{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4766DFEO3EAOH6F67SV6EYBWTR","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":"3a3b6230f5f60622118639c54023571685bb07b8f370f81833ea1e24d332a8ad","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T07:12:12Z","title_canon_sha256":"03408a39bcb8a0dba09a061dc41a314c06543635e1c1c96efd1691a3ecfeeafa"},"schema_version":"1.0","source":{"id":"2406.07012","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07012","created_at":"2026-07-05T08:32:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07012v2","created_at":"2026-07-05T08:32:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07012","created_at":"2026-07-05T08:32:42Z"},{"alias_kind":"pith_short_12","alias_value":"4766DFEO3EAO","created_at":"2026-07-05T08:32:42Z"},{"alias_kind":"pith_short_16","alias_value":"4766DFEO3EAOH6F6","created_at":"2026-07-05T08:32:42Z"},{"alias_kind":"pith_short_8","alias_value":"4766DFEO","created_at":"2026-07-05T08:32:42Z"}],"graph_snapshots":[{"event_id":"sha256:b417a248ff8358f0869e9a523987c64ca2497ab0181d02fd5720bd1c85f9900a","target":"graph","created_at":"2026-07-05T08:32:42Z","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/2406.07012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given the abundance of non-English content in real-world data. To address these linguistic disparities, we propose a language enhancement (LE), using a multilingual text encoder (SONAR) to encode the text data with language-specific information. Additionally, we optimize the audio encoder through the application of consistent ensemble distillation (CED), ","authors_text":"Bin Wang, Heinrich Dinkel, Jizhong Liu, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T07:12:12Z","title":"Bridging Language Gaps in Audio-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07012","kind":"arxiv","version":2},"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":"sha256:2be16a57353913904c2b479d4c598dcb91353e0faeba0cf82caf788088919483","target":"record","created_at":"2026-07-05T08:32:42Z","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":"3a3b6230f5f60622118639c54023571685bb07b8f370f81833ea1e24d332a8ad","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T07:12:12Z","title_canon_sha256":"03408a39bcb8a0dba09a061dc41a314c06543635e1c1c96efd1691a3ecfeeafa"},"schema_version":"1.0","source":{"id":"2406.07012","kind":"arxiv","version":2}},"canonical_sha256":"e7fde1948ed900e3f8befcabe260369c6645e690a8d40a02a1809535fb49424c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7fde1948ed900e3f8befcabe260369c6645e690a8d40a02a1809535fb49424c","first_computed_at":"2026-07-05T08:32:42.284339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:42.284339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vKW4+NFOeNghH67TAOQ3yCgaJqjI/x0XPc6gFYHpmIPWIGwCqA/KeQAJWa/50O9ubk+k7z1e+rvpJ6GNY8xpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:42.284816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07012","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2be16a57353913904c2b479d4c598dcb91353e0faeba0cf82caf788088919483","sha256:b417a248ff8358f0869e9a523987c64ca2497ab0181d02fd5720bd1c85f9900a"],"state_sha256":"f7069ee9e5084c600905b6505cd26119c613113a3574562b1966b6ca4c3b0f2f"}