{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4ULKVTBSD5FZPWHHS2PI3HGJLL","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":"6164e2c792484793ace88d3435b9552649525d230c850dc5da73623ecd436cb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:23:25Z","title_canon_sha256":"e72cb6e1dedcbe796f99c1cf12c1199865b6c0a29de6162303dd7273b5d44fba"},"schema_version":"1.0","source":{"id":"2305.11000","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11000","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11000v2","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11000","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"4ULKVTBSD5FZ","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"4ULKVTBSD5FZPWHH","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"4ULKVTBS","created_at":"2026-07-05T06:11:46Z"}],"graph_snapshots":[{"event_id":"sha256:a8ff6631b3a0dd2efffe037a0c338dc0632cb77c3a702baad27d993e7c3b8554","target":"graph","created_at":"2026-07-05T06:11:46Z","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/2305.11000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. However, current speech-language models typically adopt the cascade paradigm, preventing inter-modal knowledge transfer. In this paper, we propose SpeechGPT, a large language model with intrinsic cross-modal conversational abilities, capable of perceiving and generating multi-model content. With discrete speech representations, we first construct SpeechInstruct, a large-scale cross-modal speech instruction dataset. ","authors_text":"Dong Zhang, Jun Zhan, Pengyu Wang, Shimin Li, Xin Zhang, Xipeng Qiu, Yaqian Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:23:25Z","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11000","kind":"arxiv","version":2},"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:ac59ad85ab1c3dbc215c9099212ccfa9fd33b7cdc216fa403a7104b530d07ebb","target":"record","created_at":"2026-07-05T06:11:46Z","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":"6164e2c792484793ace88d3435b9552649525d230c850dc5da73623ecd436cb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:23:25Z","title_canon_sha256":"e72cb6e1dedcbe796f99c1cf12c1199865b6c0a29de6162303dd7273b5d44fba"},"schema_version":"1.0","source":{"id":"2305.11000","kind":"arxiv","version":2}},"canonical_sha256":"e516aacc321f4b97d8e7969e8d9cc95acd3a46bb31e65a6f332a91d8498892d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e516aacc321f4b97d8e7969e8d9cc95acd3a46bb31e65a6f332a91d8498892d2","first_computed_at":"2026-07-05T06:11:46.416771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:46.416771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yul18DKrHukgpCc1J8a1mC2Ua8jd9RbyDk8cVOMpUBBDi8rguHRqtKmyAhmfzHaO20PMz66Z+G0gXpH4EhM/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:46.417189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11000","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac59ad85ab1c3dbc215c9099212ccfa9fd33b7cdc216fa403a7104b530d07ebb","sha256:a8ff6631b3a0dd2efffe037a0c338dc0632cb77c3a702baad27d993e7c3b8554"],"state_sha256":"f2cdd0dc6a02b251d06051d36a20be1be281932479f8b834b8fff952e86523c3"}