{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XEMMKWKJYKE6U6MLWP2ZDN2PKP","short_pith_number":"pith:XEMMKWKJ","schema_version":"1.0","canonical_sha256":"b918c55949c289ea798bb3f591b74f53ded7ca7ce7ab76d7b353ece0b8809bc3","source":{"kind":"arxiv","id":"2606.06047","version":1},"attestation_state":"computed","paper":{"title":"Automatic Labelling of Speech Translation Errors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominik Mach\\'a\\v{c}ek, Maike Z\\\"ufle, Ondrej Klejch","submitted_at":"2026-06-04T11:42:37Z","abstract_excerpt":"Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no established methodology for evaluating confidence and quality estimation of speech translations. To initiate progress in this direction, we propose Speech Translation Error Labelling (STEL). We create an annotation protocol, a small authentic end-to-end evaluation dataset, and we analyse how existing text-only and speech-processing systems perform the STEL task. Our results show that text-only XCOMET and multimodal LLM Qwen2.5-Omni are able to per"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.06047","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T11:42:37Z","cross_cats_sorted":[],"title_canon_sha256":"6f6f735e6d8159ce43a8b4fdb29cfc5da667ee5f7db54908235d8a9cf42ee534","abstract_canon_sha256":"87baa3ef429ec082af0e63bf61e6331192a8c55ad4a163b93a990a09db781e72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:31.492173Z","signature_b64":"lJBQhN8gc+UPsx3ofCCDK085LI6h53dNs8vy1qHZ8LZl9udEln0geX4f8+6fu4mHd30IQpYHxu0Tmyrt04DRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b918c55949c289ea798bb3f591b74f53ded7ca7ce7ab76d7b353ece0b8809bc3","last_reissued_at":"2026-06-05T01:15:31.491789Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:31.491789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Labelling of Speech Translation Errors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominik Mach\\'a\\v{c}ek, Maike Z\\\"ufle, Ondrej Klejch","submitted_at":"2026-06-04T11:42:37Z","abstract_excerpt":"Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no established methodology for evaluating confidence and quality estimation of speech translations. To initiate progress in this direction, we propose Speech Translation Error Labelling (STEL). We create an annotation protocol, a small authentic end-to-end evaluation dataset, and we analyse how existing text-only and speech-processing systems perform the STEL task. Our results show that text-only XCOMET and multimodal LLM Qwen2.5-Omni are able to per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06047","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/2606.06047/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.06047","created_at":"2026-06-05T01:15:31.491853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06047v1","created_at":"2026-06-05T01:15:31.491853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06047","created_at":"2026-06-05T01:15:31.491853+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEMMKWKJYKE6","created_at":"2026-06-05T01:15:31.491853+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEMMKWKJYKE6U6ML","created_at":"2026-06-05T01:15:31.491853+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEMMKWKJ","created_at":"2026-06-05T01:15:31.491853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP","json":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP.json","graph_json":"https://pith.science/api/pith-number/XEMMKWKJYKE6U6MLWP2ZDN2PKP/graph.json","events_json":"https://pith.science/api/pith-number/XEMMKWKJYKE6U6MLWP2ZDN2PKP/events.json","paper":"https://pith.science/paper/XEMMKWKJ"},"agent_actions":{"view_html":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP","download_json":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP.json","view_paper":"https://pith.science/paper/XEMMKWKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06047&json=true","fetch_graph":"https://pith.science/api/pith-number/XEMMKWKJYKE6U6MLWP2ZDN2PKP/graph.json","fetch_events":"https://pith.science/api/pith-number/XEMMKWKJYKE6U6MLWP2ZDN2PKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP/action/storage_attestation","attest_author":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP/action/author_attestation","sign_citation":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP/action/citation_signature","submit_replication":"https://pith.science/pith/XEMMKWKJYKE6U6MLWP2ZDN2PKP/action/replication_record"}},"created_at":"2026-06-05T01:15:31.491853+00:00","updated_at":"2026-06-05T01:15:31.491853+00:00"}