{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YFLX3INSXUGT2MNOCMVOA47GFY","short_pith_number":"pith:YFLX3INS","schema_version":"1.0","canonical_sha256":"c1577da1b2bd0d3d31ae132ae073e62e1e2aee3c4ac00b60a39f52c119df276a","source":{"kind":"arxiv","id":"2503.05379","version":2},"attestation_state":"computed","paper":{"title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiaxing Zhao, Liefeng Bo, Xihan Wei","submitted_at":"2025-03-07T12:46:42Z","abstract_excerpt":"In this work, we present the first application of Reinforcement Learning with Verifiable Reward (RLVR) to an Omni-multimodal large language model in the context of emotion recognition, a task where both visual and audio modalities play crucial roles. We leverage RLVR to optimize the Omni model, significantly enhancing its performance in three key aspects: reasoning capability, emotion recognition accuracy, and generalization ability. The introduction of RLVR not only improves the model's overall performance on in-distribution data but also demonstrates superior robustness when evaluated on out"},"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":"2503.05379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T12:46:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a47a7afb3bae559fedf9094f59499bfd93ee1f72ca819a6bb2386b0bc95e2da3","abstract_canon_sha256":"dbf7c19550e812b1879f9b29d9c7bcd15a98df5e69f347f9d58b1ebe2205217d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:28.762608Z","signature_b64":"1z+aH9FmK3TXYI9AwnO3q2qzau748W8qEjGAxanKUCoFXK9toV0tcgdvJsckVyFn48MdrDb8ZJEDX/qijwRGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1577da1b2bd0d3d31ae132ae073e62e1e2aee3c4ac00b60a39f52c119df276a","last_reissued_at":"2026-07-05T10:27:28.762106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:28.762106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiaxing Zhao, Liefeng Bo, Xihan Wei","submitted_at":"2025-03-07T12:46:42Z","abstract_excerpt":"In this work, we present the first application of Reinforcement Learning with Verifiable Reward (RLVR) to an Omni-multimodal large language model in the context of emotion recognition, a task where both visual and audio modalities play crucial roles. We leverage RLVR to optimize the Omni model, significantly enhancing its performance in three key aspects: reasoning capability, emotion recognition accuracy, and generalization ability. The introduction of RLVR not only improves the model's overall performance on in-distribution data but also demonstrates superior robustness when evaluated on out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05379","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/2503.05379/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":"2503.05379","created_at":"2026-07-05T10:27:28.762166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05379v2","created_at":"2026-07-05T10:27:28.762166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05379","created_at":"2026-07-05T10:27:28.762166+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFLX3INSXUGT","created_at":"2026-07-05T10:27:28.762166+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFLX3INSXUGT2MNO","created_at":"2026-07-05T10:27:28.762166+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFLX3INS","created_at":"2026-07-05T10:27:28.762166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25325","citing_title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20970","citing_title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07643","citing_title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27652","citing_title":"MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05271","citing_title":"DeepEyesV2: Toward Agentic Multimodal Model","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02123","citing_title":"Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":290,"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":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11244","citing_title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02378","citing_title":"Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY","json":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY.json","graph_json":"https://pith.science/api/pith-number/YFLX3INSXUGT2MNOCMVOA47GFY/graph.json","events_json":"https://pith.science/api/pith-number/YFLX3INSXUGT2MNOCMVOA47GFY/events.json","paper":"https://pith.science/paper/YFLX3INS"},"agent_actions":{"view_html":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY","download_json":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY.json","view_paper":"https://pith.science/paper/YFLX3INS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05379&json=true","fetch_graph":"https://pith.science/api/pith-number/YFLX3INSXUGT2MNOCMVOA47GFY/graph.json","fetch_events":"https://pith.science/api/pith-number/YFLX3INSXUGT2MNOCMVOA47GFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY/action/storage_attestation","attest_author":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY/action/author_attestation","sign_citation":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY/action/citation_signature","submit_replication":"https://pith.science/pith/YFLX3INSXUGT2MNOCMVOA47GFY/action/replication_record"}},"created_at":"2026-07-05T10:27:28.762166+00:00","updated_at":"2026-07-05T10:27:28.762166+00:00"}