{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TX4LLJZN52OXTVWZLG6DSO34GK","short_pith_number":"pith:TX4LLJZN","canonical_record":{"source":{"id":"2407.00837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T21:40:26Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"841b34c7e512f4b5086f93e8a89d962ef1c4742d339745fe4c63d6faead18193","abstract_canon_sha256":"9549c8e4e6bce5c993b11f211e246d2746faf4b4b45cb6edd39a26b02c2d5cd8"},"schema_version":"1.0"},"canonical_sha256":"9df8b5a72dee9d79d6d959bc393b7c32b29269e1fd27eb26fd6240eb089ca0b8","source":{"kind":"arxiv","id":"2407.00837","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00837","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00837v2","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00837","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"TX4LLJZN52OX","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"TX4LLJZN52OXTVWZ","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"TX4LLJZN","created_at":"2026-07-05T08:39:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TX4LLJZN52OXTVWZLG6DSO34GK","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T21:40:26Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"841b34c7e512f4b5086f93e8a89d962ef1c4742d339745fe4c63d6faead18193","abstract_canon_sha256":"9549c8e4e6bce5c993b11f211e246d2746faf4b4b45cb6edd39a26b02c2d5cd8"},"schema_version":"1.0"},"canonical_sha256":"9df8b5a72dee9d79d6d959bc393b7c32b29269e1fd27eb26fd6240eb089ca0b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:22.048171Z","signature_b64":"loY60bZ/gnNxdq68lm+HvTrUPYQcvUEzJvXYSe/jkx6TJpEr/3RKEgUEye+Frn7TDUYXE8RfZhPDUVk3l+joBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df8b5a72dee9d79d6d959bc393b7c32b29269e1fd27eb26fd6240eb089ca0b8","last_reissued_at":"2026-07-05T08:39:22.047744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:22.047744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00837","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVHLmYGbX7++TheqkJ8b4KL+3jkGIn0zh4EZGZDaGL4bTYL91jkcMIv0Hvj9r7CUn2+wXbHE5Ko3kMhorWJ7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:27:33.985913Z"},"content_sha256":"6e8f7117bfe3480e8a5adab714370149927a96d48b0231bada7510fdb3940c15","schema_version":"1.0","event_id":"sha256:6e8f7117bfe3480e8a5adab714370149927a96d48b0231bada7510fdb3940c15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TX4LLJZN52OXTVWZLG6DSO34GK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Robust Speech Representation Learning for Thousands of Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiatong Shi, Jinchuan Tian, Karen Livescu, Shinji Watanabe, Soumi Maiti, Wangyou Zhang, William Chen, Xinjian Li, Xuankai Chang, Yifan Peng","submitted_at":"2024-06-30T21:40:26Z","abstract_excerpt":"Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual Encoder for Universal Speech, trained on over 1 million hours of data across 4057 languages, extending the language coverage of SSL models 4-fold. We combine 1 million hours of speech from existing publicly accessible corpora with a newly created corpus of 7400+ hours from 4057 languages, which will be publicly released. To handle the diverse conditions of multili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00837","kind":"arxiv","version":2},"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/2407.00837/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":"2026-07-05T08:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEPu5QPAWIoL0CKG1kp47BlwC35oA+921NWpU8ygEQ8Gy2EoBPYgIYSGCjnCOw57hpt186Gi0xjkF3KH2u9DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:27:33.986424Z"},"content_sha256":"cff13b974910bdbda587ed4a32150e09e6182208e2897fb2cafddf7c19eab6bc","schema_version":"1.0","event_id":"sha256:cff13b974910bdbda587ed4a32150e09e6182208e2897fb2cafddf7c19eab6bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TX4LLJZN52OXTVWZLG6DSO34GK/bundle.json","state_url":"https://pith.science/pith/TX4LLJZN52OXTVWZLG6DSO34GK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TX4LLJZN52OXTVWZLG6DSO34GK/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":"2026-08-08T22:27:33Z","links":{"resolver":"https://pith.science/pith/TX4LLJZN52OXTVWZLG6DSO34GK","bundle":"https://pith.science/pith/TX4LLJZN52OXTVWZLG6DSO34GK/bundle.json","state":"https://pith.science/pith/TX4LLJZN52OXTVWZLG6DSO34GK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TX4LLJZN52OXTVWZLG6DSO34GK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TX4LLJZN52OXTVWZLG6DSO34GK","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":"9549c8e4e6bce5c993b11f211e246d2746faf4b4b45cb6edd39a26b02c2d5cd8","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T21:40:26Z","title_canon_sha256":"841b34c7e512f4b5086f93e8a89d962ef1c4742d339745fe4c63d6faead18193"},"schema_version":"1.0","source":{"id":"2407.00837","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00837","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00837v2","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00837","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"TX4LLJZN52OX","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"TX4LLJZN52OXTVWZ","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"TX4LLJZN","created_at":"2026-07-05T08:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:cff13b974910bdbda587ed4a32150e09e6182208e2897fb2cafddf7c19eab6bc","target":"graph","created_at":"2026-07-05T08:39:22Z","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/2407.00837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual Encoder for Universal Speech, trained on over 1 million hours of data across 4057 languages, extending the language coverage of SSL models 4-fold. We combine 1 million hours of speech from existing publicly accessible corpora with a newly created corpus of 7400+ hours from 4057 languages, which will be publicly released. To handle the diverse conditions of multili","authors_text":"Jiatong Shi, Jinchuan Tian, Karen Livescu, Shinji Watanabe, Soumi Maiti, Wangyou Zhang, William Chen, Xinjian Li, Xuankai Chang, Yifan Peng","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T21:40:26Z","title":"Towards Robust Speech Representation Learning for Thousands of Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00837","kind":"arxiv","version":2},"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":"sha256:6e8f7117bfe3480e8a5adab714370149927a96d48b0231bada7510fdb3940c15","target":"record","created_at":"2026-07-05T08:39:22Z","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":"9549c8e4e6bce5c993b11f211e246d2746faf4b4b45cb6edd39a26b02c2d5cd8","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T21:40:26Z","title_canon_sha256":"841b34c7e512f4b5086f93e8a89d962ef1c4742d339745fe4c63d6faead18193"},"schema_version":"1.0","source":{"id":"2407.00837","kind":"arxiv","version":2}},"canonical_sha256":"9df8b5a72dee9d79d6d959bc393b7c32b29269e1fd27eb26fd6240eb089ca0b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9df8b5a72dee9d79d6d959bc393b7c32b29269e1fd27eb26fd6240eb089ca0b8","first_computed_at":"2026-07-05T08:39:22.047744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:22.047744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loY60bZ/gnNxdq68lm+HvTrUPYQcvUEzJvXYSe/jkx6TJpEr/3RKEgUEye+Frn7TDUYXE8RfZhPDUVk3l+joBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:22.048171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00837","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e8f7117bfe3480e8a5adab714370149927a96d48b0231bada7510fdb3940c15","sha256:cff13b974910bdbda587ed4a32150e09e6182208e2897fb2cafddf7c19eab6bc"],"state_sha256":"08e4fc188660b7efab11f8b06152611b41efbafaeddbbec25e1026d7fd18c5dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cGY71g3e1w9bDuzL0ZsIroILuZvlJ3iUMc7+0e+mvqHOCLdGJ0/lBr0VcZemDNC2FTtDmBSU1PHd1psmjwnWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:27:33.991399Z","bundle_sha256":"e53d4509c5ba49db03194b1c53c01e851eee9b1b70d24b0e32d6d8148e6538e1"}}