{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LYEWTU23J24N32FPGE6WKTWCRD","short_pith_number":"pith:LYEWTU23","canonical_record":{"source":{"id":"2203.10426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T01:49:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2d376ed1107bcaa40335f5ea2403f4a27ecf3d74d803a02eccee0efce48d4be","abstract_canon_sha256":"c1d54947cae6074c74a9aa4d8a39f24c29d5fc057803b63c7febb3204eaa67e1"},"schema_version":"1.0"},"canonical_sha256":"5e0969d35b4eb8dde8af313d654ec288e9cde35d70a828c23658cad4399817f7","source":{"kind":"arxiv","id":"2203.10426","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10426","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10426v1","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10426","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"LYEWTU23J24N","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"LYEWTU23J24N32FP","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"LYEWTU23","created_at":"2026-07-05T04:06:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LYEWTU23J24N32FPGE6WKTWCRD","target":"record","payload":{"canonical_record":{"source":{"id":"2203.10426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T01:49:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2d376ed1107bcaa40335f5ea2403f4a27ecf3d74d803a02eccee0efce48d4be","abstract_canon_sha256":"c1d54947cae6074c74a9aa4d8a39f24c29d5fc057803b63c7febb3204eaa67e1"},"schema_version":"1.0"},"canonical_sha256":"5e0969d35b4eb8dde8af313d654ec288e9cde35d70a828c23658cad4399817f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:52.789658Z","signature_b64":"R5RRPgNgKhBM0xnfMe6ImxEn/VrvzICKl7u/LI2m9ZTb2Hpo4k0Ug0ihY/9iESlrwpYzjvyefwzfh8T6UK0LAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e0969d35b4eb8dde8af313d654ec288e9cde35d70a828c23658cad4399817f7","last_reissued_at":"2026-07-05T04:06:52.789304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:52.789304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.10426","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":"2026-07-05T04:06:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XjDgev/TVBYV1mRwF16RpfspISCXDUAJJExzlIxzLKtgh79zfYnwasOcLimmK705XFX/JRZ8rejGQXRUvE2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:40:17.310741Z"},"content_sha256":"d4a0e0c175f0cda6e47c8b527439c7c1f2439f15d586df63f9825518a7ab5bc1","schema_version":"1.0","event_id":"sha256:d4a0e0c175f0cda6e47c8b527439c7c1f2439f15d586df63f9825518a7ab5bc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LYEWTU23J24N32FPGE6WKTWCRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Li, Mingxuan Wang, Qingkai Fang, Rong Ye, Yang Feng","submitted_at":"2022-03-20T01:49:53Z","abstract_excerpt":"How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data? Existing techniques often attempt to transfer powerful machine translation (MT) capabilities to ST, but neglect the representation discrepancy across modalities. In this paper, we propose the Speech-TExt Manifold Mixup (STEMM) method to calibrate such discrepancy. Specifically, we mix up the representation sequences of different modalities, and take both unimodal speech sequences and multimodal mixed sequences as input to the translation model in parallel, and regularize their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10426","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/2203.10426/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":"2026-07-05T04:06:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0S9WM1tscFl/BGamLW2hG9RcGTYtAzWXdzUMOI/rFu7Etvtq6xq9BMbtzZLr3SnOR2hPtHP0ce2wJkRnJbFQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:40:17.311192Z"},"content_sha256":"a0f3d8832dd8aedac6db34498aedbd910e5d9644ba1e0b03a37bbf19c318670b","schema_version":"1.0","event_id":"sha256:a0f3d8832dd8aedac6db34498aedbd910e5d9644ba1e0b03a37bbf19c318670b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYEWTU23J24N32FPGE6WKTWCRD/bundle.json","state_url":"https://pith.science/pith/LYEWTU23J24N32FPGE6WKTWCRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYEWTU23J24N32FPGE6WKTWCRD/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":"2026-07-08T04:40:17Z","links":{"resolver":"https://pith.science/pith/LYEWTU23J24N32FPGE6WKTWCRD","bundle":"https://pith.science/pith/LYEWTU23J24N32FPGE6WKTWCRD/bundle.json","state":"https://pith.science/pith/LYEWTU23J24N32FPGE6WKTWCRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYEWTU23J24N32FPGE6WKTWCRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LYEWTU23J24N32FPGE6WKTWCRD","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":"c1d54947cae6074c74a9aa4d8a39f24c29d5fc057803b63c7febb3204eaa67e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T01:49:53Z","title_canon_sha256":"d2d376ed1107bcaa40335f5ea2403f4a27ecf3d74d803a02eccee0efce48d4be"},"schema_version":"1.0","source":{"id":"2203.10426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10426","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10426v1","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10426","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"LYEWTU23J24N","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"LYEWTU23J24N32FP","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"LYEWTU23","created_at":"2026-07-05T04:06:52Z"}],"graph_snapshots":[{"event_id":"sha256:a0f3d8832dd8aedac6db34498aedbd910e5d9644ba1e0b03a37bbf19c318670b","target":"graph","created_at":"2026-07-05T04:06:52Z","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/2203.10426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data? Existing techniques often attempt to transfer powerful machine translation (MT) capabilities to ST, but neglect the representation discrepancy across modalities. In this paper, we propose the Speech-TExt Manifold Mixup (STEMM) method to calibrate such discrepancy. Specifically, we mix up the representation sequences of different modalities, and take both unimodal speech sequences and multimodal mixed sequences as input to the translation model in parallel, and regularize their ","authors_text":"Lei Li, Mingxuan Wang, Qingkai Fang, Rong Ye, Yang Feng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T01:49:53Z","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10426","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:d4a0e0c175f0cda6e47c8b527439c7c1f2439f15d586df63f9825518a7ab5bc1","target":"record","created_at":"2026-07-05T04:06:52Z","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":"c1d54947cae6074c74a9aa4d8a39f24c29d5fc057803b63c7febb3204eaa67e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T01:49:53Z","title_canon_sha256":"d2d376ed1107bcaa40335f5ea2403f4a27ecf3d74d803a02eccee0efce48d4be"},"schema_version":"1.0","source":{"id":"2203.10426","kind":"arxiv","version":1}},"canonical_sha256":"5e0969d35b4eb8dde8af313d654ec288e9cde35d70a828c23658cad4399817f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e0969d35b4eb8dde8af313d654ec288e9cde35d70a828c23658cad4399817f7","first_computed_at":"2026-07-05T04:06:52.789304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:52.789304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R5RRPgNgKhBM0xnfMe6ImxEn/VrvzICKl7u/LI2m9ZTb2Hpo4k0Ug0ihY/9iESlrwpYzjvyefwzfh8T6UK0LAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:52.789658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4a0e0c175f0cda6e47c8b527439c7c1f2439f15d586df63f9825518a7ab5bc1","sha256:a0f3d8832dd8aedac6db34498aedbd910e5d9644ba1e0b03a37bbf19c318670b"],"state_sha256":"a0472e7a57af3b9e0a579dd6512f3209e753d56c190ad9e0d0a865c6d68cb9d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7gNBvNOGfqCSA/frZCvuVQ7ugS9xLZf/1BNy1qJac+p8pFhU8nzeLYuj/kFaTi8ApRIuppPFFeEd9emGk6CBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T04:40:17.313193Z","bundle_sha256":"fc3f8df0bff7b90a5859fc3e56318c3db0add40f85752e7a9d7e6512531d4114"}}