{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZCEVE67XNCONE6U2GICOFADN7F","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":"aaad2c6ba3278eb8f5e085efadef02fab69b42b674406489c83be0988e408102","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T12:26:39Z","title_canon_sha256":"e937c9dd9135fa0f9176b3c7abf41e1a4e3738559dab681f19bef311625808c1"},"schema_version":"1.0","source":{"id":"2608.02138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02138","created_at":"2026-08-04T02:11:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02138v1","created_at":"2026-08-04T02:11:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02138","created_at":"2026-08-04T02:11:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZCEVE67XNCON","created_at":"2026-08-04T02:11:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZCEVE67XNCONE6U2","created_at":"2026-08-04T02:11:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZCEVE67X","created_at":"2026-08-04T02:11:05Z"}],"graph_snapshots":[{"event_id":"sha256:dab4ed0081d485afd31a449f0b204b4eb6cccaac1c177d89018938117df9154f","target":"graph","created_at":"2026-08-04T02:11:05Z","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/2608.02138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current speech translation systems, including SpeechLLMs, are trained on cleaned text and tend to strip disfluencies like filled pauses and false starts rather than translate them. We show this comes at a cost: disfluencies carry meaning that gets lost when speech is cleaned up. To study this systematically, we introduce Uh-Mazing, a benchmark of human-translated, disfluency-annotated Switchboard speech covering English into eight target languages. Across these languages and several architectures, we find that false starts and self-repairs, not filled pauses or discourse markers, drive most of","authors_text":"Alexander Waibel, Fabian Retkowski, James Caverlee, Jan Niehues, Maike Z\\\"ufle, Maria Teleki, Oliver Grabner, Vil\\'em Zouhar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T12:26:39Z","title":"The Role of Disfluencies in Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02138","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:be6000b9183db4848a6468a7d4eb05666206917f7efdcf45ec973d05be3fca0d","target":"record","created_at":"2026-08-04T02:11:05Z","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":"aaad2c6ba3278eb8f5e085efadef02fab69b42b674406489c83be0988e408102","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T12:26:39Z","title_canon_sha256":"e937c9dd9135fa0f9176b3c7abf41e1a4e3738559dab681f19bef311625808c1"},"schema_version":"1.0","source":{"id":"2608.02138","kind":"arxiv","version":1}},"canonical_sha256":"c889527bf7689cd27a9a3204e2806df96b7eb1fd9339956ebff7fde2bfdc99a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c889527bf7689cd27a9a3204e2806df96b7eb1fd9339956ebff7fde2bfdc99a6","first_computed_at":"2026-08-04T02:11:05.379003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:11:05.379003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2LDoDzLbcWZJBl8G2jrhJMYjCdYnVYFzToKWnOLJfOqxV4PAAG65u4TeEey3ED5YEsfW5ZomKzXFNckaH9nmCg==","signature_status":"signed_v1","signed_at":"2026-08-04T02:11:05.380694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be6000b9183db4848a6468a7d4eb05666206917f7efdcf45ec973d05be3fca0d","sha256:dab4ed0081d485afd31a449f0b204b4eb6cccaac1c177d89018938117df9154f"],"state_sha256":"b6f6772a8d41c2f31d438e4b00e41dd6eb1e182240236e6e2fe78c0ccc0ef561"}