{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XRXQKAHZJBETOD5RM6LNM57MON","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":"6745c65435a8cdb4f3bc1f60bc8871b50b2d0fcc06f43972c66344534525e2bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-17T12:10:19Z","title_canon_sha256":"dd099d291e0be82161c0bf07091bab7b791b74ac288c5de6edce59793f2d1ec3"},"schema_version":"1.0","source":{"id":"2506.14445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14445","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14445v1","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14445","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"XRXQKAHZJBET","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"XRXQKAHZJBETOD5R","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"XRXQKAHZ","created_at":"2026-07-05T11:22:56Z"}],"graph_snapshots":[{"event_id":"sha256:03b34b6534d52864424da418317ee8f5757140438b8aa2fd1de2f5eae02f1f63","target":"graph","created_at":"2026-07-05T11:22:56Z","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/2506.14445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have seen substantial progress in recent years. However, their ability to represent multimodal information in the acoustic domain remains underexplored. In this work, we introduce Vela, a novel framework designed to adapt MLLMs for the generation of universal multimodal embeddings. By leveraging MLLMs with specially crafted prompts and selected in-context learning examples, Vela effectively bridges the modality gap across various modalities. We then propose a single-modality training approach, where the model is trained exclusively on text pairs. Our ex","authors_text":"Bo Chen, Jieming Zhu, Minghui Fang, Minjie Hong, Ruofan Hu, Tao Jin, Xiaoda Yang, Yan Xia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-17T12:10:19Z","title":"Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14445","kind":"arxiv","version":1},"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:a08a3b05dd1eea5b5f474168ab8c026b1ada230ba07f08bbd028d3c818ca420b","target":"record","created_at":"2026-07-05T11:22:56Z","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":"6745c65435a8cdb4f3bc1f60bc8871b50b2d0fcc06f43972c66344534525e2bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-17T12:10:19Z","title_canon_sha256":"dd099d291e0be82161c0bf07091bab7b791b74ac288c5de6edce59793f2d1ec3"},"schema_version":"1.0","source":{"id":"2506.14445","kind":"arxiv","version":1}},"canonical_sha256":"bc6f0500f94849370fb16796d677ec734cbc83fb80c04c8e8c6b98dfccf6eec0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc6f0500f94849370fb16796d677ec734cbc83fb80c04c8e8c6b98dfccf6eec0","first_computed_at":"2026-07-05T11:22:56.705273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:56.705273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bk9+1sISGg5ovXnWJSCYo/mtHWH1dMLdhC/oZ6gYTVgtbfnVfrP62FolBIEFQHNRFPdB9HAHv+piZILLdKDkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:56.705795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a08a3b05dd1eea5b5f474168ab8c026b1ada230ba07f08bbd028d3c818ca420b","sha256:03b34b6534d52864424da418317ee8f5757140438b8aa2fd1de2f5eae02f1f63"],"state_sha256":"e365e0ea9a9de8279488b576519c3bc39620d83bd20e53d7a20a0b91924d6158"}