{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E7UUPQYMATE7K7RZZ5USSOF55M","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":"748f88de76301b45932b5c9439553aed83ea78bd0c9aec4ef135246f7a636a86","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T21:00:11Z","title_canon_sha256":"a8e703b2b9479f9d7e4324e9ad6b33494ed45338448bc11932c0f5d7d01b3763"},"schema_version":"1.0","source":{"id":"2508.13358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13358","created_at":"2026-07-05T11:55:46Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13358v1","created_at":"2026-07-05T11:55:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13358","created_at":"2026-07-05T11:55:46Z"},{"alias_kind":"pith_short_12","alias_value":"E7UUPQYMATE7","created_at":"2026-07-05T11:55:46Z"},{"alias_kind":"pith_short_16","alias_value":"E7UUPQYMATE7K7RZ","created_at":"2026-07-05T11:55:46Z"},{"alias_kind":"pith_short_8","alias_value":"E7UUPQYM","created_at":"2026-07-05T11:55:46Z"}],"graph_snapshots":[{"event_id":"sha256:adea66cf12be1ac1862add9202c60e0886964495d11677781d8480652fc7d143","target":"graph","created_at":"2026-07-05T11:55:46Z","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/2508.13358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on Recurrent Neural Network Transducers (RNN-T) can perform real-time transcription, achieving streaming translation in real-time remains a significant challenge. To address this issue, we propose a simultaneous translation approach that effectively balances translation quality and latency. We also investigate efficient integration of ASR and MT, leveraging linguistic ","authors_text":"Christian Fuegen, Frank Seide, Ju Lin, Niko Moritz, Ruiming Xie, Simone Merello, Zeeshan Ahmed, Zhe Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T21:00:11Z","title":"Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13358","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":"sha256:79996ba53934f6077048e0514f0d4bb84de5e62644d6782e71a728838f4c0ff4","target":"record","created_at":"2026-07-05T11:55:46Z","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":"748f88de76301b45932b5c9439553aed83ea78bd0c9aec4ef135246f7a636a86","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T21:00:11Z","title_canon_sha256":"a8e703b2b9479f9d7e4324e9ad6b33494ed45338448bc11932c0f5d7d01b3763"},"schema_version":"1.0","source":{"id":"2508.13358","kind":"arxiv","version":1}},"canonical_sha256":"27e947c30c04c9f57e39cf692938bdeb16bdb946554f3fa7c8da2e87b4c1adfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27e947c30c04c9f57e39cf692938bdeb16bdb946554f3fa7c8da2e87b4c1adfd","first_computed_at":"2026-07-05T11:55:46.900135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:46.900135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+0YmdRp3tZksSGyxkblSGxgDraqiw0AfEMxAsrj6BZKSvxvM+m/lbHaW4QeBA9c1VOHUYRY93REBTo27vWPrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:46.900617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79996ba53934f6077048e0514f0d4bb84de5e62644d6782e71a728838f4c0ff4","sha256:adea66cf12be1ac1862add9202c60e0886964495d11677781d8480652fc7d143"],"state_sha256":"26e7161a3252db24446c7d1c118b80633ece89364cd71e24b33fe555b609ed24"}