{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GGGRJZHAS6RO6WNPBWG2ZG7XXF","short_pith_number":"pith:GGGRJZHA","schema_version":"1.0","canonical_sha256":"318d14e4e097a2ef59af0d8dac9bf7b970ea929bb361b15df607ebfbdec8e87f","source":{"kind":"arxiv","id":"2503.21480","version":2},"attestation_state":"computed","paper":{"title":"OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Murzaku, Owen Rambow","submitted_at":"2025-03-27T13:12:49Z","abstract_excerpt":"The use of omni-LLMs (large language models that accept any modality as input), particularly for multimodal cognitive state tasks involving speech, is understudied. We present OmniVox, the first systematic evaluation of four omni-LLMs on the zero-shot emotion recognition task. We evaluate on two widely used multimodal emotion benchmarks: IEMOCAP and MELD, and find zero-shot omni-LLMs outperform or are competitive with fine-tuned audio models. Alongside our audio-only evaluation, we also evaluate omni-LLMs on text only and text and audio. We present acoustic prompting, an audio-specific prompti"},"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":"2503.21480","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-27T13:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"db5d5170e4b34ed62cf573223df9b2a85cbd26591db27c8d181bb776fe624904","abstract_canon_sha256":"617667da2976d0bb22ce0bff8b0d5da82a3b43bcfbe02ff1278a9a9245a44a30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:02.186807Z","signature_b64":"sNaCUjtTLfGFFjig4pI/Jedq2TPCYMmcsAqYExTDeOKg7lbQQqcm5lqXnIYUgrtwCyXWgbIxWcCkLKAPzFQVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"318d14e4e097a2ef59af0d8dac9bf7b970ea929bb361b15df607ebfbdec8e87f","last_reissued_at":"2026-07-05T10:41:02.186274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:02.186274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Murzaku, Owen Rambow","submitted_at":"2025-03-27T13:12:49Z","abstract_excerpt":"The use of omni-LLMs (large language models that accept any modality as input), particularly for multimodal cognitive state tasks involving speech, is understudied. We present OmniVox, the first systematic evaluation of four omni-LLMs on the zero-shot emotion recognition task. We evaluate on two widely used multimodal emotion benchmarks: IEMOCAP and MELD, and find zero-shot omni-LLMs outperform or are competitive with fine-tuned audio models. Alongside our audio-only evaluation, we also evaluate omni-LLMs on text only and text and audio. We present acoustic prompting, an audio-specific prompti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21480","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/2503.21480/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":"2503.21480","created_at":"2026-07-05T10:41:02.186353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21480v2","created_at":"2026-07-05T10:41:02.186353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21480","created_at":"2026-07-05T10:41:02.186353+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGGRJZHAS6RO","created_at":"2026-07-05T10:41:02.186353+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGGRJZHAS6RO6WNP","created_at":"2026-07-05T10:41:02.186353+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGGRJZHA","created_at":"2026-07-05T10:41:02.186353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18547","citing_title":"VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF","json":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF.json","graph_json":"https://pith.science/api/pith-number/GGGRJZHAS6RO6WNPBWG2ZG7XXF/graph.json","events_json":"https://pith.science/api/pith-number/GGGRJZHAS6RO6WNPBWG2ZG7XXF/events.json","paper":"https://pith.science/paper/GGGRJZHA"},"agent_actions":{"view_html":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF","download_json":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF.json","view_paper":"https://pith.science/paper/GGGRJZHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21480&json=true","fetch_graph":"https://pith.science/api/pith-number/GGGRJZHAS6RO6WNPBWG2ZG7XXF/graph.json","fetch_events":"https://pith.science/api/pith-number/GGGRJZHAS6RO6WNPBWG2ZG7XXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF/action/storage_attestation","attest_author":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF/action/author_attestation","sign_citation":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF/action/citation_signature","submit_replication":"https://pith.science/pith/GGGRJZHAS6RO6WNPBWG2ZG7XXF/action/replication_record"}},"created_at":"2026-07-05T10:41:02.186353+00:00","updated_at":"2026-07-05T10:41:02.186353+00:00"}