{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZPK4HX4OEYXT3JQOACPMKEIJX3","short_pith_number":"pith:ZPK4HX4O","canonical_record":{"source":{"id":"2606.12911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T05:09:59Z","cross_cats_sorted":[],"title_canon_sha256":"81567fec6216d81da4042cd0ba3d07b740a227a3e75bba6b58dda850b8cb5d7a","abstract_canon_sha256":"23b9e64d0105638a8d4f0d6fba4aab8ca4e5d3bfe74432564dae2312add07a12"},"schema_version":"1.0"},"canonical_sha256":"cbd5c3df8e262f3da60e009ec51109bec9259f1ded294eb6d3933e8408802050","source":{"kind":"arxiv","id":"2606.12911","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12911","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12911v1","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12911","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZPK4HX4OEYXT","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZPK4HX4OEYXT3JQO","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZPK4HX4O","created_at":"2026-06-12T01:09:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZPK4HX4OEYXT3JQOACPMKEIJX3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.12911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T05:09:59Z","cross_cats_sorted":[],"title_canon_sha256":"81567fec6216d81da4042cd0ba3d07b740a227a3e75bba6b58dda850b8cb5d7a","abstract_canon_sha256":"23b9e64d0105638a8d4f0d6fba4aab8ca4e5d3bfe74432564dae2312add07a12"},"schema_version":"1.0"},"canonical_sha256":"cbd5c3df8e262f3da60e009ec51109bec9259f1ded294eb6d3933e8408802050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:34.201181Z","signature_b64":"WjRzpZhPNtKOKHRbbNRAeN05cKgDto7LTGJFPKyt64/yTIjZt8yw1g+wP5uIj5bBemxHvgLQNIO6+2uJcyHZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd5c3df8e262f3da60e009ec51109bec9259f1ded294eb6d3933e8408802050","last_reissued_at":"2026-06-12T01:09:34.200587Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:34.200587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.12911","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":"2026-06-12T01:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRcQZrFVxPMVRSNIsfs7v+D37D5ifG8wDH8sGoXamcWm+tfnj+mKT+8AoW9u7dqsCtKLFG7Y6Nr0Rv36oyaAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T09:41:14.737758Z"},"content_sha256":"3695868a639954bf6b7f470ce561e68d1b102215860d0cfe7d173faadd04ca90","schema_version":"1.0","event_id":"sha256:3695868a639954bf6b7f470ce561e68d1b102215860d0cfe7d173faadd04ca90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZPK4HX4OEYXT3JQOACPMKEIJX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dung D. Le, Giang Son Nguyen, Hieu Minh Truong, Nhu Vo, Tung X. Nguyen, Wray Buntine","submitted_at":"2026-06-11T05:09:59Z","abstract_excerpt":"Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic categorization of ASR errors for Vietnamese ST, classifying substitution errors by phonetic cause and quantifying their impact on downstream Neural Machine Translation (NMT) performance using Linear Mixed-Effects Modelling. We confirm that most ASR substitution errors arise from phonetic confusions rather than random noise, and that these phonetic errors significantly degrade ST quality. Motivated by this finding, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12911","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/2606.12911/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":"2026-06-12T01:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QhFA2sI/sufuct1V+LH/7hcn0DPEs7FhN5uuA4tVuaRQiiq64tIUYbKozHPGeVMNcGQDxFRZDL7ERIB8qJrBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T09:41:14.738124Z"},"content_sha256":"ee0898033908a5e39f105f1e4db656ea2dd2101a14dc63f4b3dda62989c5dfb3","schema_version":"1.0","event_id":"sha256:ee0898033908a5e39f105f1e4db656ea2dd2101a14dc63f4b3dda62989c5dfb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3/bundle.json","state_url":"https://pith.science/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3/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":"2026-07-03T09:41:14Z","links":{"resolver":"https://pith.science/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3","bundle":"https://pith.science/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3/bundle.json","state":"https://pith.science/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPK4HX4OEYXT3JQOACPMKEIJX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZPK4HX4OEYXT3JQOACPMKEIJX3","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":"23b9e64d0105638a8d4f0d6fba4aab8ca4e5d3bfe74432564dae2312add07a12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T05:09:59Z","title_canon_sha256":"81567fec6216d81da4042cd0ba3d07b740a227a3e75bba6b58dda850b8cb5d7a"},"schema_version":"1.0","source":{"id":"2606.12911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12911","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12911v1","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12911","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZPK4HX4OEYXT","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZPK4HX4OEYXT3JQO","created_at":"2026-06-12T01:09:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZPK4HX4O","created_at":"2026-06-12T01:09:34Z"}],"graph_snapshots":[{"event_id":"sha256:ee0898033908a5e39f105f1e4db656ea2dd2101a14dc63f4b3dda62989c5dfb3","target":"graph","created_at":"2026-06-12T01:09:34Z","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/2606.12911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic categorization of ASR errors for Vietnamese ST, classifying substitution errors by phonetic cause and quantifying their impact on downstream Neural Machine Translation (NMT) performance using Linear Mixed-Effects Modelling. We confirm that most ASR substitution errors arise from phonetic confusions rather than random noise, and that these phonetic errors significantly degrade ST quality. Motivated by this finding, we propo","authors_text":"Dung D. Le, Giang Son Nguyen, Hieu Minh Truong, Nhu Vo, Tung X. Nguyen, Wray Buntine","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T05:09:59Z","title":"PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12911","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":"sha256:3695868a639954bf6b7f470ce561e68d1b102215860d0cfe7d173faadd04ca90","target":"record","created_at":"2026-06-12T01:09:34Z","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":"23b9e64d0105638a8d4f0d6fba4aab8ca4e5d3bfe74432564dae2312add07a12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T05:09:59Z","title_canon_sha256":"81567fec6216d81da4042cd0ba3d07b740a227a3e75bba6b58dda850b8cb5d7a"},"schema_version":"1.0","source":{"id":"2606.12911","kind":"arxiv","version":1}},"canonical_sha256":"cbd5c3df8e262f3da60e009ec51109bec9259f1ded294eb6d3933e8408802050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbd5c3df8e262f3da60e009ec51109bec9259f1ded294eb6d3933e8408802050","first_computed_at":"2026-06-12T01:09:34.200587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:34.200587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WjRzpZhPNtKOKHRbbNRAeN05cKgDto7LTGJFPKyt64/yTIjZt8yw1g+wP5uIj5bBemxHvgLQNIO6+2uJcyHZAQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:34.201181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3695868a639954bf6b7f470ce561e68d1b102215860d0cfe7d173faadd04ca90","sha256:ee0898033908a5e39f105f1e4db656ea2dd2101a14dc63f4b3dda62989c5dfb3"],"state_sha256":"16ad2ff7668f3bfb84f8d37697ec0580dae0e4d5bdae56e83799f41e4e8bf2d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3nYcQGxM8wqnCh3V4pcsCSJ1znBvHkwLwKQGNCEIejo3dMVju9smR+7rnGsej6V6dXbXtiVkFo7kLpb9hmImBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T09:41:14.740066Z","bundle_sha256":"f2ed5ad200d961aa18602b8c4616d73be12a13adfb51efe2c610bb679063d2c6"}}