{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DXZLYYXTQKLF7BUVJVMSMDIUCW","short_pith_number":"pith:DXZLYYXT","canonical_record":{"source":{"id":"2312.05187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T17:18:42Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"129bdd978a901c91c86088fe558cd4cb87c61e21b03293de78e47c58daaf5a8c","abstract_canon_sha256":"389f2634d5e586c51faeacc10f184ad6688b7a4b7a31fbef13f2448e8e4c7d81"},"schema_version":"1.0"},"canonical_sha256":"1df2bc62f382965f86954d59260d14159633a1d88820872e2567bf436c813e1b","source":{"kind":"arxiv","id":"2312.05187","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05187","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05187v1","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05187","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"DXZLYYXTQKLF","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"DXZLYYXTQKLF7BUV","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"DXZLYYXT","created_at":"2026-07-05T07:21:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DXZLYYXTQKLF7BUVJVMSMDIUCW","target":"record","payload":{"canonical_record":{"source":{"id":"2312.05187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T17:18:42Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"129bdd978a901c91c86088fe558cd4cb87c61e21b03293de78e47c58daaf5a8c","abstract_canon_sha256":"389f2634d5e586c51faeacc10f184ad6688b7a4b7a31fbef13f2448e8e4c7d81"},"schema_version":"1.0"},"canonical_sha256":"1df2bc62f382965f86954d59260d14159633a1d88820872e2567bf436c813e1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:58.253538Z","signature_b64":"vI/IKL6Z5q16BrQddvvVJFOeVKymYHMxKYUfVThdxn3KhuCy8X2FaquKZq/hNygKh2wwyU4sXFW7QEf/MygXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1df2bc62f382965f86954d59260d14159633a1d88820872e2567bf436c813e1b","last_reissued_at":"2026-07-05T07:21:58.253145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:58.253145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.05187","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":"2026-07-05T07:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"laKp3qY6VrgP8fnRg5VO45lyu0OYj6kmXYWO/PMlwu6bQVOcQrZhxjmracba1OTA8YyycbDd25LPpZTZZ750DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:37:48.553574Z"},"content_sha256":"5eae0dddd3d5034b9a1a34956a442cadcdf4a5d521f156b67a7da8d0d24f40a3","schema_version":"1.0","event_id":"sha256:5eae0dddd3d5034b9a1a34956a442cadcdf4a5d521f156b67a7da8d0d24f40a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DXZLYYXTQKLF7BUVJVMSMDIUCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seamless: Multilingual Expressive and Streaming Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abinesh Ramakrishnan, Alex Mourachko, Alice Rakotoarison, Amanda Kallet, Anna Sun, Ann Lee, Artyom Kozhevnikov, Benjamin Peloquin, Bokai Yu, Brian Ellis, Can Balioglu, Carleigh Wood, Changhan Wang, Christopher Klaiber, Christophe Ropers, Christophe Touret, Corinne Wong, Cynthia Gao, Daniel Licht, David Dale, Elahe Kalbassi, Ethan Ye, Francisco Guzm\\'an, Gabriel Mejia Gonzalez, Guillaume Wenzek, Hady Elsahar, Hirofumi Inaguma, Holger Schwenk, Hongyu Gong, Ilia Kulikov, Ivan Evtimov, Jean Maillard, Jeff Wang, John Hoffman, Juan Pino, Justine Kao, Justin Haaheim, Kaushik Ram Sadagopan, Kevin Heffernan, Lo\\\"ic Barrault, Maha Elbayad, Mariano Coria Meglioli, Mark Duppenthaler, Marta R. Costa-juss\\`a, Mary Williamson, Min-Jae Hwang, Ning Dong, Paden Tomasello, Paul-Ambroise Duquenne, Peng-Jen Chen, Pengwei Li, Pierre Andrews, Pierre Fernandez, Prangthip Hansanti, Robin San Roman, Ruslan Mavlyutov, Safiyyah Saleem, Seamless Communication, Skyler Wang, Somya Jain, Sravya Popuri, Tuan Tran, Xutai Ma, Yilin Yang, Yu-An Chung","submitted_at":"2023-12-08T17:18:42Z","abstract_excerpt":"Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion. First, we contribute an improved version of the massively multilingual and multimodal SeamlessM4T model-SeamlessM4T v2. This newer model, incorporating an updated UnitY2 framework, was trained on more low-resource language data. SeamlessM4T v2 provides the foundation on which our next two models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05187","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/2312.05187/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":"2026-07-05T07:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9xnIgl9ys21LOz2dmJ/X48GOHAcsjoVTg2SDXsh2Vn2anLUfRphtCdUk8gaOmPq0NZWTlay0Ace1gifAkDXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:37:48.553969Z"},"content_sha256":"331a19fa018c622429ef9fae008a1f3064ea2c19fb738b02b2e42cb6b4950cca","schema_version":"1.0","event_id":"sha256:331a19fa018c622429ef9fae008a1f3064ea2c19fb738b02b2e42cb6b4950cca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW/bundle.json","state_url":"https://pith.science/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW/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":"2026-08-06T18:37:48Z","links":{"resolver":"https://pith.science/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW","bundle":"https://pith.science/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW/bundle.json","state":"https://pith.science/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXZLYYXTQKLF7BUVJVMSMDIUCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DXZLYYXTQKLF7BUVJVMSMDIUCW","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":"389f2634d5e586c51faeacc10f184ad6688b7a4b7a31fbef13f2448e8e4c7d81","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T17:18:42Z","title_canon_sha256":"129bdd978a901c91c86088fe558cd4cb87c61e21b03293de78e47c58daaf5a8c"},"schema_version":"1.0","source":{"id":"2312.05187","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05187","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05187v1","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05187","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"DXZLYYXTQKLF","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"DXZLYYXTQKLF7BUV","created_at":"2026-07-05T07:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"DXZLYYXT","created_at":"2026-07-05T07:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:331a19fa018c622429ef9fae008a1f3064ea2c19fb738b02b2e42cb6b4950cca","target":"graph","created_at":"2026-07-05T07:21:58Z","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/2312.05187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion. First, we contribute an improved version of the massively multilingual and multimodal SeamlessM4T model-SeamlessM4T v2. This newer model, incorporating an updated UnitY2 framework, was trained on more low-resource language data. SeamlessM4T v2 provides the foundation on which our next two models","authors_text":"Abinesh Ramakrishnan, Alex Mourachko, Alice Rakotoarison, Amanda Kallet, Anna Sun, Ann Lee, Artyom Kozhevnikov, Benjamin Peloquin, Bokai Yu, Brian Ellis, Can Balioglu, Carleigh Wood, Changhan Wang, Christopher Klaiber, Christophe Ropers, Christophe Touret, Corinne Wong, Cynthia Gao, Daniel Licht, David Dale, Elahe Kalbassi, Ethan Ye, Francisco Guzm\\'an, Gabriel Mejia Gonzalez, Guillaume Wenzek, Hady Elsahar, Hirofumi Inaguma, Holger Schwenk, Hongyu Gong, Ilia Kulikov, Ivan Evtimov, Jean Maillard, Jeff Wang, John Hoffman, Juan Pino, Justine Kao, Justin Haaheim, Kaushik Ram Sadagopan, Kevin Heffernan, Lo\\\"ic Barrault, Maha Elbayad, Mariano Coria Meglioli, Mark Duppenthaler, Marta R. Costa-juss\\`a, Mary Williamson, Min-Jae Hwang, Ning Dong, Paden Tomasello, Paul-Ambroise Duquenne, Peng-Jen Chen, Pengwei Li, Pierre Andrews, Pierre Fernandez, Prangthip Hansanti, Robin San Roman, Ruslan Mavlyutov, Safiyyah Saleem, Seamless Communication, Skyler Wang, Somya Jain, Sravya Popuri, Tuan Tran, Xutai Ma, Yilin Yang, Yu-An Chung","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T17:18:42Z","title":"Seamless: Multilingual Expressive and Streaming Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05187","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":"sha256:5eae0dddd3d5034b9a1a34956a442cadcdf4a5d521f156b67a7da8d0d24f40a3","target":"record","created_at":"2026-07-05T07:21:58Z","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":"389f2634d5e586c51faeacc10f184ad6688b7a4b7a31fbef13f2448e8e4c7d81","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T17:18:42Z","title_canon_sha256":"129bdd978a901c91c86088fe558cd4cb87c61e21b03293de78e47c58daaf5a8c"},"schema_version":"1.0","source":{"id":"2312.05187","kind":"arxiv","version":1}},"canonical_sha256":"1df2bc62f382965f86954d59260d14159633a1d88820872e2567bf436c813e1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1df2bc62f382965f86954d59260d14159633a1d88820872e2567bf436c813e1b","first_computed_at":"2026-07-05T07:21:58.253145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:58.253145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vI/IKL6Z5q16BrQddvvVJFOeVKymYHMxKYUfVThdxn3KhuCy8X2FaquKZq/hNygKh2wwyU4sXFW7QEf/MygXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:58.253538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05187","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5eae0dddd3d5034b9a1a34956a442cadcdf4a5d521f156b67a7da8d0d24f40a3","sha256:331a19fa018c622429ef9fae008a1f3064ea2c19fb738b02b2e42cb6b4950cca"],"state_sha256":"f9a894d39c70b5ce671f74589fc36e51c9be892806f7dfb9d520fe0f96024aa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2UAOz2s+oLD9HbB3Kq9WTCYw8D/agaxuGFtkNRaBEAFmm9NZA8z66wh6spIf0QB1fNCw2fACcF6c3VS06/4eAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:37:48.557006Z","bundle_sha256":"9a630aa61d5a82f2fe49be87e5b781b86a68e85e141abb5cc01d2de38be822e5"}}