{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JLJTZBECLLJWRD46FPSFL5ZMJY","short_pith_number":"pith:JLJTZBEC","canonical_record":{"source":{"id":"2308.15710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T02:14:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"659ce7c93f9cd048f42980ecf8043fa73cc5e4df37aed3aa6ce7d298be1d9112","abstract_canon_sha256":"306b3eebca58310f13d8591be6f004b0a3b0ddf5202831a05524c71aaafacca9"},"schema_version":"1.0"},"canonical_sha256":"4ad33c84825ad3688f9e2be455f72c4e29d05c457b881f7e318e605c3836e59d","source":{"kind":"arxiv","id":"2308.15710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15710","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15710v1","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15710","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"JLJTZBECLLJW","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"JLJTZBECLLJWRD46","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"JLJTZBEC","created_at":"2026-07-05T06:46:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JLJTZBECLLJWRD46FPSFL5ZMJY","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T02:14:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"659ce7c93f9cd048f42980ecf8043fa73cc5e4df37aed3aa6ce7d298be1d9112","abstract_canon_sha256":"306b3eebca58310f13d8591be6f004b0a3b0ddf5202831a05524c71aaafacca9"},"schema_version":"1.0"},"canonical_sha256":"4ad33c84825ad3688f9e2be455f72c4e29d05c457b881f7e318e605c3836e59d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:12.179261Z","signature_b64":"MTdfHE8h3Oi5sGWd1V42Ri34GAknfglfG2nqH1I0SFouwzE2ERG4X0WtaxBxl37iGLPqxUdC0OCZGaKpDojWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ad33c84825ad3688f9e2be455f72c4e29d05c457b881f7e318e605c3836e59d","last_reissued_at":"2026-07-05T06:46:12.178918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:12.178918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15710","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfzqv7NsFHSrEzmmqg2v0waOTv3vo+Iv1D4Hap1F4B2WpsOFnQAbEGLao3+gTpR33d2scnd5pc6mhKS31JwZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:06:24.574857Z"},"content_sha256":"51c2647a8eb74e494bb2b61efaf566767400bb86f26b69d470128a3674314341","schema_version":"1.0","event_id":"sha256:51c2647a8eb74e494bb2b61efaf566767400bb86f26b69d470128a3674314341"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JLJTZBECLLJWRD46FPSFL5ZMJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Wikimedia: A 77 Language Multilingual Speech Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Galvez, David Kanter, Juan Ciro, Juli\\'an Eusse, Kurt Bollacker, Rafael Mosquera G\\'omez, Ryan Hileman","submitted_at":"2023-08-30T02:14:49Z","abstract_excerpt":"The Speech Wikimedia Dataset is a publicly available compilation of audio with transcriptions extracted from Wikimedia Commons. It includes 1780 hours (195 GB) of CC-BY-SA licensed transcribed speech from a diverse set of scenarios and speakers, in 77 different languages. Each audio file has one or more transcriptions in different languages, making this dataset suitable for training speech recognition, speech translation, and machine translation models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15710","kind":"arxiv","version":1},"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/2308.15710/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":"2026-07-05T06:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sP1NkYj9C09JqmdPjSApJOyR9P2+Y1H/gIM/uRJq+dTvCdvOujlCa1tiWjLt7ur13klqXbwKEpkT5G/BmTkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:06:24.575224Z"},"content_sha256":"a487b09643cb7f78e73dfe56a46a8d556eb0dda0a89ae14d5ca0d66318e31921","schema_version":"1.0","event_id":"sha256:a487b09643cb7f78e73dfe56a46a8d556eb0dda0a89ae14d5ca0d66318e31921"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLJTZBECLLJWRD46FPSFL5ZMJY/bundle.json","state_url":"https://pith.science/pith/JLJTZBECLLJWRD46FPSFL5ZMJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLJTZBECLLJWRD46FPSFL5ZMJY/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":"2026-07-06T18:06:24Z","links":{"resolver":"https://pith.science/pith/JLJTZBECLLJWRD46FPSFL5ZMJY","bundle":"https://pith.science/pith/JLJTZBECLLJWRD46FPSFL5ZMJY/bundle.json","state":"https://pith.science/pith/JLJTZBECLLJWRD46FPSFL5ZMJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLJTZBECLLJWRD46FPSFL5ZMJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JLJTZBECLLJWRD46FPSFL5ZMJY","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":"306b3eebca58310f13d8591be6f004b0a3b0ddf5202831a05524c71aaafacca9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T02:14:49Z","title_canon_sha256":"659ce7c93f9cd048f42980ecf8043fa73cc5e4df37aed3aa6ce7d298be1d9112"},"schema_version":"1.0","source":{"id":"2308.15710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15710","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15710v1","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15710","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"JLJTZBECLLJW","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"JLJTZBECLLJWRD46","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"JLJTZBEC","created_at":"2026-07-05T06:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:a487b09643cb7f78e73dfe56a46a8d556eb0dda0a89ae14d5ca0d66318e31921","target":"graph","created_at":"2026-07-05T06:46:12Z","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/2308.15710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Speech Wikimedia Dataset is a publicly available compilation of audio with transcriptions extracted from Wikimedia Commons. It includes 1780 hours (195 GB) of CC-BY-SA licensed transcribed speech from a diverse set of scenarios and speakers, in 77 different languages. Each audio file has one or more transcriptions in different languages, making this dataset suitable for training speech recognition, speech translation, and machine translation models.","authors_text":"Daniel Galvez, David Kanter, Juan Ciro, Juli\\'an Eusse, Kurt Bollacker, Rafael Mosquera G\\'omez, Ryan Hileman","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T02:14:49Z","title":"Speech Wikimedia: A 77 Language Multilingual Speech Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15710","kind":"arxiv","version":1},"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":"sha256:51c2647a8eb74e494bb2b61efaf566767400bb86f26b69d470128a3674314341","target":"record","created_at":"2026-07-05T06:46:12Z","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":"306b3eebca58310f13d8591be6f004b0a3b0ddf5202831a05524c71aaafacca9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T02:14:49Z","title_canon_sha256":"659ce7c93f9cd048f42980ecf8043fa73cc5e4df37aed3aa6ce7d298be1d9112"},"schema_version":"1.0","source":{"id":"2308.15710","kind":"arxiv","version":1}},"canonical_sha256":"4ad33c84825ad3688f9e2be455f72c4e29d05c457b881f7e318e605c3836e59d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ad33c84825ad3688f9e2be455f72c4e29d05c457b881f7e318e605c3836e59d","first_computed_at":"2026-07-05T06:46:12.178918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:12.178918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MTdfHE8h3Oi5sGWd1V42Ri34GAknfglfG2nqH1I0SFouwzE2ERG4X0WtaxBxl37iGLPqxUdC0OCZGaKpDojWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:12.179261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51c2647a8eb74e494bb2b61efaf566767400bb86f26b69d470128a3674314341","sha256:a487b09643cb7f78e73dfe56a46a8d556eb0dda0a89ae14d5ca0d66318e31921"],"state_sha256":"0cfa0a873deb10a0da242434081d5ecc5289f43153024632c9a1e02f0be469c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kw3wOmfMAfcgWVwBzSiGlldBwmkiJliwBiqYmsRpY8GTcVT4cD7BX+3dyZtKHX6toOi1BpJZz+eY0+m0724gCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:06:24.577197Z","bundle_sha256":"d2444de2219d04d6fbdc4bad84bbabac5babd03808c124871f97325f33398c1a"}}