{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:L3FPEJY5PIGNA6WVPDML4GGSCM","short_pith_number":"pith:L3FPEJY5","canonical_record":{"source":{"id":"2211.04508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:09:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4877502f1f2fb88f2a539d1299cddec3a79e253080cfde53e01b96a8bb78ed8f","abstract_canon_sha256":"463ad0f61ff88f2bbb14f17ecbe57311753adf43290ce372228027e1ca859993"},"schema_version":"1.0"},"canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","source":{"kind":"arxiv","id":"2211.04508","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04508","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04508v1","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04508","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"L3FPEJY5PIGN","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"L3FPEJY5PIGNA6WV","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"L3FPEJY5","created_at":"2026-07-05T05:14:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:L3FPEJY5PIGNA6WVPDML4GGSCM","target":"record","payload":{"canonical_record":{"source":{"id":"2211.04508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:09:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4877502f1f2fb88f2a539d1299cddec3a79e253080cfde53e01b96a8bb78ed8f","abstract_canon_sha256":"463ad0f61ff88f2bbb14f17ecbe57311753adf43290ce372228027e1ca859993"},"schema_version":"1.0"},"canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:38.709767Z","signature_b64":"BABVf8/i84WbFhM3IioEwpyeE0/iCjZB3/5kyZ2huIFy6qzuU0G2TmG8ypJfpMxYU6xAgHprJgRIoRYg1uA1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","last_reissued_at":"2026-07-05T05:14:38.709251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:38.709251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.04508","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":"2026-07-05T05:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ey8a93H/PyZ6cP2IASyVpIxZsJT13U0s0XtISLOCcrBpsnfOWjvQTcEXGsSSx01z0+Y0uo6jsqLU5Sa4704PCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:30:00.095782Z"},"content_sha256":"47b757bb6a6828614e464caa3c06b86d489ae388fe8f34c21913af7758ddfb7f","schema_version":"1.0","event_id":"sha256:47b757bb6a6828614e464caa3c06b86d489ae388fe8f34c21913af7758ddfb7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:L3FPEJY5PIGNA6WVPDML4GGSCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Beno\\^it Sagot, Changhan Wang, Holger Schwenk, Hongyu Gong, Jingfei Du, Juan Pino, Ning Dong, Paul-Ambroise Duquenne, Vedanuj Goswani","submitted_at":"2022-11-08T19:09:27Z","abstract_excerpt":"We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04508","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/2211.04508/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":"2026-07-05T05:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wzySfikgXxTKqtXplDks8LNfUXtWyIWQXYOrDRNmTmnrhwVRuK8rqTn2dswmDsNAdumPxavkaOZ8emVb2VciAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:30:00.096505Z"},"content_sha256":"f693f1a37fca49af9a04b6e5b191a1f0f9a0a722a8277d3ee23549ab588416a9","schema_version":"1.0","event_id":"sha256:f693f1a37fca49af9a04b6e5b191a1f0f9a0a722a8277d3ee23549ab588416a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/bundle.json","state_url":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/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":"2026-08-03T09:30:00Z","links":{"resolver":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM","bundle":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/bundle.json","state":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:L3FPEJY5PIGNA6WVPDML4GGSCM","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":"463ad0f61ff88f2bbb14f17ecbe57311753adf43290ce372228027e1ca859993","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:09:27Z","title_canon_sha256":"4877502f1f2fb88f2a539d1299cddec3a79e253080cfde53e01b96a8bb78ed8f"},"schema_version":"1.0","source":{"id":"2211.04508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04508","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04508v1","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04508","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"L3FPEJY5PIGN","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"L3FPEJY5PIGNA6WV","created_at":"2026-07-05T05:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"L3FPEJY5","created_at":"2026-07-05T05:14:38Z"}],"graph_snapshots":[{"event_id":"sha256:f693f1a37fca49af9a04b6e5b191a1f0f9a0a722a8277d3ee23549ab588416a9","target":"graph","created_at":"2026-07-05T05:14:38Z","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/2211.04508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by fe","authors_text":"Ann Lee, Beno\\^it Sagot, Changhan Wang, Holger Schwenk, Hongyu Gong, Jingfei Du, Juan Pino, Ning Dong, Paul-Ambroise Duquenne, Vedanuj Goswani","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:09:27Z","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04508","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":"sha256:47b757bb6a6828614e464caa3c06b86d489ae388fe8f34c21913af7758ddfb7f","target":"record","created_at":"2026-07-05T05:14:38Z","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":"463ad0f61ff88f2bbb14f17ecbe57311753adf43290ce372228027e1ca859993","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:09:27Z","title_canon_sha256":"4877502f1f2fb88f2a539d1299cddec3a79e253080cfde53e01b96a8bb78ed8f"},"schema_version":"1.0","source":{"id":"2211.04508","kind":"arxiv","version":1}},"canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","first_computed_at":"2026-07-05T05:14:38.709251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:38.709251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BABVf8/i84WbFhM3IioEwpyeE0/iCjZB3/5kyZ2huIFy6qzuU0G2TmG8ypJfpMxYU6xAgHprJgRIoRYg1uA1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:38.709767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47b757bb6a6828614e464caa3c06b86d489ae388fe8f34c21913af7758ddfb7f","sha256:f693f1a37fca49af9a04b6e5b191a1f0f9a0a722a8277d3ee23549ab588416a9"],"state_sha256":"407e4373f2f843dfe40b63eb10ecd7771bae7d4385bac846b194f0a904438866"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtF6k7uEN2Dnaa4mGH9IKhzrIrSV46cZ4d7VNxqO2mqZV8jYPLMTwBcYhySXajVMckITByr+xR7lOv4FIPUnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T09:30:00.103258Z","bundle_sha256":"245046d9d1bfbbb45599e5d908f617c4ab45b51cefb65692011ecc2b9e98b263"}}