{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SCYRTUYV2QGBTB646Q4CUR3NKF","short_pith_number":"pith:SCYRTUYV","schema_version":"1.0","canonical_sha256":"90b119d315d40c1987dcf4382a476d5147b12d1828c98c906fc68f2299cdaf38","source":{"kind":"arxiv","id":"2308.11596","version":3},"attestation_state":"computed","paper":{"title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abinesh Ramakrishnan, Alexandre Mourachko, Alice Rakotoarison, Amanda Kallet, Anna Sun, Ann Lee, Bapi Akula, Benjamin Peloquin, Bernie Huang, Bokai Yu, Brian Ellis, Can Balioglu, Carleigh Wood, Changhan Wang, Christopher Klaiber, Christophe Ropers, Cynthia Gao, Daniel Li, Daniel Licht, David Dale, Elahe Kalbassi, Ethan Ye, Francisco Guzm\\'an, Gabriel Mejia Gonzalez, Guillaume Wenzek, Hady Elsahar, Hirofumi Inaguma, Holger Schwenk, Hongyu Gong, Igor Tufanov, Ilia Kulikov, Janice Lam, Jean Maillard, Jeff Wang, John Hoffman, Juan Pino, Justine Kao, Justin Haaheim, Kaushik Ram Sadagopan, Kevin Heffernan, Kevin Tran, Lo\\\"ic Barrault, Maha Elbayad, Mariano Cora Meglioli, Marta R. Costa-juss\\`a, Min-Jae Hwang, Mohamed Ramadan, Naji El Hachem, Ning Dong, Onur Celebi, Paden Tomasello, Paul-Ambroise Duquenne, Peng-Jen Chen, Pengwei Li, Pierre Andrews, Prangthip Hansanti, Ruslan Mavlyutov, Russ Howes, Safiyyah Saleem, Seamless Communication, Skyler Wang, Somya Jain, Sravya Popuri, Tuan Tran, Vish Vogeti, Xutai Ma, Yilin Yang, Yu-An Chung","submitted_at":"2023-08-22T17:44:18Z","abstract_excerpt":"What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200 languages, unified speech-to-speech translation models have yet to achieve similar strides. More specifically, conventional speech-to-speech translation systems rely on cascaded systems that perform translation progressively, putting high-performing unified systems out of reach. To address these gaps, we introduce SeamlessM4T, a single model that supports speech-to-speech tran"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.11596","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-22T17:44:18Z","cross_cats_sorted":[],"title_canon_sha256":"cc7e742c2e3223432f63e81263acb386561b99e714b8eb95eb885f47bf9ef751","abstract_canon_sha256":"e88c71c480635fdc8d5b45a94b560d0b666f43fbe9971094984418005424b3dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:50.225606Z","signature_b64":"ooCSW5Mvtp0muk9rmKgk5giq6M/34Psjd6HzAlbKJyuNJ0il5/gmwzPXfGsjITXFMs+Hexy2+Ss08B9gIGyiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90b119d315d40c1987dcf4382a476d5147b12d1828c98c906fc68f2299cdaf38","last_reissued_at":"2026-07-05T07:04:50.225127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:50.225127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abinesh Ramakrishnan, Alexandre Mourachko, Alice Rakotoarison, Amanda Kallet, Anna Sun, Ann Lee, Bapi Akula, Benjamin Peloquin, Bernie Huang, Bokai Yu, Brian Ellis, Can Balioglu, Carleigh Wood, Changhan Wang, Christopher Klaiber, Christophe Ropers, Cynthia Gao, Daniel Li, Daniel Licht, David Dale, Elahe Kalbassi, Ethan Ye, Francisco Guzm\\'an, Gabriel Mejia Gonzalez, Guillaume Wenzek, Hady Elsahar, Hirofumi Inaguma, Holger Schwenk, Hongyu Gong, Igor Tufanov, Ilia Kulikov, Janice Lam, Jean Maillard, Jeff Wang, John Hoffman, Juan Pino, Justine Kao, Justin Haaheim, Kaushik Ram Sadagopan, Kevin Heffernan, Kevin Tran, Lo\\\"ic Barrault, Maha Elbayad, Mariano Cora Meglioli, Marta R. Costa-juss\\`a, Min-Jae Hwang, Mohamed Ramadan, Naji El Hachem, Ning Dong, Onur Celebi, Paden Tomasello, Paul-Ambroise Duquenne, Peng-Jen Chen, Pengwei Li, Pierre Andrews, Prangthip Hansanti, Ruslan Mavlyutov, Russ Howes, Safiyyah Saleem, Seamless Communication, Skyler Wang, Somya Jain, Sravya Popuri, Tuan Tran, Vish Vogeti, Xutai Ma, Yilin Yang, Yu-An Chung","submitted_at":"2023-08-22T17:44:18Z","abstract_excerpt":"What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200 languages, unified speech-to-speech translation models have yet to achieve similar strides. More specifically, conventional speech-to-speech translation systems rely on cascaded systems that perform translation progressively, putting high-performing unified systems out of reach. To address these gaps, we introduce SeamlessM4T, a single model that supports speech-to-speech tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11596","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/2308.11596/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.11596","created_at":"2026-07-05T07:04:50.225181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11596v3","created_at":"2026-07-05T07:04:50.225181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11596","created_at":"2026-07-05T07:04:50.225181+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCYRTUYV2QGB","created_at":"2026-07-05T07:04:50.225181+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCYRTUYV2QGBTB64","created_at":"2026-07-05T07:04:50.225181+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCYRTUYV","created_at":"2026-07-05T07:04:50.225181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20369","citing_title":"CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01960","citing_title":"NAVER LABS Europe Submission to the Instruction-following 2026 Short Track","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13121","citing_title":"NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10368","citing_title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08748","citing_title":"HydraQE: OSU's Submission for the IWSLT 2026 Speech Translation Metrics Shared Task","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04730","citing_title":"Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04474","citing_title":"Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01108","citing_title":"NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03948","citing_title":"A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03241","citing_title":"Benchmarking Speech-to-Speech Translation Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31173","citing_title":"MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31432","citing_title":"DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":212,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25162","citing_title":"STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28642","citing_title":"Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03526","citing_title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16026","citing_title":"From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03295","citing_title":"How to Evaluate Speech Translation with Source-Aware Neural MT Metrics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02446","citing_title":"Low-Resource Languages Jailbreak GPT-4","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01512","citing_title":"MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16378","citing_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26327","citing_title":"Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual Speaker Verification","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09167","citing_title":"WorldSpeech: A Multilingual Speech Corpus from Around the World","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2401.08281","citing_title":"The Faiss library","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2503.01743","citing_title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF","json":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF.json","graph_json":"https://pith.science/api/pith-number/SCYRTUYV2QGBTB646Q4CUR3NKF/graph.json","events_json":"https://pith.science/api/pith-number/SCYRTUYV2QGBTB646Q4CUR3NKF/events.json","paper":"https://pith.science/paper/SCYRTUYV"},"agent_actions":{"view_html":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF","download_json":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF.json","view_paper":"https://pith.science/paper/SCYRTUYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11596&json=true","fetch_graph":"https://pith.science/api/pith-number/SCYRTUYV2QGBTB646Q4CUR3NKF/graph.json","fetch_events":"https://pith.science/api/pith-number/SCYRTUYV2QGBTB646Q4CUR3NKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF/action/storage_attestation","attest_author":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF/action/author_attestation","sign_citation":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF/action/citation_signature","submit_replication":"https://pith.science/pith/SCYRTUYV2QGBTB646Q4CUR3NKF/action/replication_record"}},"created_at":"2026-07-05T07:04:50.225181+00:00","updated_at":"2026-07-05T07:04:50.225181+00:00"}