{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TV7BUSLEZQW5FKCHECRSS5Z3YJ","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":"25886727934d9d421ce5af623934acd0ff28770912b0bbf982f5b981f9383d20","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T14:39:47Z","title_canon_sha256":"b8b6ff34d24950cb06dc7bb67b4d8a7b8380eae6b45f884670fc934162f78fda"},"schema_version":"1.0","source":{"id":"2305.16107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16107","created_at":"2026-07-05T06:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16107v1","created_at":"2026-07-05T06:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16107","created_at":"2026-07-05T06:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"TV7BUSLEZQW5","created_at":"2026-07-05T06:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"TV7BUSLEZQW5FKCH","created_at":"2026-07-05T06:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"TV7BUSLE","created_at":"2026-07-05T06:13:59Z"}],"graph_snapshots":[{"event_id":"sha256:55277be335d74146e3c4cbde7551263231d7497e58ac31d8c964eab1103fbdd7","target":"graph","created_at":"2026-07-05T06:13:59Z","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/2305.16107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text, such as speech-to-text, text-to-text, text-to-speech, and speech-to-speech tasks, as a conditional codec language model task via multi-task learning framework. To accomplish this, we first convert all the speech utterances to discrete tokens (similar to the textual data) using an offline n","authors_text":"Furu Wei, Jinyu Li, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yu Wu, Zhuo Chen, Ziqiang Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T14:39:47Z","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16107","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":"sha256:0f33275dd2b5ec6065d73a570ed72c635a7e1e36b90af1af67293cf4aed8eb2b","target":"record","created_at":"2026-07-05T06:13:59Z","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":"25886727934d9d421ce5af623934acd0ff28770912b0bbf982f5b981f9383d20","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T14:39:47Z","title_canon_sha256":"b8b6ff34d24950cb06dc7bb67b4d8a7b8380eae6b45f884670fc934162f78fda"},"schema_version":"1.0","source":{"id":"2305.16107","kind":"arxiv","version":1}},"canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","first_computed_at":"2026-07-05T06:13:59.666165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:59.666165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lRsdbP6eMWkmk60W11oHsnyLxqzZFnKB6T0L+5E7nCYs2WRlK16VzItuD885Q1Lvn5asKOsCOEOvVMFmCnSzAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:59.666557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f33275dd2b5ec6065d73a570ed72c635a7e1e36b90af1af67293cf4aed8eb2b","sha256:55277be335d74146e3c4cbde7551263231d7497e58ac31d8c964eab1103fbdd7"],"state_sha256":"8b08218fe2623be73783f870a9abdc84f1c2a71fb2c9cf598cd52faf1aae131c"}