{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BVOE37PUZGGUWEKHFMBSJPOS3E","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":"212d225c21d028cc593f1d7f49a00402c6e67d0663d2905ab7a3a46550b82c74","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:43:42Z","title_canon_sha256":"635686e8fc082649042169c8f2c6bcc2ed8788cc61055be75124e47f0b5a2175"},"schema_version":"1.0","source":{"id":"2211.05756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05756","created_at":"2026-07-05T05:15:07Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05756v1","created_at":"2026-07-05T05:15:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05756","created_at":"2026-07-05T05:15:07Z"},{"alias_kind":"pith_short_12","alias_value":"BVOE37PUZGGU","created_at":"2026-07-05T05:15:07Z"},{"alias_kind":"pith_short_16","alias_value":"BVOE37PUZGGUWEKH","created_at":"2026-07-05T05:15:07Z"},{"alias_kind":"pith_short_8","alias_value":"BVOE37PU","created_at":"2026-07-05T05:15:07Z"}],"graph_snapshots":[{"event_id":"sha256:d818e69cbed8358f6a65a13c4805cb78ff5feea454253554a57fd4246a5c609d","target":"graph","created_at":"2026-07-05T05:15:07Z","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/2211.05756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high-resource to low-resource languages. However, scaling up the number of languages, total hours, and number of unique tokens is not a trivial task. This paper explores large-scale multilingual ASR models on 70 languages. We inspect two architectures: (1) Shared embedding and output and (2) Multiple embedding and output model. In the shared model experiments, we show the importance of tokenization strategy across differ","authors_text":"Abdelrahman Mohamed, Andros Tjandra, David Zhang, Duc Le, Michael L. Seltzer, Nayan Singhal, Ozlem Kalinli","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:43:42Z","title":"Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05756","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:f1c59dfdf89bc39e7ed76d97039c526eccaf65c12052c487d8c48fe119f35d9d","target":"record","created_at":"2026-07-05T05:15:07Z","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":"212d225c21d028cc593f1d7f49a00402c6e67d0663d2905ab7a3a46550b82c74","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T18:43:42Z","title_canon_sha256":"635686e8fc082649042169c8f2c6bcc2ed8788cc61055be75124e47f0b5a2175"},"schema_version":"1.0","source":{"id":"2211.05756","kind":"arxiv","version":1}},"canonical_sha256":"0d5c4dfdf4c98d4b11472b0324bdd2d90ab210c2ccab44b58da62bda4685b99d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d5c4dfdf4c98d4b11472b0324bdd2d90ab210c2ccab44b58da62bda4685b99d","first_computed_at":"2026-07-05T05:15:07.389729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:07.389729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w/xawk4HORSD4wsqHKXPqS3F2nWiLUypYmXdyu5g0h4kBl4nVaa0yrE1Eww0W1BntECRpZXmmY/K7Cv/P44TBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:07.390114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.05756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1c59dfdf89bc39e7ed76d97039c526eccaf65c12052c487d8c48fe119f35d9d","sha256:d818e69cbed8358f6a65a13c4805cb78ff5feea454253554a57fd4246a5c609d"],"state_sha256":"8285a3598394d18e41bd4e1626da41f8ae5ee4e550a1f47f646b24cb2f037b84"}