{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AIUJ6Z4RSOV6LNTJ5OY7G2HBJN","short_pith_number":"pith:AIUJ6Z4R","canonical_record":{"source":{"id":"2204.05409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T20:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"29994f3f103f246041dc6d3719f2dfb5c0ea594d03ea6b57820aab48e45ea123","abstract_canon_sha256":"03263e4730c6100880acad78496dfb398cbb45ed606716fd74a453b7e51a22f4"},"schema_version":"1.0"},"canonical_sha256":"02289f679193abe5b669ebb1f368e14b4d0d465fdb1b00ca1224e79bbf3de2f0","source":{"kind":"arxiv","id":"2204.05409","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05409","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05409v1","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05409","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"AIUJ6Z4RSOV6","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"AIUJ6Z4RSOV6LNTJ","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"AIUJ6Z4R","created_at":"2026-07-05T04:13:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AIUJ6Z4RSOV6LNTJ5OY7G2HBJN","target":"record","payload":{"canonical_record":{"source":{"id":"2204.05409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T20:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"29994f3f103f246041dc6d3719f2dfb5c0ea594d03ea6b57820aab48e45ea123","abstract_canon_sha256":"03263e4730c6100880acad78496dfb398cbb45ed606716fd74a453b7e51a22f4"},"schema_version":"1.0"},"canonical_sha256":"02289f679193abe5b669ebb1f368e14b4d0d465fdb1b00ca1224e79bbf3de2f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:57.764399Z","signature_b64":"iH9M7fUn+3TIKZq0c65md5FvJVO5fOfAEEw3cv3vuPZCaCeMWdZZfr9vxZeGSFXEwBA/rUBKaMZ6CTlk4PldBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02289f679193abe5b669ebb1f368e14b4d0d465fdb1b00ca1224e79bbf3de2f0","last_reissued_at":"2026-07-05T04:13:57.764043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:57.764043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.05409","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":"2026-07-05T04:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1tcSn82xlnNqC3pBAXrcwd+FmS3htIQHgm2KGtCUMNQpm1LiaGsKRt7GfFgT6H6eUinEneNjPAQLCicrBFMuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:54:46.799494Z"},"content_sha256":"03884469df068332f321835228741855feb6a148f7055dc67a337c2df858d6e8","schema_version":"1.0","event_id":"sha256:03884469df068332f321835228741855feb6a148f7055dc67a337c2df858d6e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AIUJ6Z4RSOV6LNTJ5OY7G2HBJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Alexei Baevski, Changhan Wang, Hongyu Gong, Jiatao Gu, Juan Pino, Michael Auli, Ning Dong, Wei-Ning Hsu, Xian Li, Yun Tang","submitted_at":"2022-04-11T20:59:51Z","abstract_excerpt":"We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask leverages unlabelled speech data, and a (self-)supervised text to text subtask makes use of abundant text training data. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Our contribution lies in integrating linguistic information from the text corpus into the speech pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05409","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/2204.05409/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":"2026-07-05T04:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3B7YMXHqW6Pemwn3UMNU6ZqfKq/aY8q+rF2EwP/rAhX+fcHA29F2aqINFLSxpQNedIsG8LsbQXGIdrmNaTeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:54:46.799990Z"},"content_sha256":"ff253765606bdd03f0484cda2291e50b32c24e6badac25892d33f91f18c10de5","schema_version":"1.0","event_id":"sha256:ff253765606bdd03f0484cda2291e50b32c24e6badac25892d33f91f18c10de5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN/bundle.json","state_url":"https://pith.science/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN/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":"2026-08-06T05:54:46Z","links":{"resolver":"https://pith.science/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN","bundle":"https://pith.science/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN/bundle.json","state":"https://pith.science/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AIUJ6Z4RSOV6LNTJ5OY7G2HBJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AIUJ6Z4RSOV6LNTJ5OY7G2HBJN","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":"03263e4730c6100880acad78496dfb398cbb45ed606716fd74a453b7e51a22f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T20:59:51Z","title_canon_sha256":"29994f3f103f246041dc6d3719f2dfb5c0ea594d03ea6b57820aab48e45ea123"},"schema_version":"1.0","source":{"id":"2204.05409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05409","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05409v1","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05409","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"AIUJ6Z4RSOV6","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"AIUJ6Z4RSOV6LNTJ","created_at":"2026-07-05T04:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"AIUJ6Z4R","created_at":"2026-07-05T04:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:ff253765606bdd03f0484cda2291e50b32c24e6badac25892d33f91f18c10de5","target":"graph","created_at":"2026-07-05T04:13:57Z","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/2204.05409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask leverages unlabelled speech data, and a (self-)supervised text to text subtask makes use of abundant text training data. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Our contribution lies in integrating linguistic information from the text corpus into the speech pre-trainin","authors_text":"Abdelrahman Mohamed, Alexei Baevski, Changhan Wang, Hongyu Gong, Jiatao Gu, Juan Pino, Michael Auli, Ning Dong, Wei-Ning Hsu, Xian Li, Yun Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T20:59:51Z","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05409","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":"sha256:03884469df068332f321835228741855feb6a148f7055dc67a337c2df858d6e8","target":"record","created_at":"2026-07-05T04:13:57Z","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":"03263e4730c6100880acad78496dfb398cbb45ed606716fd74a453b7e51a22f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T20:59:51Z","title_canon_sha256":"29994f3f103f246041dc6d3719f2dfb5c0ea594d03ea6b57820aab48e45ea123"},"schema_version":"1.0","source":{"id":"2204.05409","kind":"arxiv","version":1}},"canonical_sha256":"02289f679193abe5b669ebb1f368e14b4d0d465fdb1b00ca1224e79bbf3de2f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02289f679193abe5b669ebb1f368e14b4d0d465fdb1b00ca1224e79bbf3de2f0","first_computed_at":"2026-07-05T04:13:57.764043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:57.764043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iH9M7fUn+3TIKZq0c65md5FvJVO5fOfAEEw3cv3vuPZCaCeMWdZZfr9vxZeGSFXEwBA/rUBKaMZ6CTlk4PldBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:57.764399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03884469df068332f321835228741855feb6a148f7055dc67a337c2df858d6e8","sha256:ff253765606bdd03f0484cda2291e50b32c24e6badac25892d33f91f18c10de5"],"state_sha256":"25a411f6069a93c869ce1024c07f3b3883f08d0b094f238b22951954a1e06780"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SX9la4MIyGg6xKM/7HRN5wtQiM5Vh/8aTW89XzV0ClGNTwmGhYy9HKVvRgSQHoUD36NIkUnQRf1p60Vnr9H8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:54:46.803243Z","bundle_sha256":"13955d69c79898cb8c59015ae018dd830cb21a9082b478e2c27f3e7d90323abf"}}