{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KXOZB7YXDGCE3ONPZSOMGGLAXX","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":"02b653030617e208daaa3d4677f44c55e1f955784fdca85c95bbaadcde29ed73","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-08T06:47:58Z","title_canon_sha256":"02a43e12ccb9780fb0af22347de59ca007d6b3e3b4852b62d6da5b48209f10bf"},"schema_version":"1.0","source":{"id":"2307.03917","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03917","created_at":"2026-07-05T06:55:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03917v3","created_at":"2026-07-05T06:55:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03917","created_at":"2026-07-05T06:55:56Z"},{"alias_kind":"pith_short_12","alias_value":"KXOZB7YXDGCE","created_at":"2026-07-05T06:55:56Z"},{"alias_kind":"pith_short_16","alias_value":"KXOZB7YXDGCE3ONP","created_at":"2026-07-05T06:55:56Z"},{"alias_kind":"pith_short_8","alias_value":"KXOZB7YX","created_at":"2026-07-05T06:55:56Z"}],"graph_snapshots":[{"event_id":"sha256:b65235580da81dabccd437253c9440f8e84c5d6033af2c4815a5125f0e4a6cc3","target":"graph","created_at":"2026-07-05T06:55:56Z","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/2307.03917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been explored well. The \"decoder-only\" architecture has also not been well studied for speech processing tasks. In this research, we introduce Speech-LLaMA, a novel approach that effectively incorporates acoustic information into text-based large language models. Our method leverages Connectionist Temporal Classification and a simple audio encoder to map","authors_text":"Bo Ren, Jian Wu, Jinyu Li, Linquan Liu, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yimeng Zhu, Yu Wu, Zhuo Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-08T06:47:58Z","title":"On decoder-only architecture for speech-to-text and large language model integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03917","kind":"arxiv","version":3},"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":"sha256:9504bc2b01df92b152e7db20c6cd975d83421427bd7d0d0c45d443b90077d506","target":"record","created_at":"2026-07-05T06:55:56Z","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":"02b653030617e208daaa3d4677f44c55e1f955784fdca85c95bbaadcde29ed73","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-08T06:47:58Z","title_canon_sha256":"02a43e12ccb9780fb0af22347de59ca007d6b3e3b4852b62d6da5b48209f10bf"},"schema_version":"1.0","source":{"id":"2307.03917","kind":"arxiv","version":3}},"canonical_sha256":"55dd90ff1719844db9afcc9cc31960bdc65c3f4e65cf81edbcf1de81d0b6e3f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55dd90ff1719844db9afcc9cc31960bdc65c3f4e65cf81edbcf1de81d0b6e3f7","first_computed_at":"2026-07-05T06:55:56.905155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:56.905155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mtoRGeOrhU2LvQQsA9/OTLWj7FnOHqUEVsIKyA1ZZThsO8FiAC5r1yusNw0C4r9jbSH5fSiVnXYGTQEgRTNzDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:56.905849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03917","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9504bc2b01df92b152e7db20c6cd975d83421427bd7d0d0c45d443b90077d506","sha256:b65235580da81dabccd437253c9440f8e84c5d6033af2c4815a5125f0e4a6cc3"],"state_sha256":"829c14babf9ea822f68ec5fdb12fc7c817d0189016fc572adb384328f90285dc"}