{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DYZIS3MHKY57ZYBCBHETM6ZSRJ","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":"a9a95f29cd8a9acf23dd66fef7faaffa7405acd3744e24b3982c4307f28e6c99","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-17T18:49:42Z","title_canon_sha256":"bc6eb1af2f3ac5cf95c6964b5b50e9758ca48a29d124b3adf978b309b44360a9"},"schema_version":"1.0","source":{"id":"2111.09296","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09296","created_at":"2026-07-05T03:41:27Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09296v3","created_at":"2026-07-05T03:41:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09296","created_at":"2026-07-05T03:41:27Z"},{"alias_kind":"pith_short_12","alias_value":"DYZIS3MHKY57","created_at":"2026-07-05T03:41:27Z"},{"alias_kind":"pith_short_16","alias_value":"DYZIS3MHKY57ZYBC","created_at":"2026-07-05T03:41:27Z"},{"alias_kind":"pith_short_8","alias_value":"DYZIS3MH","created_at":"2026-07-05T03:41:27Z"}],"graph_snapshots":[{"event_id":"sha256:335dad92bc6275fe13e0b6ecd707543c6f9c05661d350b73ca09d85eba0cc352","target":"graph","created_at":"2026-07-05T03:41:27Z","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/2111.09296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech reco","authors_text":"Alexei Baevski, Alexis Conneau, Andros Tjandra, Arun Babu, Changhan Wang, Juan Pino, Kritika Singh, Kushal Lakhotia, Michael Auli, Naman Goyal, Patrick von Platen, Qiantong Xu, Yatharth Saraf","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-17T18:49:42Z","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09296","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":"sha256:82d45a942afa7ab8198578c8722db7e988be992479dfb0eeac591f35975aa543","target":"record","created_at":"2026-07-05T03:41:27Z","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":"a9a95f29cd8a9acf23dd66fef7faaffa7405acd3744e24b3982c4307f28e6c99","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-17T18:49:42Z","title_canon_sha256":"bc6eb1af2f3ac5cf95c6964b5b50e9758ca48a29d124b3adf978b309b44360a9"},"schema_version":"1.0","source":{"id":"2111.09296","kind":"arxiv","version":3}},"canonical_sha256":"1e32896d87563bfce02209c9367b328a519528e3233d1d2162a5d462e12540f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e32896d87563bfce02209c9367b328a519528e3233d1d2162a5d462e12540f1","first_computed_at":"2026-07-05T03:41:27.872433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:27.872433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NBDzUrmbToa6PfqpO0WnHXaSk07YEnImNC3EfR7npRXKJR1oW8Z5AwGAuzAn+q3YKOSffKEyfPTb2V+RWXXXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:27.872828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09296","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82d45a942afa7ab8198578c8722db7e988be992479dfb0eeac591f35975aa543","sha256:335dad92bc6275fe13e0b6ecd707543c6f9c05661d350b73ca09d85eba0cc352"],"state_sha256":"9468486e603c88b7d945884b5f969d6c15319d998ca9e8feac1c5591b76f1916"}