{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VUKF5JE7ALM55SHSNOOYXO4ZZJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cb84ef11df916050ee23a0c1ba7aef07d9337dff8f753df2b643869e5d6c1123","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T03:01:22Z","title_canon_sha256":"63b9b3cb0c166d590c2a669dff3209945ddda221e2ef48f124e533c6419b531d"},"schema_version":"1.0","source":{"id":"2406.11161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11161","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11161v2","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11161","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"VUKF5JE7ALM5","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"VUKF5JE7ALM55SHS","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"VUKF5JE7","created_at":"2026-07-05T09:30:17Z"}],"graph_snapshots":[{"event_id":"sha256:cd484ef4f4bc00b49c6bb85bc071108b97a171613a238c9aedf71c2a8693689c","target":"graph","created_at":"2026-07-05T09:30:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.11161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Hauptmann, Jingdong Sun, Jun-Yan He, Kai Wang, Xiaojiang Peng, Yuxiang Lin, Zebang Cheng, Zheng Lian, Zhi-Qi Cheng","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T03:01:22Z","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11161","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4554fbad75f8764de13b96756f712b676b40652fc36191609970fdae637832d1","target":"record","created_at":"2026-07-05T09:30:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cb84ef11df916050ee23a0c1ba7aef07d9337dff8f753df2b643869e5d6c1123","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T03:01:22Z","title_canon_sha256":"63b9b3cb0c166d590c2a669dff3209945ddda221e2ef48f124e533c6419b531d"},"schema_version":"1.0","source":{"id":"2406.11161","kind":"arxiv","version":2}},"canonical_sha256":"ad145ea49f02d9dec8f26b9d8bbb99ca55c9c91ae5420f667c623d99fe88b5c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad145ea49f02d9dec8f26b9d8bbb99ca55c9c91ae5420f667c623d99fe88b5c3","first_computed_at":"2026-07-05T09:30:17.295120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:17.295120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zyNWEIsX7y37npOTWwN2Qjo49kzTb3Iw7lGTLS8p3edV9xEaItnS6pATwSdeX0dOZJgKhIK57b7o4dvnYUUBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:17.295639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4554fbad75f8764de13b96756f712b676b40652fc36191609970fdae637832d1","sha256:cd484ef4f4bc00b49c6bb85bc071108b97a171613a238c9aedf71c2a8693689c"],"state_sha256":"46116830f6fd17b1d288770e8f0ec1f275a9388a5a58af69bf19a80d4a3ef553"}