{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:77C5CWBJHFPSZDV6N7AZP733QU","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":"ea49d5362b7f020fdf3159d8b933e4d6cb02ab96082d5652c5980b461184f2a4","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-24T11:09:13Z","title_canon_sha256":"09f564fe6db062a244b024291eda6fc0412584a61a17444baec6f8f174a4fbc5"},"schema_version":"1.0","source":{"id":"2505.18644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18644","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18644v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18644","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"77C5CWBJHFPS","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"77C5CWBJHFPSZDV6","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"77C5CWBJ","created_at":"2026-07-05T11:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:233d73c433294814d5f65879b06faf198e94d1067ae1f0fa2db7054225ea5a3a","target":"graph","created_at":"2026-07-05T11:09:16Z","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/2505.18644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable generalization across tasks, leading to increased interest in integrating speech with LLMs. These speech LLMs (SLLMs) typically use supervised fine-tuning to align speech with text-based LLMs. However, the lack of annotated speech data across a wide range of tasks hinders alignment efficiency, resulting in poor generalization. To address these issues, we propose a novel multi-task 'behavior imitation' method with speech-text interleaving, called MTBI, which relies solely on paired speech and transcripts. By ensuring the LLM decoder generates e","authors_text":"Hui Wang, Jingran Xie, Xiang Li, Xixin Wu, Yang Xiang, Yue Yu, Zhiyong Wu","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-24T11:09:13Z","title":"Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18644","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:eb0e42eac22b38d3adf2f88eeb8d630b6f1edcc24acc9414b3219cce44e5c655","target":"record","created_at":"2026-07-05T11:09:16Z","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":"ea49d5362b7f020fdf3159d8b933e4d6cb02ab96082d5652c5980b461184f2a4","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-24T11:09:13Z","title_canon_sha256":"09f564fe6db062a244b024291eda6fc0412584a61a17444baec6f8f174a4fbc5"},"schema_version":"1.0","source":{"id":"2505.18644","kind":"arxiv","version":1}},"canonical_sha256":"ffc5d15829395f2c8ebe6fc197ff7b851af6618e1e0b92d0a6587cbef8c69c21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffc5d15829395f2c8ebe6fc197ff7b851af6618e1e0b92d0a6587cbef8c69c21","first_computed_at":"2026-07-05T11:09:16.975632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:16.975632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/TFjCgF6KTBBh/Zpgn8tfWxzKbrPfCXCfQCuaH6oMrWq1A3hhBdVoURKISimx5A3mQx2NC56l91Gs4AZwcSqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:16.976133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb0e42eac22b38d3adf2f88eeb8d630b6f1edcc24acc9414b3219cce44e5c655","sha256:233d73c433294814d5f65879b06faf198e94d1067ae1f0fa2db7054225ea5a3a"],"state_sha256":"144e57eb22942501fee6d4944be17b61daa660fd26a3e382f4f957a7cfe91f67"}