{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BXCKJI2RVE246OJL43WTE64XQT","short_pith_number":"pith:BXCKJI2R","canonical_record":{"source":{"id":"1912.06670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-13T19:22:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89842a41d6da4385b722197152b0d86b9217adf675646a9e03592b3687bc3648","abstract_canon_sha256":"a7ca5508d8b7f5ad4fa0db0822678ddbce0df3b768a03743097c3ff7a72eed4d"},"schema_version":"1.0"},"canonical_sha256":"0dc4a4a351a935cf392be6ed327b9784c8f452404bd7032e83cf5b757768114c","source":{"kind":"arxiv","id":"1912.06670","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.06670","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"1912.06670v2","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06670","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"BXCKJI2RVE24","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"BXCKJI2RVE246OJL","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"BXCKJI2R","created_at":"2026-07-05T00:46:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BXCKJI2RVE246OJL43WTE64XQT","target":"record","payload":{"canonical_record":{"source":{"id":"1912.06670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-13T19:22:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89842a41d6da4385b722197152b0d86b9217adf675646a9e03592b3687bc3648","abstract_canon_sha256":"a7ca5508d8b7f5ad4fa0db0822678ddbce0df3b768a03743097c3ff7a72eed4d"},"schema_version":"1.0"},"canonical_sha256":"0dc4a4a351a935cf392be6ed327b9784c8f452404bd7032e83cf5b757768114c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:05.703987Z","signature_b64":"Iq29G9HClmIehXl6GpLTzkHJQeMmpFv2/VR+4oC8qljfZ1mTbcDU5CxmgYn4gTt6hYaZgdtBUyAKPm8cfQIXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc4a4a351a935cf392be6ed327b9784c8f452404bd7032e83cf5b757768114c","last_reissued_at":"2026-07-05T00:46:05.703460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:05.703460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.06670","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":"2026-07-05T00:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPPQV4mEFItGKU6U/EgAfU/6rLJcxZyu/fJXY845kXj2olAgkY2fWaFjBIrNLJ+eCsRIN9Ltvr53lhqit2hJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:41:57.029565Z"},"content_sha256":"ccd2588e17d4b6c20846bbd2196900fc968733bd641435c355f495afd1fedcb8","schema_version":"1.0","event_id":"sha256:ccd2588e17d4b6c20846bbd2196900fc968733bd641435c355f495afd1fedcb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BXCKJI2RVE246OJL43WTE64XQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Common Voice: A Massively-Multilingual Speech Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Francis M. Tyers, Gregor Weber, Josh Meyer, Kelly Davis, Lindsay Saunders, Megan Branson, Michael Henretty, Michael Kohler, Reuben Morais, Rosana Ardila","submitted_at":"2019-12-13T19:22:44Z","abstract_excerpt":"The Common Voice corpus is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Common Voice is designed for Automatic Speech Recognition purposes but can be useful in other domains (e.g. language identification). To achieve scale and sustainability, the Common Voice project employs crowdsourcing for both data collection and data validation. The most recent release includes 29 languages, and as of November 2019 there are a total of 38 languages collecting data. Over 50,000 individuals have participated so far, resulting in 2,500 hou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06670","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/1912.06670/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":"2026-07-05T00:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LKQ39gtCoueKuqfi4pLo0pjBOGsAjgvYMmTc0YCUQZTFuZL6EERsbHR4yuQgBJ4i7sFnn4hjNradm/dmpgyxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:41:57.030128Z"},"content_sha256":"0e3780c05cf45ae13e0c5910c762cf87db9015d1ff85714d58f28215ee02ce0f","schema_version":"1.0","event_id":"sha256:0e3780c05cf45ae13e0c5910c762cf87db9015d1ff85714d58f28215ee02ce0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXCKJI2RVE246OJL43WTE64XQT/bundle.json","state_url":"https://pith.science/pith/BXCKJI2RVE246OJL43WTE64XQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXCKJI2RVE246OJL43WTE64XQT/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":"2026-08-19T11:41:57Z","links":{"resolver":"https://pith.science/pith/BXCKJI2RVE246OJL43WTE64XQT","bundle":"https://pith.science/pith/BXCKJI2RVE246OJL43WTE64XQT/bundle.json","state":"https://pith.science/pith/BXCKJI2RVE246OJL43WTE64XQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXCKJI2RVE246OJL43WTE64XQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BXCKJI2RVE246OJL43WTE64XQT","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":"a7ca5508d8b7f5ad4fa0db0822678ddbce0df3b768a03743097c3ff7a72eed4d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-13T19:22:44Z","title_canon_sha256":"89842a41d6da4385b722197152b0d86b9217adf675646a9e03592b3687bc3648"},"schema_version":"1.0","source":{"id":"1912.06670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.06670","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"1912.06670v2","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06670","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"BXCKJI2RVE24","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"BXCKJI2RVE246OJL","created_at":"2026-07-05T00:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"BXCKJI2R","created_at":"2026-07-05T00:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:0e3780c05cf45ae13e0c5910c762cf87db9015d1ff85714d58f28215ee02ce0f","target":"graph","created_at":"2026-07-05T00:46:05Z","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/1912.06670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Common Voice corpus is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Common Voice is designed for Automatic Speech Recognition purposes but can be useful in other domains (e.g. language identification). To achieve scale and sustainability, the Common Voice project employs crowdsourcing for both data collection and data validation. The most recent release includes 29 languages, and as of November 2019 there are a total of 38 languages collecting data. Over 50,000 individuals have participated so far, resulting in 2,500 hou","authors_text":"Francis M. Tyers, Gregor Weber, Josh Meyer, Kelly Davis, Lindsay Saunders, Megan Branson, Michael Henretty, Michael Kohler, Reuben Morais, Rosana Ardila","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-13T19:22:44Z","title":"Common Voice: A Massively-Multilingual Speech Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06670","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:ccd2588e17d4b6c20846bbd2196900fc968733bd641435c355f495afd1fedcb8","target":"record","created_at":"2026-07-05T00:46:05Z","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":"a7ca5508d8b7f5ad4fa0db0822678ddbce0df3b768a03743097c3ff7a72eed4d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-13T19:22:44Z","title_canon_sha256":"89842a41d6da4385b722197152b0d86b9217adf675646a9e03592b3687bc3648"},"schema_version":"1.0","source":{"id":"1912.06670","kind":"arxiv","version":2}},"canonical_sha256":"0dc4a4a351a935cf392be6ed327b9784c8f452404bd7032e83cf5b757768114c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dc4a4a351a935cf392be6ed327b9784c8f452404bd7032e83cf5b757768114c","first_computed_at":"2026-07-05T00:46:05.703460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:46:05.703460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iq29G9HClmIehXl6GpLTzkHJQeMmpFv2/VR+4oC8qljfZ1mTbcDU5CxmgYn4gTt6hYaZgdtBUyAKPm8cfQIXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:46:05.703987Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.06670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccd2588e17d4b6c20846bbd2196900fc968733bd641435c355f495afd1fedcb8","sha256:0e3780c05cf45ae13e0c5910c762cf87db9015d1ff85714d58f28215ee02ce0f"],"state_sha256":"b376cfc547191e37c6bd050e36146c046e8b2f84b776c92d1eb49307ee5956e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ShtiLWekC44SVGmdthanM8GKXv8U9pKsy32YcuU/kl9+a3asl0aPYeh+Y3t8qxA15oSLLxOzSFo9r4zUtFi2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:41:57.040952Z","bundle_sha256":"9917ed5f74ac51fada75c4ef99740d10f6c17b305b4f13e0845c6e54ff960ad1"}}