{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NH7D2GE3PRKZKCSV53QHO25WBO","short_pith_number":"pith:NH7D2GE3","canonical_record":{"source":{"id":"2212.03657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-07T14:22:00Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a07cef4abff7a99fcb0bcf1db59621d67c2cc32c971d9d18dcf92c5cfdbd3a25","abstract_canon_sha256":"bb517a52656da3bebc8c3681ce221fb223e857aecd96d91d8d9e9cfa9aa97f40"},"schema_version":"1.0"},"canonical_sha256":"69fe3d189b7c55950a55eee0776bb60b8cc6f4c70075233c1b7af4b462ee55eb","source":{"kind":"arxiv","id":"2212.03657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03657","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03657v1","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03657","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"NH7D2GE3PRKZ","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"NH7D2GE3PRKZKCSV","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"NH7D2GE3","created_at":"2026-07-05T05:23:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NH7D2GE3PRKZKCSV53QHO25WBO","target":"record","payload":{"canonical_record":{"source":{"id":"2212.03657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-07T14:22:00Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a07cef4abff7a99fcb0bcf1db59621d67c2cc32c971d9d18dcf92c5cfdbd3a25","abstract_canon_sha256":"bb517a52656da3bebc8c3681ce221fb223e857aecd96d91d8d9e9cfa9aa97f40"},"schema_version":"1.0"},"canonical_sha256":"69fe3d189b7c55950a55eee0776bb60b8cc6f4c70075233c1b7af4b462ee55eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:19.182902Z","signature_b64":"hR4XnR5fEjwzVawMcLAdJiHRwiLVC47+9WN35uqEgqr/lXu9Y0o4tBSOk1taO2+fB8PG9Gycwh3mMwHgfyXVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69fe3d189b7c55950a55eee0776bb60b8cc6f4c70075233c1b7af4b462ee55eb","last_reissued_at":"2026-07-05T05:23:19.182471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:19.182471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.03657","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":"2026-07-05T05:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftsWUOo+A92QbkuH+npgHlWdQXf9nPPwSpb275v6sd26xJ0xVa1wsk7qQ54OvADNcfAbj0Lc7cMoqW8CZJohCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:07:43.472037Z"},"content_sha256":"e893d57a0d58aaa68f2fbbcab6815735fbce025507cdc420e83155b1e4947c30","schema_version":"1.0","event_id":"sha256:e893d57a0d58aaa68f2fbbcab6815735fbce025507cdc420e83155b1e4947c30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NH7D2GE3PRKZKCSV53QHO25WBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M3ST: Mix at Three Levels for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Fengpeng Yue, Mingxuan Wang, Qianqian Dong, Tom Ko, Xuxin Cheng, Yuexian Zou","submitted_at":"2022-12-07T14:22:00Z","abstract_excerpt":"How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many tasks by enlarging the dataset. In this paper, we propose Mix at three levels for Speech Translation (M^3ST) method to increase the diversity of the augmented training corpus. Specifically, we conduct two phases of fine-tuning based on a pre-trained model using external machine translation (MT) data. In the first stage of fine-tuning, we mix the training corpus at three levels, including word level, sentence level a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03657","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/2212.03657/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":"2026-07-05T05:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HVQW4+ugVgAtdh3S/qtxEfcVdFHQvkC1xPpzTAqRHe5Fxx/crY8Q4zMrCdXrDu8VGU+lAd+9kRuX87Q96kMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:07:43.472455Z"},"content_sha256":"aaf63f338dcdf48586d38ba61e46d47eef56a4be6d4e1602b9b1ed26d6c52a8b","schema_version":"1.0","event_id":"sha256:aaf63f338dcdf48586d38ba61e46d47eef56a4be6d4e1602b9b1ed26d6c52a8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NH7D2GE3PRKZKCSV53QHO25WBO/bundle.json","state_url":"https://pith.science/pith/NH7D2GE3PRKZKCSV53QHO25WBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NH7D2GE3PRKZKCSV53QHO25WBO/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":"2026-07-05T14:07:43Z","links":{"resolver":"https://pith.science/pith/NH7D2GE3PRKZKCSV53QHO25WBO","bundle":"https://pith.science/pith/NH7D2GE3PRKZKCSV53QHO25WBO/bundle.json","state":"https://pith.science/pith/NH7D2GE3PRKZKCSV53QHO25WBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NH7D2GE3PRKZKCSV53QHO25WBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NH7D2GE3PRKZKCSV53QHO25WBO","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":"bb517a52656da3bebc8c3681ce221fb223e857aecd96d91d8d9e9cfa9aa97f40","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-07T14:22:00Z","title_canon_sha256":"a07cef4abff7a99fcb0bcf1db59621d67c2cc32c971d9d18dcf92c5cfdbd3a25"},"schema_version":"1.0","source":{"id":"2212.03657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03657","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03657v1","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03657","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"NH7D2GE3PRKZ","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"NH7D2GE3PRKZKCSV","created_at":"2026-07-05T05:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"NH7D2GE3","created_at":"2026-07-05T05:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:aaf63f338dcdf48586d38ba61e46d47eef56a4be6d4e1602b9b1ed26d6c52a8b","target":"graph","created_at":"2026-07-05T05:23:19Z","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/2212.03657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many tasks by enlarging the dataset. In this paper, we propose Mix at three levels for Speech Translation (M^3ST) method to increase the diversity of the augmented training corpus. Specifically, we conduct two phases of fine-tuning based on a pre-trained model using external machine translation (MT) data. In the first stage of fine-tuning, we mix the training corpus at three levels, including word level, sentence level a","authors_text":"Fengpeng Yue, Mingxuan Wang, Qianqian Dong, Tom Ko, Xuxin Cheng, Yuexian Zou","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-07T14:22:00Z","title":"M3ST: Mix at Three Levels for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03657","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:e893d57a0d58aaa68f2fbbcab6815735fbce025507cdc420e83155b1e4947c30","target":"record","created_at":"2026-07-05T05:23:19Z","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":"bb517a52656da3bebc8c3681ce221fb223e857aecd96d91d8d9e9cfa9aa97f40","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-07T14:22:00Z","title_canon_sha256":"a07cef4abff7a99fcb0bcf1db59621d67c2cc32c971d9d18dcf92c5cfdbd3a25"},"schema_version":"1.0","source":{"id":"2212.03657","kind":"arxiv","version":1}},"canonical_sha256":"69fe3d189b7c55950a55eee0776bb60b8cc6f4c70075233c1b7af4b462ee55eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69fe3d189b7c55950a55eee0776bb60b8cc6f4c70075233c1b7af4b462ee55eb","first_computed_at":"2026-07-05T05:23:19.182471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:19.182471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hR4XnR5fEjwzVawMcLAdJiHRwiLVC47+9WN35uqEgqr/lXu9Y0o4tBSOk1taO2+fB8PG9Gycwh3mMwHgfyXVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:19.182902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e893d57a0d58aaa68f2fbbcab6815735fbce025507cdc420e83155b1e4947c30","sha256:aaf63f338dcdf48586d38ba61e46d47eef56a4be6d4e1602b9b1ed26d6c52a8b"],"state_sha256":"53658ac47697a98c18266d776573f3f525e5979389728a0abba1d0a47b01c1fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8/SHtwOMH10U+zaXn3pLCtyVLZ+djj1RimYNtvX4IFrC//+6L5UkA0szBGazRXhPrmU+zNVvfQf77MCbjI2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:07:43.474924Z","bundle_sha256":"220b7021b94a28d4aa8d9c337a9efd932ac80b55b14cc37506b59811ccb233cd"}}