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description. However, the current community suffers from a lack of large-scale datasets with intensive, descriptive emotion annotations, as well as a multimodal-centric framework to maximize the potential of MLLMs for emotion understanding. To address this, we establish a new benchmark for MLLM-based emotion understanding with a novel dataset (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16566","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/2501.16566/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":"2501.16566","created_at":"2026-07-05T10:59:48.965034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16566v2","created_at":"2026-07-05T10:59:48.965034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16566","created_at":"2026-07-05T10:59:48.965034+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3KYQ6B2S2HF","created_at":"2026-07-05T10:59:48.965034+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3KYQ6B2S2HFG5V2","created_at":"2026-07-05T10:59:48.965034+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3KYQ6B2","created_at":"2026-07-05T10:59:48.965034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13192","citing_title":"Reasoning for Mobile User Experience with Multimodal LLMs: Task, Benchmark, and Approach","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11385","citing_title":"DeceptionX: From Multimodal Evidence to Explainable Deception Detection","ref_index":23,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09703","citing_title":"MOTOR-Bench: A Real-world Dataset and Multi-agent Framework for Zero-shot Human Mental State Understanding","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23348","citing_title":"EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW","json":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW.json","graph_json":"https://pith.science/api/pith-number/K3KYQ6B2S2HFG5V2C54MM347FW/graph.json","events_json":"https://pith.science/api/pith-number/K3KYQ6B2S2HFG5V2C54MM347FW/events.json","paper":"https://pith.science/paper/K3KYQ6B2"},"agent_actions":{"view_html":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW","download_json":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW.json","view_paper":"https://pith.science/paper/K3KYQ6B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16566&json=true","fetch_graph":"https://pith.science/api/pith-number/K3KYQ6B2S2HFG5V2C54MM347FW/graph.json","fetch_events":"https://pith.science/api/pith-number/K3KYQ6B2S2HFG5V2C54MM347FW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW/action/storage_attestation","attest_author":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW/action/author_attestation","sign_citation":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW/action/citation_signature","submit_replication":"https://pith.science/pith/K3KYQ6B2S2HFG5V2C54MM347FW/action/replication_record"}},"created_at":"2026-07-05T10:59:48.965034+00:00","updated_at":"2026-07-05T10:59:48.965034+00:00"}