{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SUXYLW2A4JBJTI6Q76OYG2QLFG","short_pith_number":"pith:SUXYLW2A","canonical_record":{"source":{"id":"2101.00390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:24:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0fe2553fd8b7cac01588afabb17445b15210d5f66fea7eba300f55069777c260","abstract_canon_sha256":"4104c6a10912d3e4cbcf96a554a624c674b888aaf45a2730b6639d3ad9a1ae58"},"schema_version":"1.0"},"canonical_sha256":"952f85db40e24299a3d0ff9d836a0b29b6747df07bb1d74d71e909b364c88511","source":{"kind":"arxiv","id":"2101.00390","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00390","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00390v2","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00390","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"SUXYLW2A4JBJ","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"SUXYLW2A4JBJTI6Q","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"SUXYLW2A","created_at":"2026-07-05T03:00:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SUXYLW2A4JBJTI6Q76OYG2QLFG","target":"record","payload":{"canonical_record":{"source":{"id":"2101.00390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:24:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0fe2553fd8b7cac01588afabb17445b15210d5f66fea7eba300f55069777c260","abstract_canon_sha256":"4104c6a10912d3e4cbcf96a554a624c674b888aaf45a2730b6639d3ad9a1ae58"},"schema_version":"1.0"},"canonical_sha256":"952f85db40e24299a3d0ff9d836a0b29b6747df07bb1d74d71e909b364c88511","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:48.132801Z","signature_b64":"SV+m37NcYs70dR0i4bx24rs6Aawx5jc+/uixQ+hKqk1aWbEb88viUVTFNch/hiK9ScedPiDXe3Be4rEKRSE+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"952f85db40e24299a3d0ff9d836a0b29b6747df07bb1d74d71e909b364c88511","last_reissued_at":"2026-07-05T03:00:48.132375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:48.132375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.00390","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":"2026-07-05T03:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uvEmIEzNzPVdPEwl3CZmxIqLYWf8/KZExGCJH4/vbFhWFce0NgFR4lwQapOnevKr8ajk5BHaAzX9ozlE+OpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:04:24.997799Z"},"content_sha256":"18f37bc7b8d3a78db899b3ca824f7b79f035079a86a9b9f6a6890105915dee59","schema_version":"1.0","event_id":"sha256:18f37bc7b8d3a78db899b3ca824f7b79f035079a86a9b9f6a6890105915dee59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SUXYLW2A4JBJTI6Q76OYG2QLFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anne Wu, Ann Lee, Chaitanya Talnikar, Changhan Wang, Daniel Haziza, Emmanuel Dupoux, Juan Pino, Mary Williamson, Morgane Rivi\\`ere","submitted_at":"2021-01-02T07:24:21Z","abstract_excerpt":"We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning as well as semi-supervised learning. VoxPopuli also contains 1.8K hours of transcribed speeches in 16 languages and their aligned oral interpretations into 5 other languages totaling 5.1K hours. We provide speech recognition baselines and validate the versatility of VoxPopuli unlabelled data in semi-supervised learning under challenging out-of-domain settings. We will release the corpus at https://"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00390","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/2101.00390/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":"2026-07-05T03:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nF5+WeMncbx4AUtwiEdwumvUV9NrY4CfwPhzz8u58rvk6PksAeLmDfDd7guYbhiBM8yIHIMqjOmYnhzVvxG2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:04:24.998423Z"},"content_sha256":"deca718575fd86eae970497c41ce276832ff88cb3cda7cc1ba3ea81965eb96d2","schema_version":"1.0","event_id":"sha256:deca718575fd86eae970497c41ce276832ff88cb3cda7cc1ba3ea81965eb96d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG/bundle.json","state_url":"https://pith.science/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG/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":"2026-08-07T18:04:25Z","links":{"resolver":"https://pith.science/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG","bundle":"https://pith.science/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG/bundle.json","state":"https://pith.science/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SUXYLW2A4JBJTI6Q76OYG2QLFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SUXYLW2A4JBJTI6Q76OYG2QLFG","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":"4104c6a10912d3e4cbcf96a554a624c674b888aaf45a2730b6639d3ad9a1ae58","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:24:21Z","title_canon_sha256":"0fe2553fd8b7cac01588afabb17445b15210d5f66fea7eba300f55069777c260"},"schema_version":"1.0","source":{"id":"2101.00390","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00390","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00390v2","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00390","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"SUXYLW2A4JBJ","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"SUXYLW2A4JBJTI6Q","created_at":"2026-07-05T03:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"SUXYLW2A","created_at":"2026-07-05T03:00:48Z"}],"graph_snapshots":[{"event_id":"sha256:deca718575fd86eae970497c41ce276832ff88cb3cda7cc1ba3ea81965eb96d2","target":"graph","created_at":"2026-07-05T03:00:48Z","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/2101.00390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning as well as semi-supervised learning. VoxPopuli also contains 1.8K hours of transcribed speeches in 16 languages and their aligned oral interpretations into 5 other languages totaling 5.1K hours. We provide speech recognition baselines and validate the versatility of VoxPopuli unlabelled data in semi-supervised learning under challenging out-of-domain settings. We will release the corpus at https://","authors_text":"Anne Wu, Ann Lee, Chaitanya Talnikar, Changhan Wang, Daniel Haziza, Emmanuel Dupoux, Juan Pino, Mary Williamson, Morgane Rivi\\`ere","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:24:21Z","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00390","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":"sha256:18f37bc7b8d3a78db899b3ca824f7b79f035079a86a9b9f6a6890105915dee59","target":"record","created_at":"2026-07-05T03:00:48Z","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":"4104c6a10912d3e4cbcf96a554a624c674b888aaf45a2730b6639d3ad9a1ae58","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:24:21Z","title_canon_sha256":"0fe2553fd8b7cac01588afabb17445b15210d5f66fea7eba300f55069777c260"},"schema_version":"1.0","source":{"id":"2101.00390","kind":"arxiv","version":2}},"canonical_sha256":"952f85db40e24299a3d0ff9d836a0b29b6747df07bb1d74d71e909b364c88511","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"952f85db40e24299a3d0ff9d836a0b29b6747df07bb1d74d71e909b364c88511","first_computed_at":"2026-07-05T03:00:48.132375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:48.132375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SV+m37NcYs70dR0i4bx24rs6Aawx5jc+/uixQ+hKqk1aWbEb88viUVTFNch/hiK9ScedPiDXe3Be4rEKRSE+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:48.132801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00390","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18f37bc7b8d3a78db899b3ca824f7b79f035079a86a9b9f6a6890105915dee59","sha256:deca718575fd86eae970497c41ce276832ff88cb3cda7cc1ba3ea81965eb96d2"],"state_sha256":"3a09a8b54053b5c8af60c17e32f9acf35cf88b253075d7ebe8d29b227f7d781c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eyXsJNn+VEYLkRixco5z6pdHy1lE1GJd+Jn0sC1mvCWf/2bmrLcqEc3jcltZBtannb4THTyTw3d2Vn8t9s2yAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:04:25.003296Z","bundle_sha256":"b4fdbe7b008c938432749dd6cb841cb7ce09e257c8877672e9ab683fdb860908"}}