{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OHNVEV57C5R7ZRKJT5IFR7ZLGC","short_pith_number":"pith:OHNVEV57","schema_version":"1.0","canonical_sha256":"71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3","source":{"kind":"arxiv","id":"2604.18360","version":2},"attestation_state":"computed","paper":{"title":"Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives.","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Du-Seong Chang, HaeJun Yoo, Insung Lee, Myoung-Wan Koo, Yongseop Shin","submitted_at":"2026-04-20T14:50:33Z","abstract_excerpt":"Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world search behavior, limiting their assessment of practical retrieval robustness. We present Omni-Embed-Audio (OEA), a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding. To systematically evaluate robustness beyond caption-style queries, we introduce User-Intent Queries (UIQs) - five formulations reflecting natural search behavior"},"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":"2604.18360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-20T14:50:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc418e7de2ea951045d10e7ac57469466a5bdaf533fe209814cf4a66b8a8d411","abstract_canon_sha256":"c71db82ae68cf48b45abec4ee3d1ebd433ea1122a17fda15efec9ac51d276218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:17.865304Z","signature_b64":"WIoBkOhWcY6AtYZ45oJ8vxyUj3jTlWoLmAUF1l423hVaP2zoCF5Y/O80WgLv7rNifLkcCVHqK1aWu5B/HPvYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3","last_reissued_at":"2026-06-02T02:04:17.864783Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:17.864783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives.","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Du-Seong Chang, HaeJun Yoo, Insung Lee, Myoung-Wan Koo, Yongseop Shin","submitted_at":"2026-04-20T14:50:33Z","abstract_excerpt":"Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world search behavior, limiting their assessment of practical retrieval robustness. We present Omni-Embed-Audio (OEA), a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding. To systematically evaluate robustness beyond caption-style queries, we introduce User-Intent Queries (UIQs) - five formulations reflecting natural search behavior"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas: (1) dominant text-to-text retrieval (+22% relative improvement), and (2) substantially superior hard negative discrimination (+4.3%p HNSR@10, +34.7% relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the five User-Intent Query formulations accurately capture real-world search behavior and that observed gains are caused by the multimodal LLM backbone rather than differences in training data, scale, or other unstated factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Omni-Embed-Audio uses multimodal LLMs to match CLAP on standard audio retrieval while improving text-to-text retrieval by 22% relative and hard negative discrimination by 4.3 points HNSR@10 on user-intent queries.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0f5fb61915f7b1ccebf1023f0a762097dfc8a791cd14010c149064ea35599d0c"},"source":{"id":"2604.18360","kind":"arxiv","version":2},"verdict":{"id":"9b406d60-952b-437f-b121-3548b4c2c03b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T03:19:17.745809Z","strongest_claim":"OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas: (1) dominant text-to-text retrieval (+22% relative improvement), and (2) substantially superior hard negative discrimination (+4.3%p HNSR@10, +34.7% relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries.","one_line_summary":"Omni-Embed-Audio uses multimodal LLMs to match CLAP on standard audio retrieval while improving text-to-text retrieval by 22% relative and hard negative discrimination by 4.3 points HNSR@10 on user-intent queries.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the five User-Intent Query formulations accurately capture real-world search behavior and that observed gains are caused by the multimodal LLM backbone rather than differences in training data, scale, or other unstated factors.","pith_extraction_headline":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.18360/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T04:08:51.595166Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a3929a5b747ec6cde5e8f566a2d8a84b496d4c2e00fa82b0820ff3819c7eaccc"},"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":"2604.18360","created_at":"2026-06-02T02:04:17.864840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.18360v2","created_at":"2026-06-02T02:04:17.864840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18360","created_at":"2026-06-02T02:04:17.864840+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHNVEV57C5R7","created_at":"2026-06-02T02:04:17.864840+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHNVEV57C5R7ZRKJ","created_at":"2026-06-02T02:04:17.864840+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHNVEV57","created_at":"2026-06-02T02:04:17.864840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC","json":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC.json","graph_json":"https://pith.science/api/pith-number/OHNVEV57C5R7ZRKJT5IFR7ZLGC/graph.json","events_json":"https://pith.science/api/pith-number/OHNVEV57C5R7ZRKJT5IFR7ZLGC/events.json","paper":"https://pith.science/paper/OHNVEV57"},"agent_actions":{"view_html":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC","download_json":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC.json","view_paper":"https://pith.science/paper/OHNVEV57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.18360&json=true","fetch_graph":"https://pith.science/api/pith-number/OHNVEV57C5R7ZRKJT5IFR7ZLGC/graph.json","fetch_events":"https://pith.science/api/pith-number/OHNVEV57C5R7ZRKJT5IFR7ZLGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/action/storage_attestation","attest_author":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/action/author_attestation","sign_citation":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/action/citation_signature","submit_replication":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/action/replication_record"}},"created_at":"2026-06-02T02:04:17.864840+00:00","updated_at":"2026-06-02T02:04:17.864840+00:00"}