{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TV7BUSLEZQW5FKCHECRSS5Z3YJ","short_pith_number":"pith:TV7BUSLE","canonical_record":{"source":{"id":"2305.16107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T14:39:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b8b6ff34d24950cb06dc7bb67b4d8a7b8380eae6b45f884670fc934162f78fda","abstract_canon_sha256":"25886727934d9d421ce5af623934acd0ff28770912b0bbf982f5b981f9383d20"},"schema_version":"1.0"},"canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","source":{"kind":"arxiv","id":"2305.16107","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TV7BUSLEZQW5FKCHECRSS5Z3YJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T14:39:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b8b6ff34d24950cb06dc7bb67b4d8a7b8380eae6b45f884670fc934162f78fda","abstract_canon_sha256":"25886727934d9d421ce5af623934acd0ff28770912b0bbf982f5b981f9383d20"},"schema_version":"1.0"},"canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:59.666557Z","signature_b64":"lRsdbP6eMWkmk60W11oHsnyLxqzZFnKB6T0L+5E7nCYs2WRlK16VzItuD885Q1Lvn5asKOsCOEOvVMFmCnSzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","last_reissued_at":"2026-07-05T06:13:59.666165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:59.666165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16107","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w67/veyNTmwyQ7RDmAA88b3aP1QGsFxBNEod4t23IQ+qrlNQOKnUcs/JE/bwH+MG5szes+INVWRU4mViBVyuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:11:46.998554Z"},"content_sha256":"0f33275dd2b5ec6065d73a570ed72c635a7e1e36b90af1af67293cf4aed8eb2b","schema_version":"1.0","event_id":"sha256:0f33275dd2b5ec6065d73a570ed72c635a7e1e36b90af1af67293cf4aed8eb2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TV7BUSLEZQW5FKCHECRSS5Z3YJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jinyu Li, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yu Wu, Zhuo Chen, Ziqiang Zhang","submitted_at":"2023-05-25T14:39:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16107","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.16107/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QInY6FgNwvVr66RnxViRzhP3agQhx3iXry8ruLtrAsc6s1/myl7alIhitrug/9ZkdtKXAV4LXv0KNXS1NbypCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:11:46.999497Z"},"content_sha256":"55277be335d74146e3c4cbde7551263231d7497e58ac31d8c964eab1103fbdd7","schema_version":"1.0","event_id":"sha256:55277be335d74146e3c4cbde7551263231d7497e58ac31d8c964eab1103fbdd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/bundle.json","state_url":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T17:11:47Z","links":{"resolver":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ","bundle":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/bundle.json","state":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ojWT5RcDUKa9zLfKxS1T7dGsFZSO2Q30ByGLgPdPnZBKrm80WG0TZdQVD6PyfbacIGVd+x3eQNmQF4XBRZZpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:11:47.008647Z","bundle_sha256":"44e57297a9b95c266bdea6abcdba69f77ca1acd39c542c0e57952df44e3a594a"}}