{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O6TKPYWEKUUFLN53MEUMK2CIZS","short_pith_number":"pith:O6TKPYWE","canonical_record":{"source":{"id":"2009.09704","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T09:19:07Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fd48638f117be23733f917485b7f53426c343652b4dd46e4905e8b1601644150","abstract_canon_sha256":"8f2d41e292aa640596cbd92780725a1c1cc0fd7c7161a50919ca5b5397e26d12"},"schema_version":"1.0"},"canonical_sha256":"77a6a7e2c4552855b7bb6128c56848ccbac71a369d4701f934712e6ed56ea70c","source":{"kind":"arxiv","id":"2009.09704","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09704","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09704v3","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09704","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"O6TKPYWEKUUF","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"O6TKPYWEKUUFLN53","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"O6TKPYWE","created_at":"2026-07-05T02:28:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O6TKPYWEKUUFLN53MEUMK2CIZS","target":"record","payload":{"canonical_record":{"source":{"id":"2009.09704","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T09:19:07Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fd48638f117be23733f917485b7f53426c343652b4dd46e4905e8b1601644150","abstract_canon_sha256":"8f2d41e292aa640596cbd92780725a1c1cc0fd7c7161a50919ca5b5397e26d12"},"schema_version":"1.0"},"canonical_sha256":"77a6a7e2c4552855b7bb6128c56848ccbac71a369d4701f934712e6ed56ea70c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:51.477560Z","signature_b64":"BIHFchq2OuInLMXEnsdgXClPIdMfJ0DPkfyG17w+nFWO8XCIn03RQR1r9T8G4EwpuY2K0jF8cbgH5VaHOtxcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77a6a7e2c4552855b7bb6128c56848ccbac71a369d4701f934712e6ed56ea70c","last_reissued_at":"2026-07-05T02:28:51.477149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:51.477149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.09704","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/2jVI5wxbxAVacVjr/ycuUUdoAh3XCdFEUSHBTZ350fEz//Sl6QeTTW8GA3HA8yXQtjwgbN5tshh+c068QfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:58:46.117196Z"},"content_sha256":"bddeeaea4e1d00f917bfdbdb4f3defa2fed85a091505b35911314f6f7a4a9a58","schema_version":"1.0","event_id":"sha256:bddeeaea4e1d00f917bfdbdb4f3defa2fed85a091505b35911314f6f7a4a9a58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O6TKPYWEKUUFLN53MEUMK2CIZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"Listen, Understand and Translate\": Triple Supervision Decouples End-to-end Speech-to-text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Hao Zhou, Lei Li, Mingxuan Wang, Qianqian Dong, Rong Ye, Shuang Xu","submitted_at":"2020-09-21T09:19:07Z","abstract_excerpt":"An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Existing methods are limited by the amount of parallel corpus. Can we build a system to fully utilize signals in a parallel ST corpus? We are inspired by human understanding system which is composed of auditory perception and cognitive processing. In this paper, we propose Listen-Understand-Translate, (LUT), a unified framework with triple supervision signals to decouple the end-to-end speech-to-text translation task. LUT is able to guide the acoustic encoder to extract as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09704","kind":"arxiv","version":3},"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/2009.09704/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":"2026-07-05T02:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EA20KyuCnlRftSADWuMWAoPVyC5jFakjwrDlxJ73/V0nLDvdXKX0MQoDqeoB7hID624WUBXfgxF0egRar1oZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:58:46.117869Z"},"content_sha256":"36e7d4aabb1832239e845a42f0a930ac9e7d5fad46919b85803dc20e58126463","schema_version":"1.0","event_id":"sha256:36e7d4aabb1832239e845a42f0a930ac9e7d5fad46919b85803dc20e58126463"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6TKPYWEKUUFLN53MEUMK2CIZS/bundle.json","state_url":"https://pith.science/pith/O6TKPYWEKUUFLN53MEUMK2CIZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6TKPYWEKUUFLN53MEUMK2CIZS/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":"2026-07-07T21:58:46Z","links":{"resolver":"https://pith.science/pith/O6TKPYWEKUUFLN53MEUMK2CIZS","bundle":"https://pith.science/pith/O6TKPYWEKUUFLN53MEUMK2CIZS/bundle.json","state":"https://pith.science/pith/O6TKPYWEKUUFLN53MEUMK2CIZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6TKPYWEKUUFLN53MEUMK2CIZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O6TKPYWEKUUFLN53MEUMK2CIZS","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":"8f2d41e292aa640596cbd92780725a1c1cc0fd7c7161a50919ca5b5397e26d12","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T09:19:07Z","title_canon_sha256":"fd48638f117be23733f917485b7f53426c343652b4dd46e4905e8b1601644150"},"schema_version":"1.0","source":{"id":"2009.09704","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09704","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09704v3","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09704","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"O6TKPYWEKUUF","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"O6TKPYWEKUUFLN53","created_at":"2026-07-05T02:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"O6TKPYWE","created_at":"2026-07-05T02:28:51Z"}],"graph_snapshots":[{"event_id":"sha256:36e7d4aabb1832239e845a42f0a930ac9e7d5fad46919b85803dc20e58126463","target":"graph","created_at":"2026-07-05T02:28:51Z","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/2009.09704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Existing methods are limited by the amount of parallel corpus. Can we build a system to fully utilize signals in a parallel ST corpus? We are inspired by human understanding system which is composed of auditory perception and cognitive processing. In this paper, we propose Listen-Understand-Translate, (LUT), a unified framework with triple supervision signals to decouple the end-to-end speech-to-text translation task. LUT is able to guide the acoustic encoder to extract as ","authors_text":"Bo Xu, Hao Zhou, Lei Li, Mingxuan Wang, Qianqian Dong, Rong Ye, Shuang Xu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T09:19:07Z","title":"\"Listen, Understand and Translate\": Triple Supervision Decouples End-to-end Speech-to-text Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09704","kind":"arxiv","version":3},"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:bddeeaea4e1d00f917bfdbdb4f3defa2fed85a091505b35911314f6f7a4a9a58","target":"record","created_at":"2026-07-05T02:28:51Z","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":"8f2d41e292aa640596cbd92780725a1c1cc0fd7c7161a50919ca5b5397e26d12","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T09:19:07Z","title_canon_sha256":"fd48638f117be23733f917485b7f53426c343652b4dd46e4905e8b1601644150"},"schema_version":"1.0","source":{"id":"2009.09704","kind":"arxiv","version":3}},"canonical_sha256":"77a6a7e2c4552855b7bb6128c56848ccbac71a369d4701f934712e6ed56ea70c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77a6a7e2c4552855b7bb6128c56848ccbac71a369d4701f934712e6ed56ea70c","first_computed_at":"2026-07-05T02:28:51.477149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:51.477149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BIHFchq2OuInLMXEnsdgXClPIdMfJ0DPkfyG17w+nFWO8XCIn03RQR1r9T8G4EwpuY2K0jF8cbgH5VaHOtxcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:51.477560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.09704","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bddeeaea4e1d00f917bfdbdb4f3defa2fed85a091505b35911314f6f7a4a9a58","sha256:36e7d4aabb1832239e845a42f0a930ac9e7d5fad46919b85803dc20e58126463"],"state_sha256":"b506d09292070704e1a6e2ed52cfe27b4cd4dc61154b98b1bb30f57a50f5f9ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ZMPvvKT+nvGgk6Gm70UxSS1/98/TNx+mcpN8YdNRi7+MpvQ6XygvXvbW6S679h2GmfDR2YiPmCJl4S0S8BJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T21:58:46.121350Z","bundle_sha256":"675024643712311441c2a2b014db834be52e925c5efe4c3707b27aea4bb714d1"}}