{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SUXQ7RETEU4DAWVRQ7MAFVSKJS","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":"5c3f86b6ad9436156740ea0d4b4f6e6227cec696765f1cf2ddf78ff6d2e58ca5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-03T02:26:40Z","title_canon_sha256":"4e225b012c4fedc7428c94f59b730030b533f757caf95bc2d39ee0d1c5917f27"},"schema_version":"1.0","source":{"id":"2202.01374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.01374","created_at":"2026-07-05T03:53:53Z"},{"alias_kind":"arxiv_version","alias_value":"2202.01374v1","created_at":"2026-07-05T03:53:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01374","created_at":"2026-07-05T03:53:53Z"},{"alias_kind":"pith_short_12","alias_value":"SUXQ7RETEU4D","created_at":"2026-07-05T03:53:53Z"},{"alias_kind":"pith_short_16","alias_value":"SUXQ7RETEU4DAWVR","created_at":"2026-07-05T03:53:53Z"},{"alias_kind":"pith_short_8","alias_value":"SUXQ7RET","created_at":"2026-07-05T03:53:53Z"}],"graph_snapshots":[{"event_id":"sha256:a43ed26a66b76a3ce0e96715f2f8ba0be1267e48122d5a12223696282b9caec2","target":"graph","created_at":"2026-07-05T03:53:53Z","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/2202.01374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines w2v-BERT pre-training on speech with SpanBERT pre-training on character-level text, along with Connectionist Temporal Classification (CTC) losses on paired speech and transcript data, to learn a single model capable of learning from and representing both speech and text signals in a shared representation space. We evaluate mSLAM on several downstream speech ","authors_text":"Alexis Conneau, Ankur Bapna, Colin Cherry, Jason Riesa, Melvin Johnson, Simran Khanuja, Ye Jia, Yong Cheng, Yu Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-03T02:26:40Z","title":"mSLAM: Massively multilingual joint pre-training for speech and text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01374","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":"sha256:394984f7fe87bb88e38ab5374f8bd1467508a1aaa1c8f740618bd83f1c605191","target":"record","created_at":"2026-07-05T03:53:53Z","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":"5c3f86b6ad9436156740ea0d4b4f6e6227cec696765f1cf2ddf78ff6d2e58ca5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-03T02:26:40Z","title_canon_sha256":"4e225b012c4fedc7428c94f59b730030b533f757caf95bc2d39ee0d1c5917f27"},"schema_version":"1.0","source":{"id":"2202.01374","kind":"arxiv","version":1}},"canonical_sha256":"952f0fc4932538305ab187d802d64a4cbeb85f65af4f8e8820d973d95d797ed7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"952f0fc4932538305ab187d802d64a4cbeb85f65af4f8e8820d973d95d797ed7","first_computed_at":"2026-07-05T03:53:53.598142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:53.598142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+AHoKzpVUESZhXENTm63PxWyCQSjsMWJHfBmJwafqL85HOh6tEHcnr29AfvmdB71YMVTmH47X/wDgwEcyvhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:53.598607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.01374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:394984f7fe87bb88e38ab5374f8bd1467508a1aaa1c8f740618bd83f1c605191","sha256:a43ed26a66b76a3ce0e96715f2f8ba0be1267e48122d5a12223696282b9caec2"],"state_sha256":"40fd6b883e9605e8aca2edc8df4bd11f7e2c89b5fef9d538655504690cdbc5f6"}