{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:D3VJHTYJ4IBDHVSIRAK5DVFH4N","short_pith_number":"pith:D3VJHTYJ","canonical_record":{"source":{"id":"1907.12895","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-30T13:31:49Z","cross_cats_sorted":[],"title_canon_sha256":"c0f732d243579175bd65477fc4ce309115f59eb73144c30e77f74bbff54e165e","abstract_canon_sha256":"e91a97034d87f687e17f016fec06f742b76077164ed0943eaf1af5a69ecdb3cc"},"schema_version":"1.0"},"canonical_sha256":"1eea93cf09e20233d6488815d1d4a7e35fd072afa096338f1dac4ce5923e6763","source":{"kind":"arxiv","id":"1907.12895","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12895","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12895v3","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12895","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"D3VJHTYJ4IBD","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"pith_short_16","alias_value":"D3VJHTYJ4IBDHVSI","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"pith_short_8","alias_value":"D3VJHTYJ","created_at":"2026-07-05T00:43:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:D3VJHTYJ4IBDHVSIRAK5DVFH4N","target":"record","payload":{"canonical_record":{"source":{"id":"1907.12895","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-30T13:31:49Z","cross_cats_sorted":[],"title_canon_sha256":"c0f732d243579175bd65477fc4ce309115f59eb73144c30e77f74bbff54e165e","abstract_canon_sha256":"e91a97034d87f687e17f016fec06f742b76077164ed0943eaf1af5a69ecdb3cc"},"schema_version":"1.0"},"canonical_sha256":"1eea93cf09e20233d6488815d1d4a7e35fd072afa096338f1dac4ce5923e6763","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:55.288387Z","signature_b64":"e87DvTahBmnGsPgu89jLdhPypziUFcbQBCndFl+l9IKx7ipI9qxlAU9QeorQGYyfDNCQ8QJ6JmNXF69vLjZQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eea93cf09e20233d6488815d1d4a7e35fd072afa096338f1dac4ce5923e6763","last_reissued_at":"2026-07-05T00:43:55.287810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:55.287810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.12895","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:43:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YHS1x2p1bEh5TmHyl3eQaA+j/uBHKBC03V7NXgT5VMRAKwORdKkUWF/viDac5Bm0JtTWSBsbtRO0Ph626xXEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:15:19.051317Z"},"content_sha256":"6a86aeba8f8a3e9b71362f1565cfbb7a16e2f55ef0f639ae22e3bd4fb7c66ef1","schema_version":"1.0","event_id":"sha256:6a86aeba8f8a3e9b71362f1565cfbb7a16e2f55ef0f639ae22e3bd4fb7c66ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:D3VJHTYJ4IBDHVSIRAK5DVFH4N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"\\'Eric Le Ferrand, Laurent Besacier, Mahault Garnerin, Marcely Zanon Boito, William N. Havard","submitted_at":"2019-07-30T13:31:49Z","abstract_excerpt":"The CMU Wilderness Multilingual Speech Dataset (Black, 2019) is a newly published multilingual speech dataset based on recorded readings of the New Testament. It provides data to build Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) models for potentially 700 languages. However, the fact that the source content (the Bible) is the same for all the languages is not exploited to date.Therefore, this article proposes to add multilingual links between speech segments in different languages, and shares a large and clean dataset of 8,130 parallel spoken utterances across 8 languages (56 l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12895","kind":"arxiv","version":3},"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/1907.12895/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":"2026-07-05T00:43:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fV4EiUSQLIu3kiFjAcFoZCpc+DkQZ1mQeq4GXmGxY43VxWUb50ukjRuLlJooH4TyL9ehNutTJpkcMARhyRDtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:15:19.051812Z"},"content_sha256":"89ffd9d4dff4ad7a63381efa926098d61b646414c2a00bd20c1021ac71c1bd1b","schema_version":"1.0","event_id":"sha256:89ffd9d4dff4ad7a63381efa926098d61b646414c2a00bd20c1021ac71c1bd1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N/bundle.json","state_url":"https://pith.science/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N/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":"2026-08-16T10:15:19Z","links":{"resolver":"https://pith.science/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N","bundle":"https://pith.science/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N/bundle.json","state":"https://pith.science/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D3VJHTYJ4IBDHVSIRAK5DVFH4N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:D3VJHTYJ4IBDHVSIRAK5DVFH4N","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":"e91a97034d87f687e17f016fec06f742b76077164ed0943eaf1af5a69ecdb3cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-30T13:31:49Z","title_canon_sha256":"c0f732d243579175bd65477fc4ce309115f59eb73144c30e77f74bbff54e165e"},"schema_version":"1.0","source":{"id":"1907.12895","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12895","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12895v3","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12895","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"D3VJHTYJ4IBD","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"pith_short_16","alias_value":"D3VJHTYJ4IBDHVSI","created_at":"2026-07-05T00:43:55Z"},{"alias_kind":"pith_short_8","alias_value":"D3VJHTYJ","created_at":"2026-07-05T00:43:55Z"}],"graph_snapshots":[{"event_id":"sha256:89ffd9d4dff4ad7a63381efa926098d61b646414c2a00bd20c1021ac71c1bd1b","target":"graph","created_at":"2026-07-05T00:43:55Z","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/1907.12895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The CMU Wilderness Multilingual Speech Dataset (Black, 2019) is a newly published multilingual speech dataset based on recorded readings of the New Testament. It provides data to build Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) models for potentially 700 languages. However, the fact that the source content (the Bible) is the same for all the languages is not exploited to date.Therefore, this article proposes to add multilingual links between speech segments in different languages, and shares a large and clean dataset of 8,130 parallel spoken utterances across 8 languages (56 l","authors_text":"\\'Eric Le Ferrand, Laurent Besacier, Mahault Garnerin, Marcely Zanon Boito, William N. Havard","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-30T13:31:49Z","title":"MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12895","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":"sha256:6a86aeba8f8a3e9b71362f1565cfbb7a16e2f55ef0f639ae22e3bd4fb7c66ef1","target":"record","created_at":"2026-07-05T00:43:55Z","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":"e91a97034d87f687e17f016fec06f742b76077164ed0943eaf1af5a69ecdb3cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-30T13:31:49Z","title_canon_sha256":"c0f732d243579175bd65477fc4ce309115f59eb73144c30e77f74bbff54e165e"},"schema_version":"1.0","source":{"id":"1907.12895","kind":"arxiv","version":3}},"canonical_sha256":"1eea93cf09e20233d6488815d1d4a7e35fd072afa096338f1dac4ce5923e6763","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eea93cf09e20233d6488815d1d4a7e35fd072afa096338f1dac4ce5923e6763","first_computed_at":"2026-07-05T00:43:55.287810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:55.287810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e87DvTahBmnGsPgu89jLdhPypziUFcbQBCndFl+l9IKx7ipI9qxlAU9QeorQGYyfDNCQ8QJ6JmNXF69vLjZQAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:55.288387Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.12895","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a86aeba8f8a3e9b71362f1565cfbb7a16e2f55ef0f639ae22e3bd4fb7c66ef1","sha256:89ffd9d4dff4ad7a63381efa926098d61b646414c2a00bd20c1021ac71c1bd1b"],"state_sha256":"2eed5c38a7f31c6184adbce85211739978450c97f2dbfd36b62ed7e8659b9e45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4n1aIlrZZsmW2PPlGmMqE17boWaSwwzobXEhAxaz7Hdw0xoc1CrCTBfF2cSkK1lkK8EzZZ5wZaLlizGu1/oDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:15:19.055202Z","bundle_sha256":"f8c2699009ba264af1a4142362c7240cdf2d1d263cda041cd56ef5a801006d67"}}