{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PWYOTD647WH3DPCKR5ETU3VR4D","short_pith_number":"pith:PWYOTD64","canonical_record":{"source":{"id":"2105.05752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T16:09:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dd2315def832b0153fa00554e6b9f975770bc2e742d72eb7456aa3678afd22ee","abstract_canon_sha256":"caeb52d602bf60e2e68a787bd895481474aebc0fe4eb4e3baa1ddad084f4753d"},"schema_version":"1.0"},"canonical_sha256":"7db0e98fdcfd8fb1bc4a8f493a6eb1e0dc96506513dd30bf8c45853961deb0a3","source":{"kind":"arxiv","id":"2105.05752","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05752","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05752v2","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05752","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"PWYOTD647WH3","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"pith_short_16","alias_value":"PWYOTD647WH3DPCK","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"pith_short_8","alias_value":"PWYOTD64","created_at":"2026-07-05T02:49:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PWYOTD647WH3DPCKR5ETU3VR4D","target":"record","payload":{"canonical_record":{"source":{"id":"2105.05752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T16:09:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dd2315def832b0153fa00554e6b9f975770bc2e742d72eb7456aa3678afd22ee","abstract_canon_sha256":"caeb52d602bf60e2e68a787bd895481474aebc0fe4eb4e3baa1ddad084f4753d"},"schema_version":"1.0"},"canonical_sha256":"7db0e98fdcfd8fb1bc4a8f493a6eb1e0dc96506513dd30bf8c45853961deb0a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:30.503956Z","signature_b64":"nf6yt0CvN9qkiQnmZIneOHDDhyUXnFhySQq5IqPqJD943e/F759SMt7AOATcNjIxpHran46Px3TLOGuaZRvjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db0e98fdcfd8fb1bc4a8f493a6eb1e0dc96506513dd30bf8c45853961deb0a3","last_reissued_at":"2026-07-05T02:49:30.503532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:30.503532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.05752","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":"2026-07-05T02:49:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqbHee27hNmO77JKIxUzZLKuNw/1KLoymqoSqI93lLZDUYO5zGenx5Dh/4JR0gqU2rfKZHy2Jn1HCe7RNxNPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T14:05:17.508630Z"},"content_sha256":"f7356621fd6cb0221e57df7c13913df002b8470b45fec18b6f831744d0316633","schema_version":"1.0","event_id":"sha256:f7356621fd6cb0221e57df7c13913df002b8470b45fec18b6f831744d0316633"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PWYOTD647WH3DPCKR5ETU3VR4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bojie Hu, Chen Xu, Jingbo Zhu, Qi Ju, Shen Huang, Tong Xiao, Yanyang Li, Yuhao Zhang","submitted_at":"2021-05-12T16:09:53Z","abstract_excerpt":"Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT) encoders. For example, we find that ASR encoders lack the global context representation, which is necessary for translation, whereas MT encoders are not designed to deal with long but locally attentive acoustic sequences. In this work, we propose a Stacked Acoustic-and-Textual Encoding (SATE) method for speech translation. Our encoder begins with processing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05752","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/2105.05752/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":"2026-07-05T02:49:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mgTNoHrgt8YzzGJ0fRSBCD75jWUlO9e3fOOZa+rnDUC0ZGknLP9nxy1GUbu5L+J2wzszrDUC92c6g0zaBP6HDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T14:05:17.510303Z"},"content_sha256":"19958a9ac1899bea32c48f1f1c4099ac65a8f336f1039b2b5042054b7aeac5ba","schema_version":"1.0","event_id":"sha256:19958a9ac1899bea32c48f1f1c4099ac65a8f336f1039b2b5042054b7aeac5ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWYOTD647WH3DPCKR5ETU3VR4D/bundle.json","state_url":"https://pith.science/pith/PWYOTD647WH3DPCKR5ETU3VR4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWYOTD647WH3DPCKR5ETU3VR4D/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":"2026-07-26T14:05:17Z","links":{"resolver":"https://pith.science/pith/PWYOTD647WH3DPCKR5ETU3VR4D","bundle":"https://pith.science/pith/PWYOTD647WH3DPCKR5ETU3VR4D/bundle.json","state":"https://pith.science/pith/PWYOTD647WH3DPCKR5ETU3VR4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWYOTD647WH3DPCKR5ETU3VR4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PWYOTD647WH3DPCKR5ETU3VR4D","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":"caeb52d602bf60e2e68a787bd895481474aebc0fe4eb4e3baa1ddad084f4753d","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T16:09:53Z","title_canon_sha256":"dd2315def832b0153fa00554e6b9f975770bc2e742d72eb7456aa3678afd22ee"},"schema_version":"1.0","source":{"id":"2105.05752","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05752","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05752v2","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05752","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"PWYOTD647WH3","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"pith_short_16","alias_value":"PWYOTD647WH3DPCK","created_at":"2026-07-05T02:49:30Z"},{"alias_kind":"pith_short_8","alias_value":"PWYOTD64","created_at":"2026-07-05T02:49:30Z"}],"graph_snapshots":[{"event_id":"sha256:19958a9ac1899bea32c48f1f1c4099ac65a8f336f1039b2b5042054b7aeac5ba","target":"graph","created_at":"2026-07-05T02:49:30Z","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/2105.05752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT) encoders. For example, we find that ASR encoders lack the global context representation, which is necessary for translation, whereas MT encoders are not designed to deal with long but locally attentive acoustic sequences. In this work, we propose a Stacked Acoustic-and-Textual Encoding (SATE) method for speech translation. Our encoder begins with processing th","authors_text":"Bojie Hu, Chen Xu, Jingbo Zhu, Qi Ju, Shen Huang, Tong Xiao, Yanyang Li, Yuhao Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T16:09:53Z","title":"Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05752","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:f7356621fd6cb0221e57df7c13913df002b8470b45fec18b6f831744d0316633","target":"record","created_at":"2026-07-05T02:49:30Z","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":"caeb52d602bf60e2e68a787bd895481474aebc0fe4eb4e3baa1ddad084f4753d","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T16:09:53Z","title_canon_sha256":"dd2315def832b0153fa00554e6b9f975770bc2e742d72eb7456aa3678afd22ee"},"schema_version":"1.0","source":{"id":"2105.05752","kind":"arxiv","version":2}},"canonical_sha256":"7db0e98fdcfd8fb1bc4a8f493a6eb1e0dc96506513dd30bf8c45853961deb0a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7db0e98fdcfd8fb1bc4a8f493a6eb1e0dc96506513dd30bf8c45853961deb0a3","first_computed_at":"2026-07-05T02:49:30.503532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:30.503532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nf6yt0CvN9qkiQnmZIneOHDDhyUXnFhySQq5IqPqJD943e/F759SMt7AOATcNjIxpHran46Px3TLOGuaZRvjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:30.503956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05752","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7356621fd6cb0221e57df7c13913df002b8470b45fec18b6f831744d0316633","sha256:19958a9ac1899bea32c48f1f1c4099ac65a8f336f1039b2b5042054b7aeac5ba"],"state_sha256":"d9122d4b1155e4828a9dac51dca60d330eee4cb4c60cc156d813b15e19cd3b2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q+fm1ON/6gL5i3tNn/ObNz5AkRnHGMdc5ZqEUa41NsWsrJ3ah4l2xcw3XNtP/E7FPsRkqBNgMU5HG1jPgh9ECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T14:05:17.515177Z","bundle_sha256":"adb8e15317b7632a58f7fc4f45eb1b509fad0db4daad8a25ff89f0c8c8da0ba7"}}