{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YL5HM35HKMDBZWY74JSE776PE7","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":"7b43dfa3ff4aad97a8b6c75a307df19daa2bbf77336b1abf9b5e3e1d8e1b1c31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T08:49:48Z","title_canon_sha256":"fcca0ec17c5de1ee2ac095790c2a47e1a3f6cdaa068a37764904fb9c174d8100"},"schema_version":"1.0","source":{"id":"2608.04586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04586","created_at":"2026-08-06T01:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04586v1","created_at":"2026-08-06T01:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04586","created_at":"2026-08-06T01:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"YL5HM35HKMDB","created_at":"2026-08-06T01:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"YL5HM35HKMDBZWY7","created_at":"2026-08-06T01:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"YL5HM35H","created_at":"2026-08-06T01:36:12Z"}],"graph_snapshots":[{"event_id":"sha256:ef1b7c4659a4c6b12dc0f6bef77f3994a62af741c1841faa942585bdb396a8d7","target":"graph","created_at":"2026-08-06T01:36:12Z","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/2608.04586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT). However, when processing multilingual speech inputs, a single speech encoder shared across all languages suffers from the curse of multilinguality: languages at different resource levels compete for limited representation capacity, leading to strong high-resource performance but substantial degradation on low-resource speech. To address this problem and improve multilingual consistency, we propose MSRT, a novel framework built around a resource-aware Mixture of Speech Encoders (MoSE","authors_text":"Bo Yang, Chengpeng Fu, Kaiyuan Liu, Ming Liu, Yexing Du, Youcheng Pan, Yu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T08:49:48Z","title":"Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04586","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:dc3e57d5d460be795030dd9e7a18e5677d716706036a0b2732cff7f2b2333bc1","target":"record","created_at":"2026-08-06T01:36:12Z","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":"7b43dfa3ff4aad97a8b6c75a307df19daa2bbf77336b1abf9b5e3e1d8e1b1c31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T08:49:48Z","title_canon_sha256":"fcca0ec17c5de1ee2ac095790c2a47e1a3f6cdaa068a37764904fb9c174d8100"},"schema_version":"1.0","source":{"id":"2608.04586","kind":"arxiv","version":1}},"canonical_sha256":"c2fa766fa753061cdb1fe2644fffcf27f7ebc59af2105e2792f99278978aceda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2fa766fa753061cdb1fe2644fffcf27f7ebc59af2105e2792f99278978aceda","first_computed_at":"2026-08-06T01:36:12.766396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:36:12.766396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YqWl/1AOx/6T9N8binim07i8/TV2HQikE7qnu4utTB1ztl4i7najVmEwLVWi2OVi+EC9XG6TyBa8L+731BncBQ==","signature_status":"signed_v1","signed_at":"2026-08-06T01:36:12.767817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc3e57d5d460be795030dd9e7a18e5677d716706036a0b2732cff7f2b2333bc1","sha256:ef1b7c4659a4c6b12dc0f6bef77f3994a62af741c1841faa942585bdb396a8d7"],"state_sha256":"273d01f2505ca4c95ac6a98761968b80dcb28c1e062a88b40d3a45a8c96463d3"}