{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B5VRELI4M4MZOGMU26MZCLSVSU","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":"b4e4a9ac313c661761a26eff0e5cc5576f85552e0d83bdf589e019cd9b1b755c","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-04-29T14:59:42Z","title_canon_sha256":"5c9e80b683539c8741bad11753092a857b22069404ab64601619eaeae766e595"},"schema_version":"1.0","source":{"id":"2504.20835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20835","created_at":"2026-07-05T10:55:49Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20835v1","created_at":"2026-07-05T10:55:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20835","created_at":"2026-07-05T10:55:49Z"},{"alias_kind":"pith_short_12","alias_value":"B5VRELI4M4MZ","created_at":"2026-07-05T10:55:49Z"},{"alias_kind":"pith_short_16","alias_value":"B5VRELI4M4MZOGMU","created_at":"2026-07-05T10:55:49Z"},{"alias_kind":"pith_short_8","alias_value":"B5VRELI4","created_at":"2026-07-05T10:55:49Z"}],"graph_snapshots":[{"event_id":"sha256:5e63344a122e9be9b9b8273ef2d85ef10fb099b5219476388f3051d523bf425b","target":"graph","created_at":"2026-07-05T10:55:49Z","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/2504.20835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have been extended to the speech domain, leading to the development of speech large language models (SLLMs). While existing SLLMs demonstrate strong performance in speech instruction-following for core languages (e.g., English), they often struggle with non-core languages due to the scarcity of paired speech-text data and limited multilingual semantic reasoning capabilities. To address this, we propose the semi-implicit Cross-lingual Speech Chain-of-Thought (XS-CoT) framework, which integrates speech-to-text translation into the reasoning process of SLLMs. The XS-CoT gene","authors_text":"Hexin Liu, Hongfei Xue, Jun Zhang, Lei Xie, Xuelong Geng, Yufeng Tang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-04-29T14:59:42Z","title":"Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20835","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":"sha256:0e27e7cc9ebe3f079e8f57679f7191cd584683fadff5035425a5670fe07e558b","target":"record","created_at":"2026-07-05T10:55:49Z","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":"b4e4a9ac313c661761a26eff0e5cc5576f85552e0d83bdf589e019cd9b1b755c","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-04-29T14:59:42Z","title_canon_sha256":"5c9e80b683539c8741bad11753092a857b22069404ab64601619eaeae766e595"},"schema_version":"1.0","source":{"id":"2504.20835","kind":"arxiv","version":1}},"canonical_sha256":"0f6b122d1c6719971994d799912e55952d0ea40012dde3a7c6b4d104363527a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f6b122d1c6719971994d799912e55952d0ea40012dde3a7c6b4d104363527a2","first_computed_at":"2026-07-05T10:55:49.566724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:49.566724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YZJGKznaapdq3IW0BeD/PCqpxQ/W1oBkQRXxI5Y3ipIVF4FW+cMlzKXbmOoPXqfIs3UTyf8DjKyIpHxjwaP3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:49.567230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e27e7cc9ebe3f079e8f57679f7191cd584683fadff5035425a5670fe07e558b","sha256:5e63344a122e9be9b9b8273ef2d85ef10fb099b5219476388f3051d523bf425b"],"state_sha256":"1925ae8233e5e79d6cc7bf75e037a22c52470e8701d5d6e88c0a39a6d6c82f6f"}