{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TPTUAULFSPBJ456OP2YON6W5HC","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":"aa14d730f17e0b066197b87b726ab54d1ad8fe6456be703913248ce79be9d20e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-08T19:37:06Z","title_canon_sha256":"e7275da1cd759832b6ec4daf9e31fbdc6998931cb373849056706fe46a598921"},"schema_version":"1.0","source":{"id":"2107.04082","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.04082","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2107.04082v4","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04082","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"TPTUAULFSPBJ","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"TPTUAULFSPBJ456O","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"TPTUAULF","created_at":"2026-07-05T03:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:418fcfde99f5c1edbbab7d89c5edc1098a860d6121e6e1d50609fe2075067f89","target":"graph","created_at":"2026-07-05T03:23:12Z","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/2107.04082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech tasks. We extend previous self-supervised work on language identification by experimenting with pre-trained models which were learned on real-world unconstrained speech in multiple languages and not just on English. We show that models pre-trained on many languages perform better and enable language identification systems that require very little labeled da","authors_text":"Alexei Baevski, Alexis Conneau, Andros Tjandra, Assaf Sela, Diptanu Gon Choudhury, Frank Zhang, Kritika Singh, Michael Auli, Yatharth Saraf","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-08T19:37:06Z","title":"Improved Language Identification Through Cross-Lingual Self-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04082","kind":"arxiv","version":4},"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":"sha256:0235f04244ab5078c0e46ac3b3d3c2459bbe712e1b91f4a29dd06e531727201a","target":"record","created_at":"2026-07-05T03:23:12Z","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":"aa14d730f17e0b066197b87b726ab54d1ad8fe6456be703913248ce79be9d20e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-08T19:37:06Z","title_canon_sha256":"e7275da1cd759832b6ec4daf9e31fbdc6998931cb373849056706fe46a598921"},"schema_version":"1.0","source":{"id":"2107.04082","kind":"arxiv","version":4}},"canonical_sha256":"9be740516593c29e77ce7eb0e6fadd38b22d9fe70d58b5438979bf2ec62f3bc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9be740516593c29e77ce7eb0e6fadd38b22d9fe70d58b5438979bf2ec62f3bc3","first_computed_at":"2026-07-05T03:23:12.472786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:12.472786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F1R8ovfyuxak46xBQzwaRZzwKWNyoPcIfD+HAODp/f6Z3ctIWvCHuVT4sA7YyiuGcJlWQTDeRLcwv5W/PF6XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:12.473217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.04082","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0235f04244ab5078c0e46ac3b3d3c2459bbe712e1b91f4a29dd06e531727201a","sha256:418fcfde99f5c1edbbab7d89c5edc1098a860d6121e6e1d50609fe2075067f89"],"state_sha256":"1c5b9ff6f3d78d41eda6f83127c21d8ca028c91bbc373a9a3d0fe037253d3c4c"}