{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ALRPRGUZ32XRTNMZLQWSGVSHMQ","short_pith_number":"pith:ALRPRGUZ","canonical_record":{"source":{"id":"2104.10380","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T06:44:31Z","cross_cats_sorted":[],"title_canon_sha256":"35c04233ff824a8efb01143cda6e4abe8f8e2021fb5d908eaf94b75347a70778","abstract_canon_sha256":"4f0c3bc9e2ccbbb1d30c55764f5fa4827eb5ac0e23b93619406b69d17224f5f1"},"schema_version":"1.0"},"canonical_sha256":"02e2f89a99deaf19b5995c2d23564764242a1b669f53d0302f6190d53f53a135","source":{"kind":"arxiv","id":"2104.10380","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10380","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10380v2","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10380","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"pith_short_12","alias_value":"ALRPRGUZ32XR","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"pith_short_16","alias_value":"ALRPRGUZ32XRTNMZ","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"pith_short_8","alias_value":"ALRPRGUZ","created_at":"2026-07-05T02:50:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ALRPRGUZ32XRTNMZLQWSGVSHMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2104.10380","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T06:44:31Z","cross_cats_sorted":[],"title_canon_sha256":"35c04233ff824a8efb01143cda6e4abe8f8e2021fb5d908eaf94b75347a70778","abstract_canon_sha256":"4f0c3bc9e2ccbbb1d30c55764f5fa4827eb5ac0e23b93619406b69d17224f5f1"},"schema_version":"1.0"},"canonical_sha256":"02e2f89a99deaf19b5995c2d23564764242a1b669f53d0302f6190d53f53a135","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:29.786907Z","signature_b64":"bilejuR598WOKk6r7ZZsQ5toDtpf7NBcX7OCPbM6nBYaLkryp1hdqs2EZgpHV/bvaa+OF+6wnJ1D7ncKQuHdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02e2f89a99deaf19b5995c2d23564764242a1b669f53d0302f6190d53f53a135","last_reissued_at":"2026-07-05T02:50:29.786475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:29.786475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.10380","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IaoWYTvyeZVqkVTyuLEh1XOfm4oZJIXvpAgHVd6bh+pTpRnUv3E8TErw/Op5ABaab++o1RkCx7QpEBY84tR7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:46:38.446211Z"},"content_sha256":"d869294adf43f530a23c777c9ef835a0ce58d60984d68cbc924a4a079b9634e9","schema_version":"1.0","event_id":"sha256:d869294adf43f530a23c777c9ef835a0ce58d60984d68cbc924a4a079b9634e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ALRPRGUZ32XRTNMZLQWSGVSHMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-end Speech Translation via Cross-modal Progressive Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lei Li, Mingxuan Wang, Rong Ye","submitted_at":"2021-04-21T06:44:31Z","abstract_excerpt":"End-to-end speech translation models have become a new trend in research due to their potential of reducing error propagation. However, these models still suffer from the challenge of data scarcity. How to effectively use unlabeled or other parallel corpora from machine translation is promising but still an open problem. In this paper, we propose Cross Speech-Text Network (XSTNet), an end-to-end model for speech-to-text translation. XSTNet takes both speech and text as input and outputs both transcription and translation text. The model benefits from its three key design aspects: a self-superv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10380","kind":"arxiv","version":2},"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/2104.10380/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":"2026-07-05T02:50:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfRa0Juyd9Dn7SR5rfZfDlcGVIbLQQyS0ifm2vx1w301x/mQ8Wcov/TI1F+uUIiLSBGVkUnq/veBQd/RvH5uDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:46:38.446597Z"},"content_sha256":"dc52d7de663fb058ea49831bd3bde297f04115cb0d99038cb8064a4e4c5b57dd","schema_version":"1.0","event_id":"sha256:dc52d7de663fb058ea49831bd3bde297f04115cb0d99038cb8064a4e4c5b57dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ/bundle.json","state_url":"https://pith.science/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ/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":"2026-07-06T10:46:38Z","links":{"resolver":"https://pith.science/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ","bundle":"https://pith.science/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ/bundle.json","state":"https://pith.science/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ALRPRGUZ32XRTNMZLQWSGVSHMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ALRPRGUZ32XRTNMZLQWSGVSHMQ","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":"4f0c3bc9e2ccbbb1d30c55764f5fa4827eb5ac0e23b93619406b69d17224f5f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T06:44:31Z","title_canon_sha256":"35c04233ff824a8efb01143cda6e4abe8f8e2021fb5d908eaf94b75347a70778"},"schema_version":"1.0","source":{"id":"2104.10380","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10380","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10380v2","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10380","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"pith_short_12","alias_value":"ALRPRGUZ32XR","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"pith_short_16","alias_value":"ALRPRGUZ32XRTNMZ","created_at":"2026-07-05T02:50:29Z"},{"alias_kind":"pith_short_8","alias_value":"ALRPRGUZ","created_at":"2026-07-05T02:50:29Z"}],"graph_snapshots":[{"event_id":"sha256:dc52d7de663fb058ea49831bd3bde297f04115cb0d99038cb8064a4e4c5b57dd","target":"graph","created_at":"2026-07-05T02:50:29Z","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/2104.10380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end speech translation models have become a new trend in research due to their potential of reducing error propagation. However, these models still suffer from the challenge of data scarcity. How to effectively use unlabeled or other parallel corpora from machine translation is promising but still an open problem. In this paper, we propose Cross Speech-Text Network (XSTNet), an end-to-end model for speech-to-text translation. XSTNet takes both speech and text as input and outputs both transcription and translation text. The model benefits from its three key design aspects: a self-superv","authors_text":"Lei Li, Mingxuan Wang, Rong Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T06:44:31Z","title":"End-to-end Speech Translation via Cross-modal Progressive Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10380","kind":"arxiv","version":2},"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:d869294adf43f530a23c777c9ef835a0ce58d60984d68cbc924a4a079b9634e9","target":"record","created_at":"2026-07-05T02:50:29Z","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":"4f0c3bc9e2ccbbb1d30c55764f5fa4827eb5ac0e23b93619406b69d17224f5f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T06:44:31Z","title_canon_sha256":"35c04233ff824a8efb01143cda6e4abe8f8e2021fb5d908eaf94b75347a70778"},"schema_version":"1.0","source":{"id":"2104.10380","kind":"arxiv","version":2}},"canonical_sha256":"02e2f89a99deaf19b5995c2d23564764242a1b669f53d0302f6190d53f53a135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02e2f89a99deaf19b5995c2d23564764242a1b669f53d0302f6190d53f53a135","first_computed_at":"2026-07-05T02:50:29.786475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:29.786475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bilejuR598WOKk6r7ZZsQ5toDtpf7NBcX7OCPbM6nBYaLkryp1hdqs2EZgpHV/bvaa+OF+6wnJ1D7ncKQuHdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:29.786907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.10380","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d869294adf43f530a23c777c9ef835a0ce58d60984d68cbc924a4a079b9634e9","sha256:dc52d7de663fb058ea49831bd3bde297f04115cb0d99038cb8064a4e4c5b57dd"],"state_sha256":"40030a28f01ff309c073e8c4f6ff6576e23a9905963ecd33db1c09d38ee0076d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CL/NQOheoKpuW3pK0yJ4+k2qXZmNIbgN3f/tWJCJ+TNMRPW8bAO2IOXWuoOCWzqWhbAPgYxGtSCTma3pw2I7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:46:38.448555Z","bundle_sha256":"f5357801eb042e921f99dec94f746bfb1cc87437a86d4d55e36bc7c9955f9951"}}