{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SL734Q6WCALDBECNEQAJH643AR","short_pith_number":"pith:SL734Q6W","canonical_record":{"source":{"id":"2306.15687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-23T16:23:24Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"9fbdc376a5052b83ece86e2c0d0ae55b9cf1c03e0e800496d16cf592225d716f","abstract_canon_sha256":"9ccf4f86243432bd6949d5d3fd162ce993ab1357b494b1a6ef7ca4f3271b018e"},"schema_version":"1.0"},"canonical_sha256":"92ffbe43d6101630904d240093fb9b0479da72d85f55c98e18defdca99651cfb","source":{"kind":"arxiv","id":"2306.15687","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15687","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15687v2","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15687","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"SL734Q6WCALD","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"SL734Q6WCALDBECN","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"SL734Q6W","created_at":"2026-07-05T07:02:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SL734Q6WCALDBECNEQAJH643AR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.15687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-23T16:23:24Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"9fbdc376a5052b83ece86e2c0d0ae55b9cf1c03e0e800496d16cf592225d716f","abstract_canon_sha256":"9ccf4f86243432bd6949d5d3fd162ce993ab1357b494b1a6ef7ca4f3271b018e"},"schema_version":"1.0"},"canonical_sha256":"92ffbe43d6101630904d240093fb9b0479da72d85f55c98e18defdca99651cfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:30.847182Z","signature_b64":"hDkP4XzlUKqVi+/YsEBGtAfq16HBf3Xppjvr8qiBX4LotqwnDzZpkWl71Xj/iZOJJUCkdD8kBrsHh9F7mu4+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92ffbe43d6101630904d240093fb9b0479da72d85f55c98e18defdca99651cfb","last_reissued_at":"2026-07-05T07:02:30.846680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:30.846680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.15687","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWlJrN9DkqB09k/gBAI/kV/YAR8u68ESHKyxuUVB5FQO3tfy6Fln7DWbI8jKM+uacEuUd+VkEJrLF4YtBYgRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:52:16.680234Z"},"content_sha256":"a9814d65e569f953b959ac479241b193ffaaeee353facab874b7f812296d4f3d","schema_version":"1.0","event_id":"sha256:a9814d65e569f953b959ac479241b193ffaaeee353facab874b7f812296d4f3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SL734Q6WCALDBECNEQAJH643AR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Apoorv Vyas, Bowen Shi, Brian Karrer, Jay Mahadeokar, Leda Sari, Mary Williamson, Matthew Le, Rashel Moritz, Vimal Manohar, Wei-Ning Hsu, Yossi Adi","submitted_at":"2023-06-23T16:23:24Z","abstract_excerpt":"Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15687","kind":"arxiv","version":2},"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/2306.15687/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":"2026-07-05T07:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vffy8WHXx1axyolmk85ASWeWLdxOCEhyKKL1h+PnCkOgrUsj8R2b6NAjEF624gQlnH32ZJbUZ9kMu5+QmafyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:52:16.680980Z"},"content_sha256":"c75b22808b018be3e31c4c69fdc2f9c31acb903c31279d811d262388249e7267","schema_version":"1.0","event_id":"sha256:c75b22808b018be3e31c4c69fdc2f9c31acb903c31279d811d262388249e7267"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SL734Q6WCALDBECNEQAJH643AR/bundle.json","state_url":"https://pith.science/pith/SL734Q6WCALDBECNEQAJH643AR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SL734Q6WCALDBECNEQAJH643AR/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":"2026-08-06T21:52:16Z","links":{"resolver":"https://pith.science/pith/SL734Q6WCALDBECNEQAJH643AR","bundle":"https://pith.science/pith/SL734Q6WCALDBECNEQAJH643AR/bundle.json","state":"https://pith.science/pith/SL734Q6WCALDBECNEQAJH643AR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SL734Q6WCALDBECNEQAJH643AR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SL734Q6WCALDBECNEQAJH643AR","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":"9ccf4f86243432bd6949d5d3fd162ce993ab1357b494b1a6ef7ca4f3271b018e","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-23T16:23:24Z","title_canon_sha256":"9fbdc376a5052b83ece86e2c0d0ae55b9cf1c03e0e800496d16cf592225d716f"},"schema_version":"1.0","source":{"id":"2306.15687","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15687","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15687v2","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15687","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"SL734Q6WCALD","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"SL734Q6WCALDBECN","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"SL734Q6W","created_at":"2026-07-05T07:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:c75b22808b018be3e31c4c69fdc2f9c31acb903c31279d811d262388249e7267","target":"graph","created_at":"2026-07-05T07:02:30Z","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/2306.15687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enh","authors_text":"Apoorv Vyas, Bowen Shi, Brian Karrer, Jay Mahadeokar, Leda Sari, Mary Williamson, Matthew Le, Rashel Moritz, Vimal Manohar, Wei-Ning Hsu, Yossi Adi","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-23T16:23:24Z","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15687","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:a9814d65e569f953b959ac479241b193ffaaeee353facab874b7f812296d4f3d","target":"record","created_at":"2026-07-05T07:02:30Z","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":"9ccf4f86243432bd6949d5d3fd162ce993ab1357b494b1a6ef7ca4f3271b018e","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-23T16:23:24Z","title_canon_sha256":"9fbdc376a5052b83ece86e2c0d0ae55b9cf1c03e0e800496d16cf592225d716f"},"schema_version":"1.0","source":{"id":"2306.15687","kind":"arxiv","version":2}},"canonical_sha256":"92ffbe43d6101630904d240093fb9b0479da72d85f55c98e18defdca99651cfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92ffbe43d6101630904d240093fb9b0479da72d85f55c98e18defdca99651cfb","first_computed_at":"2026-07-05T07:02:30.846680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:30.846680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hDkP4XzlUKqVi+/YsEBGtAfq16HBf3Xppjvr8qiBX4LotqwnDzZpkWl71Xj/iZOJJUCkdD8kBrsHh9F7mu4+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:30.847182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15687","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9814d65e569f953b959ac479241b193ffaaeee353facab874b7f812296d4f3d","sha256:c75b22808b018be3e31c4c69fdc2f9c31acb903c31279d811d262388249e7267"],"state_sha256":"16659569a01a764e695aaaba427c6fcd32c70f1b82b7c30eebab6588fbb6cada"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l7hgF/LkXYGxyBcxvMuaZBAFamuBbONSKvil9ERw03WkRk2giyvdSlWJgWVymnqAmA6TYFBIjFrIt4gOlfh2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:52:16.690135Z","bundle_sha256":"5a22005c0ed946897910e6da645b12888e76ba2a59f977cf5fee102f716160b1"}}