{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XEHF4GWMLYTAU2LGEX55B3CMHM","short_pith_number":"pith:XEHF4GWM","canonical_record":{"source":{"id":"2306.11646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T16:14:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"60ee72e6d7d185b4a4a1f7585fea08734bd04f16e3c0667f5436e7e78c828482","abstract_canon_sha256":"7d7938063c668990b612c8174e1f11cc6c081ba2939a8f53df816e2db19d0148"},"schema_version":"1.0"},"canonical_sha256":"b90e5e1acc5e260a696625fbd0ec4c3b058bfc11e2df6d76cc6287803297e7d1","source":{"kind":"arxiv","id":"2306.11646","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11646","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11646v1","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11646","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"XEHF4GWMLYTA","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"XEHF4GWMLYTAU2LG","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"XEHF4GWM","created_at":"2026-07-05T06:22:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XEHF4GWMLYTAU2LGEX55B3CMHM","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T16:14:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"60ee72e6d7d185b4a4a1f7585fea08734bd04f16e3c0667f5436e7e78c828482","abstract_canon_sha256":"7d7938063c668990b612c8174e1f11cc6c081ba2939a8f53df816e2db19d0148"},"schema_version":"1.0"},"canonical_sha256":"b90e5e1acc5e260a696625fbd0ec4c3b058bfc11e2df6d76cc6287803297e7d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:22.006025Z","signature_b64":"jadMJk0TiRyma9eWTtPnyIxNPqXW7aovo+FE5Zg/bAzQhcrMyF2y7y2tSVWIZCVOr9wDm7CwK20MAJyG2A5NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b90e5e1acc5e260a696625fbd0ec4c3b058bfc11e2df6d76cc6287803297e7d1","last_reissued_at":"2026-07-05T06:22:22.005554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:22.005554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11646","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":"2026-07-05T06:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUzVt1npRXyxqobrpy3doJahduef/p3EJ1CAWt47zVhmF6io8BmuwlrHRRue48rawF2W6youhFMC6wol4VQpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:54:07.712466Z"},"content_sha256":"d4d7166b9ed597fdb9c367b719e0e2527e213c210d6f4f3ccc0418eb4d7866ae","schema_version":"1.0","event_id":"sha256:d4d7166b9ed597fdb9c367b719e0e2527e213c210d6f4f3ccc0418eb4d7866ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XEHF4GWMLYTAU2LGEX55B3CMHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recent Advances in Direct Speech-to-text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhao, Chen Xu, Jingbo Zhu, Mingxuan Wang, Qianqian Dong, Rong Ye, Tom Ko, Tong Xiao","submitted_at":"2023-06-20T16:14:27Z","abstract_excerpt":"Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech translation aiming to summarize the current state-of-the-art techniques. First, we categorize the existing research work into three directions based on the main challenges -- modeling burden, data scarcity, and application issues. To tackle the problem of modeling burden, two main structures have been proposed, encoder-decoder framework (Transformer and the variants) and multitask frameworks. For the challenge of dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11646","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/2306.11646/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":"2026-07-05T06:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zwS1XvQF4aCFQGIolfsTSn1vsIvE7eKl/OOKErGUXmemSh61yO7ZMzjReIvML7fB1OHOg95i7JVn1qhhruCKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:54:07.712831Z"},"content_sha256":"3fd7f4f46a9e47f7a9c1c4b099bbe1b5e8d18162bf444de3dcbb604505fc11c1","schema_version":"1.0","event_id":"sha256:3fd7f4f46a9e47f7a9c1c4b099bbe1b5e8d18162bf444de3dcbb604505fc11c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XEHF4GWMLYTAU2LGEX55B3CMHM/bundle.json","state_url":"https://pith.science/pith/XEHF4GWMLYTAU2LGEX55B3CMHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XEHF4GWMLYTAU2LGEX55B3CMHM/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":"2026-07-06T20:54:07Z","links":{"resolver":"https://pith.science/pith/XEHF4GWMLYTAU2LGEX55B3CMHM","bundle":"https://pith.science/pith/XEHF4GWMLYTAU2LGEX55B3CMHM/bundle.json","state":"https://pith.science/pith/XEHF4GWMLYTAU2LGEX55B3CMHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XEHF4GWMLYTAU2LGEX55B3CMHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XEHF4GWMLYTAU2LGEX55B3CMHM","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":"7d7938063c668990b612c8174e1f11cc6c081ba2939a8f53df816e2db19d0148","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T16:14:27Z","title_canon_sha256":"60ee72e6d7d185b4a4a1f7585fea08734bd04f16e3c0667f5436e7e78c828482"},"schema_version":"1.0","source":{"id":"2306.11646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11646","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11646v1","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11646","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"XEHF4GWMLYTA","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"XEHF4GWMLYTAU2LG","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"XEHF4GWM","created_at":"2026-07-05T06:22:22Z"}],"graph_snapshots":[{"event_id":"sha256:3fd7f4f46a9e47f7a9c1c4b099bbe1b5e8d18162bf444de3dcbb604505fc11c1","target":"graph","created_at":"2026-07-05T06:22:22Z","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/2306.11646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech translation aiming to summarize the current state-of-the-art techniques. First, we categorize the existing research work into three directions based on the main challenges -- modeling burden, data scarcity, and application issues. To tackle the problem of modeling burden, two main structures have been proposed, encoder-decoder framework (Transformer and the variants) and multitask frameworks. For the challenge of dat","authors_text":"Chengqi Zhao, Chen Xu, Jingbo Zhu, Mingxuan Wang, Qianqian Dong, Rong Ye, Tom Ko, Tong Xiao","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T16:14:27Z","title":"Recent Advances in Direct Speech-to-text Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11646","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:d4d7166b9ed597fdb9c367b719e0e2527e213c210d6f4f3ccc0418eb4d7866ae","target":"record","created_at":"2026-07-05T06:22:22Z","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":"7d7938063c668990b612c8174e1f11cc6c081ba2939a8f53df816e2db19d0148","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T16:14:27Z","title_canon_sha256":"60ee72e6d7d185b4a4a1f7585fea08734bd04f16e3c0667f5436e7e78c828482"},"schema_version":"1.0","source":{"id":"2306.11646","kind":"arxiv","version":1}},"canonical_sha256":"b90e5e1acc5e260a696625fbd0ec4c3b058bfc11e2df6d76cc6287803297e7d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b90e5e1acc5e260a696625fbd0ec4c3b058bfc11e2df6d76cc6287803297e7d1","first_computed_at":"2026-07-05T06:22:22.005554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:22.005554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jadMJk0TiRyma9eWTtPnyIxNPqXW7aovo+FE5Zg/bAzQhcrMyF2y7y2tSVWIZCVOr9wDm7CwK20MAJyG2A5NBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:22.006025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4d7166b9ed597fdb9c367b719e0e2527e213c210d6f4f3ccc0418eb4d7866ae","sha256:3fd7f4f46a9e47f7a9c1c4b099bbe1b5e8d18162bf444de3dcbb604505fc11c1"],"state_sha256":"06f47c717619916569c402112508ea671ae5c53396ae80eb0ab3ac56caa447ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9iAVbflZ0EZnaO08lKEQJJZUyJL9vB3rTxWS3gVXxn/kRUHu/iJ2fZEDQQ192wUKgXH6dvcI1oEPB1MZ60nDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:54:07.714764Z","bundle_sha256":"709d6a8e9cebdd2d184d8e3af9892552b0d40b96d988716bcd53b3f7616c7073"}}