{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OHNVEV57C5R7ZRKJT5IFR7ZLGC","short_pith_number":"pith:OHNVEV57","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"},"canonical_sha256":"71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3","source":{"kind":"arxiv","id":"2604.18360","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18360","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18360v2","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18360","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"OHNVEV57C5R7","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"OHNVEV57C5R7ZRKJ","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"OHNVEV57","created_at":"2026-06-02T02:04:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OHNVEV57C5R7ZRKJT5IFR7ZLGC","target":"record","payload":{"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"},"canonical_sha256":"71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3","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"},"source_kind":"arxiv","source_id":"2604.18360","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fc+pwnNv/rp0jSHIabtpNc/5zJ6tUXJVCp4HcqtwCmOhVz72GDM3BV5LWgtJUxMCutg+nYkFwwV5vZkxsFfWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T00:45:48.712712Z"},"content_sha256":"c2ce2e98cdb9c0f636ab074130932af0d2232ec8b8db23590ab4f9b7f617adf7","schema_version":"1.0","event_id":"sha256:c2ce2e98cdb9c0f636ab074130932af0d2232ec8b8db23590ab4f9b7f617adf7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OHNVEV57C5R7ZRKJT5IFR7ZLGC","target":"graph","payload":{"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"},"verdict_id":"9b406d60-952b-437f-b121-3548b4c2c03b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FvRwd175efngm6Ii8Eu7Og3kITerT8R800GKnqKu+vF7RP2zRCEMrPzdqxjR99gTCZzEHFdis03yDGtItTfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T00:45:48.713359Z"},"content_sha256":"a1d003a7ca424c071b9aadb3a53689cd3905ff0e19d30695e4d52e654509bedd","schema_version":"1.0","event_id":"sha256:a1d003a7ca424c071b9aadb3a53689cd3905ff0e19d30695e4d52e654509bedd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/bundle.json","state_url":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T00:45:48Z","links":{"resolver":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC","bundle":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/bundle.json","state":"https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHNVEV57C5R7ZRKJT5IFR7ZLGC","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":"c71db82ae68cf48b45abec4ee3d1ebd433ea1122a17fda15efec9ac51d276218","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-20T14:50:33Z","title_canon_sha256":"fc418e7de2ea951045d10e7ac57469466a5bdaf533fe209814cf4a66b8a8d411"},"schema_version":"1.0","source":{"id":"2604.18360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18360","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18360v2","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18360","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"OHNVEV57C5R7","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"OHNVEV57C5R7ZRKJ","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"OHNVEV57","created_at":"2026-06-02T02:04:17Z"}],"graph_snapshots":[{"event_id":"sha256:a1d003a7ca424c071b9aadb3a53689cd3905ff0e19d30695e4d52e654509bedd","target":"graph","created_at":"2026-06-02T02:04:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives."}],"snapshot_sha256":"0f5fb61915f7b1ccebf1023f0a762097dfc8a791cd14010c149064ea35599d0c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T04:08:51.595166Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.18360/integrity.json","findings":[],"snapshot_sha256":"a3929a5b747ec6cde5e8f566a2d8a84b496d4c2e00fa82b0820ff3819c7eaccc","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Du-Seong Chang, HaeJun Yoo, Insung Lee, Myoung-Wan Koo, Yongseop Shin","cross_cats":["cs.CL"],"headline":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-20T14:50:33Z","title":"Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.18360","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T03:19:17.745809Z","id":"9b406d60-952b-437f-b121-3548b4c2c03b","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives.","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.","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."}},"verdict_id":"9b406d60-952b-437f-b121-3548b4c2c03b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2ce2e98cdb9c0f636ab074130932af0d2232ec8b8db23590ab4f9b7f617adf7","target":"record","created_at":"2026-06-02T02:04:17Z","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":"c71db82ae68cf48b45abec4ee3d1ebd433ea1122a17fda15efec9ac51d276218","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-20T14:50:33Z","title_canon_sha256":"fc418e7de2ea951045d10e7ac57469466a5bdaf533fe209814cf4a66b8a8d411"},"schema_version":"1.0","source":{"id":"2604.18360","kind":"arxiv","version":2}},"canonical_sha256":"71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3","first_computed_at":"2026-06-02T02:04:17.864783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:17.864783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WIoBkOhWcY6AtYZ45oJ8vxyUj3jTlWoLmAUF1l423hVaP2zoCF5Y/O80WgLv7rNifLkcCVHqK1aWu5B/HPvYBg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:17.865304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.18360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ce2e98cdb9c0f636ab074130932af0d2232ec8b8db23590ab4f9b7f617adf7","sha256:a1d003a7ca424c071b9aadb3a53689cd3905ff0e19d30695e4d52e654509bedd"],"state_sha256":"b83b6ecdb0b1c648d825cf1e4c176a866187272ec5c162618934c771940ba624"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2A1TrtY9PUc641EluG9xCADNkfod9COsoySvb+qdfI4atPdp/YoZ0jAZmMMgvpZXNDlwXWh/QgePRncZAWHlBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T00:45:48.718501Z","bundle_sha256":"bcbe7547d2fafbd5e541dc430f20fe7180e35ed615ab03abbe26bc8baf8c12f8"}}