{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GYDIN6CXWEQLXLJZHL5CPIGOUP","short_pith_number":"pith:GYDIN6CX","canonical_record":{"source":{"id":"2303.01037","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-02T07:47:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2c318928f3d6c22a165a7fb1de2328f26102d0a4f22269d820a40c04b3b356bd","abstract_canon_sha256":"360e7295947da225857932d57e9287d80d998a3bf15e4e80e012cc1a00ccd548"},"schema_version":"1.0"},"canonical_sha256":"360686f857b120bbad393afa27a0cea3d32f7dcbcaf268b236dcd5664162a08f","source":{"kind":"arxiv","id":"2303.01037","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01037","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01037v3","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01037","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"pith_short_12","alias_value":"GYDIN6CXWEQL","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"pith_short_16","alias_value":"GYDIN6CXWEQLXLJZ","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"pith_short_8","alias_value":"GYDIN6CX","created_at":"2026-07-05T06:53:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GYDIN6CXWEQLXLJZHL5CPIGOUP","target":"record","payload":{"canonical_record":{"source":{"id":"2303.01037","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-02T07:47:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2c318928f3d6c22a165a7fb1de2328f26102d0a4f22269d820a40c04b3b356bd","abstract_canon_sha256":"360e7295947da225857932d57e9287d80d998a3bf15e4e80e012cc1a00ccd548"},"schema_version":"1.0"},"canonical_sha256":"360686f857b120bbad393afa27a0cea3d32f7dcbcaf268b236dcd5664162a08f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:35.141659Z","signature_b64":"t7pFAhU1maIeg/IrWYYDgFMTMaWdZfdLtnK7D/y/uarhCjNmMzxmzzAAZG2+BuRUSVkiBIpabqj+HOAolxS6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360686f857b120bbad393afa27a0cea3d32f7dcbcaf268b236dcd5664162a08f","last_reissued_at":"2026-07-05T06:53:35.141093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:35.141093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.01037","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":"2026-07-05T06:53:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4s+InPGszG+zAn3NE5mE0yPEfhcSgnyX67KKVDMqcIYzrr09Tf+aCErhfyllj7H7WzZW+Uyh1ay+IUPGtUO1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:36:55.746915Z"},"content_sha256":"dbf19ed45411ebc93099eadcd746b76cb7ad76e2d9dc0cbd5769225859cc9314","schema_version":"1.0","event_id":"sha256:dbf19ed45411ebc93099eadcd746b76cb7ad76e2d9dc0cbd5769225859cc9314"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GYDIN6CXWEQLXLJZHL5CPIGOUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran, Bo Li, Chung-Cheng Chiu, Daniel S. Park, Fran\\c{c}oise Beaufays, Gary Wang, Ginger Perng, Hagen Soltau, James Qin, Jason Riesa, Johan Schalkwyk, Ke Hu, Nanxin Chen, Parisa Haghani, Pedro Moreno, Rohit Prabhavalkar, Tara Sainath, Trevor Strohman, Vera Axelrod, Wei Han, Yonghui Wu, Yongqiang Wang, Yu Zhang, Zhehuai Chen, Zhong Meng","submitted_at":"2023-03-02T07:47:18Z","abstract_excerpt":"We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the encoder of the model on a large unlabeled multilingual dataset of 12 million (M) hours spanning over 300 languages, and fine-tuning on a smaller labeled dataset. We use multilingual pre-training with random-projection quantization and speech-text modality matching to achieve state-of-the-art performance on downstream multilingual ASR and speech-to-text translation tasks. We also demonstrate that despite using a labeled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01037","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/2303.01037/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":"2026-07-05T06:53:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"chr053NApKQB726AGoC8puTKJh9EWd5pWMGHb8crEbY5hn6J3IOSVDWiNSJ7/vMRZ0rjkW0zqa7Zxr0u8PrTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:36:55.747859Z"},"content_sha256":"17767ec73ce1e45135294824b60e03a226044ad1a3a7a25ee567a3c1be2c4280","schema_version":"1.0","event_id":"sha256:17767ec73ce1e45135294824b60e03a226044ad1a3a7a25ee567a3c1be2c4280"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP/bundle.json","state_url":"https://pith.science/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP/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":"2026-08-03T16:36:55Z","links":{"resolver":"https://pith.science/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP","bundle":"https://pith.science/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP/bundle.json","state":"https://pith.science/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYDIN6CXWEQLXLJZHL5CPIGOUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GYDIN6CXWEQLXLJZHL5CPIGOUP","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":"360e7295947da225857932d57e9287d80d998a3bf15e4e80e012cc1a00ccd548","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-02T07:47:18Z","title_canon_sha256":"2c318928f3d6c22a165a7fb1de2328f26102d0a4f22269d820a40c04b3b356bd"},"schema_version":"1.0","source":{"id":"2303.01037","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01037","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01037v3","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01037","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"pith_short_12","alias_value":"GYDIN6CXWEQL","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"pith_short_16","alias_value":"GYDIN6CXWEQLXLJZ","created_at":"2026-07-05T06:53:35Z"},{"alias_kind":"pith_short_8","alias_value":"GYDIN6CX","created_at":"2026-07-05T06:53:35Z"}],"graph_snapshots":[{"event_id":"sha256:17767ec73ce1e45135294824b60e03a226044ad1a3a7a25ee567a3c1be2c4280","target":"graph","created_at":"2026-07-05T06:53:35Z","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/2303.01037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the encoder of the model on a large unlabeled multilingual dataset of 12 million (M) hours spanning over 300 languages, and fine-tuning on a smaller labeled dataset. We use multilingual pre-training with random-projection quantization and speech-text modality matching to achieve state-of-the-art performance on downstream multilingual ASR and speech-to-text translation tasks. We also demonstrate that despite using a labeled ","authors_text":"Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran, Bo Li, Chung-Cheng Chiu, Daniel S. Park, Fran\\c{c}oise Beaufays, Gary Wang, Ginger Perng, Hagen Soltau, James Qin, Jason Riesa, Johan Schalkwyk, Ke Hu, Nanxin Chen, Parisa Haghani, Pedro Moreno, Rohit Prabhavalkar, Tara Sainath, Trevor Strohman, Vera Axelrod, Wei Han, Yonghui Wu, Yongqiang Wang, Yu Zhang, Zhehuai Chen, Zhong Meng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-02T07:47:18Z","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01037","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:dbf19ed45411ebc93099eadcd746b76cb7ad76e2d9dc0cbd5769225859cc9314","target":"record","created_at":"2026-07-05T06:53:35Z","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":"360e7295947da225857932d57e9287d80d998a3bf15e4e80e012cc1a00ccd548","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-02T07:47:18Z","title_canon_sha256":"2c318928f3d6c22a165a7fb1de2328f26102d0a4f22269d820a40c04b3b356bd"},"schema_version":"1.0","source":{"id":"2303.01037","kind":"arxiv","version":3}},"canonical_sha256":"360686f857b120bbad393afa27a0cea3d32f7dcbcaf268b236dcd5664162a08f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"360686f857b120bbad393afa27a0cea3d32f7dcbcaf268b236dcd5664162a08f","first_computed_at":"2026-07-05T06:53:35.141093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:35.141093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t7pFAhU1maIeg/IrWYYDgFMTMaWdZfdLtnK7D/y/uarhCjNmMzxmzzAAZG2+BuRUSVkiBIpabqj+HOAolxS6Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:35.141659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.01037","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbf19ed45411ebc93099eadcd746b76cb7ad76e2d9dc0cbd5769225859cc9314","sha256:17767ec73ce1e45135294824b60e03a226044ad1a3a7a25ee567a3c1be2c4280"],"state_sha256":"d122a973dd35b0cfa6ce0617132d6ebc9f6ba809caf56e363ed0c1f932505b5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H8KjXCL1IWM5jnqTePUye0ft1fxzm4vBQKJqFZKY0Kc6ZswNqTSPTbjl5MLVHEXbUr3QEA3ThiG0YDo1lMrRAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:36:55.753066Z","bundle_sha256":"9f23c01e26bc4d3d19a7a9f07ae86d6e05af2e727436412fbc4e7a066f0d9989"}}