{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6D4SSQS4PYNPSW2RGXZGXIZDN2","short_pith_number":"pith:6D4SSQS4","canonical_record":{"source":{"id":"2309.07937","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T03:13:18Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"362468170faae8522be66f23b05d73aa23a262dfb4260fceaacdf67a253f80e2","abstract_canon_sha256":"46ba639f4500dc2d7fa215acc361b8dc68897ce8cbca4d23be47b25dd243c47c"},"schema_version":"1.0"},"canonical_sha256":"f0f929425c7e1af95b5135f26ba3236e8056dbf29683bd34223e6f19ee7b5f26","source":{"kind":"arxiv","id":"2309.07937","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07937","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07937v3","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07937","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"6D4SSQS4PYNP","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"6D4SSQS4PYNPSW2R","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"6D4SSQS4","created_at":"2026-07-05T07:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6D4SSQS4PYNPSW2RGXZGXIZDN2","target":"record","payload":{"canonical_record":{"source":{"id":"2309.07937","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T03:13:18Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"362468170faae8522be66f23b05d73aa23a262dfb4260fceaacdf67a253f80e2","abstract_canon_sha256":"46ba639f4500dc2d7fa215acc361b8dc68897ce8cbca4d23be47b25dd243c47c"},"schema_version":"1.0"},"canonical_sha256":"f0f929425c7e1af95b5135f26ba3236e8056dbf29683bd34223e6f19ee7b5f26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:54.326390Z","signature_b64":"IoahrSFqpDqxjanu07e2V27wR5dWQb1NFMIpdGmptq68ahgahykGbV4X+4d/Maz6Vq0B7BMmoB8X7kEa7mjNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f929425c7e1af95b5135f26ba3236e8056dbf29683bd34223e6f19ee7b5f26","last_reissued_at":"2026-07-05T07:36:54.325869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:54.325869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.07937","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ro2dQmbLP/bgyrar49tlT7YiRjjx0Cn3HxM9X3iTpSGwot3l7Qpn/ymmmAZAtm+cjjSFUSEqOyOhxaaL9/sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:32:33.182575Z"},"content_sha256":"094983050fde1d9aeeba284beaf990c30b25bfd8c97f48973ff423b46b63edf4","schema_version":"1.0","event_id":"sha256:094983050fde1d9aeeba284beaf990c30b25bfd8c97f48973ff423b46b63edf4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6D4SSQS4PYNPSW2RGXZGXIZDN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jee-weon Jung, Shinji Watanabe, Shukjae Choi, Soumi Maiti, Xuankai Chang, Yifan Peng","submitted_at":"2023-09-14T03:13:18Z","abstract_excerpt":"We propose a decoder-only language model, VoxtLM, that can perform four tasks: speech recognition, speech synthesis, text generation, and speech continuation. VoxtLM integrates text vocabulary with discrete speech tokens from self-supervised speech features and uses special tokens to enable multitask learning. Compared to a single-task model, VoxtLM exhibits a significant improvement in speech synthesis, with improvements in both speech intelligibility from 28.9 to 5.6 and objective quality from 2.68 to 3.90. VoxtLM also improves speech generation and speech recognition performance over the si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07937","kind":"arxiv","version":3},"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/2309.07937/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":"2026-07-05T07:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hV/5NBVvcDRACEW8V7pblGJVQQ+Jig6IAhA13xtochIvaqQnN4pdLUegirUwXdcfr4V8SrZ19a1tYEbhoImaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:32:33.182961Z"},"content_sha256":"be78905412ab5c69c4be199a338a09261549c23afff049ed0df0981ab20b01a1","schema_version":"1.0","event_id":"sha256:be78905412ab5c69c4be199a338a09261549c23afff049ed0df0981ab20b01a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2/bundle.json","state_url":"https://pith.science/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2/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":"2026-07-15T21:32:33Z","links":{"resolver":"https://pith.science/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2","bundle":"https://pith.science/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2/bundle.json","state":"https://pith.science/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6D4SSQS4PYNPSW2RGXZGXIZDN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6D4SSQS4PYNPSW2RGXZGXIZDN2","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":"46ba639f4500dc2d7fa215acc361b8dc68897ce8cbca4d23be47b25dd243c47c","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T03:13:18Z","title_canon_sha256":"362468170faae8522be66f23b05d73aa23a262dfb4260fceaacdf67a253f80e2"},"schema_version":"1.0","source":{"id":"2309.07937","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07937","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07937v3","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07937","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"6D4SSQS4PYNP","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"6D4SSQS4PYNPSW2R","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"6D4SSQS4","created_at":"2026-07-05T07:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:be78905412ab5c69c4be199a338a09261549c23afff049ed0df0981ab20b01a1","target":"graph","created_at":"2026-07-05T07:36:54Z","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/2309.07937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a decoder-only language model, VoxtLM, that can perform four tasks: speech recognition, speech synthesis, text generation, and speech continuation. VoxtLM integrates text vocabulary with discrete speech tokens from self-supervised speech features and uses special tokens to enable multitask learning. Compared to a single-task model, VoxtLM exhibits a significant improvement in speech synthesis, with improvements in both speech intelligibility from 28.9 to 5.6 and objective quality from 2.68 to 3.90. VoxtLM also improves speech generation and speech recognition performance over the si","authors_text":"Jee-weon Jung, Shinji Watanabe, Shukjae Choi, Soumi Maiti, Xuankai Chang, Yifan Peng","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T03:13:18Z","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07937","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":"sha256:094983050fde1d9aeeba284beaf990c30b25bfd8c97f48973ff423b46b63edf4","target":"record","created_at":"2026-07-05T07:36:54Z","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":"46ba639f4500dc2d7fa215acc361b8dc68897ce8cbca4d23be47b25dd243c47c","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T03:13:18Z","title_canon_sha256":"362468170faae8522be66f23b05d73aa23a262dfb4260fceaacdf67a253f80e2"},"schema_version":"1.0","source":{"id":"2309.07937","kind":"arxiv","version":3}},"canonical_sha256":"f0f929425c7e1af95b5135f26ba3236e8056dbf29683bd34223e6f19ee7b5f26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0f929425c7e1af95b5135f26ba3236e8056dbf29683bd34223e6f19ee7b5f26","first_computed_at":"2026-07-05T07:36:54.325869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:54.325869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IoahrSFqpDqxjanu07e2V27wR5dWQb1NFMIpdGmptq68ahgahykGbV4X+4d/Maz6Vq0B7BMmoB8X7kEa7mjNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:54.326390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07937","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:094983050fde1d9aeeba284beaf990c30b25bfd8c97f48973ff423b46b63edf4","sha256:be78905412ab5c69c4be199a338a09261549c23afff049ed0df0981ab20b01a1"],"state_sha256":"ebc619a8324431e86c885b78651c118a81579f83f36d042b7013ad91717235e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3BjeN0qEDjC88QgJKJoquqqpnwkj0C3wjeaVPYqjJELY3R+pSYwFyFx8nI/LnwDhhUioophN4PNX+owucTNJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T21:32:33.185494Z","bundle_sha256":"3d6274a092472bc5c827050d6cfd9d48ca536e2f2e9b4d786aff84ab7b126c7b"}}