{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T5FEL7FDKYXPUNL5X53YOYOD37","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":"992f81b1e7b35267b0e6b9d5ec87b9ef977559f124ec1af9287fe0283158cb6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T04:35:50Z","title_canon_sha256":"3a63867b2fa9230fbf70b178baf20f940491a8e428969a36186523b327277c14"},"schema_version":"1.0","source":{"id":"2406.17272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17272","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17272v1","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17272","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_12","alias_value":"T5FEL7FDKYXP","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_16","alias_value":"T5FEL7FDKYXPUNL5","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_8","alias_value":"T5FEL7FD","created_at":"2026-07-05T08:36:32Z"}],"graph_snapshots":[{"event_id":"sha256:84baed7576636330b2aa74538c7392b32780df9f0859ba81d498f34d721e61cd","target":"graph","created_at":"2026-07-05T08:36:32Z","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/2406.17272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce speech-text alignment, and high insertion errors especially in domain mismatch conditions. This paper presents a comprehensive solution to address these issues. We begin by investigating more thoughtful fine-tuning schemes. Next, we propose a matching loss to enhance alignment between modalities. Finally, we explore training and inference methods to mitigate hi","authors_text":"Jun Zhang, Lu Lu, Tao Han, Van Tung Pham, Wei Li, Yist Lin, Yuxuan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T04:35:50Z","title":"A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17272","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":"sha256:079bffdc5b1a5ea08936e2a3a7607f0ea1e848991fea432e06c8087343b7f840","target":"record","created_at":"2026-07-05T08:36:32Z","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":"992f81b1e7b35267b0e6b9d5ec87b9ef977559f124ec1af9287fe0283158cb6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T04:35:50Z","title_canon_sha256":"3a63867b2fa9230fbf70b178baf20f940491a8e428969a36186523b327277c14"},"schema_version":"1.0","source":{"id":"2406.17272","kind":"arxiv","version":1}},"canonical_sha256":"9f4a45fca3562efa357dbf778761c3dfc5018df148743133a47dad5017fddf8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f4a45fca3562efa357dbf778761c3dfc5018df148743133a47dad5017fddf8e","first_computed_at":"2026-07-05T08:36:32.050941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:32.050941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KOdHJ3yK7A++64nPOFTugmlhGNhdKPLYb+dOiULljKnRZWkfGCW9CitjsAKyAivHiY9CuwH6NaCqmvolrXz6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:32.051379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:079bffdc5b1a5ea08936e2a3a7607f0ea1e848991fea432e06c8087343b7f840","sha256:84baed7576636330b2aa74538c7392b32780df9f0859ba81d498f34d721e61cd"],"state_sha256":"def149f97a91fa4164b52344542fe37def99825435104747c46e613490ea2e0f"}