{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GVEVEDLSL2R72OT4QETU22U3PG","short_pith_number":"pith:GVEVEDLS","schema_version":"1.0","canonical_sha256":"3549520d725ea3fd3a7c81274d6a9b79b1b1a3815599e050c51440438cc5802e","source":{"kind":"arxiv","id":"2607.13158","version":1},"attestation_state":"computed","paper":{"title":"Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdel Heba, Hoda Gholami, Jian Xue, Jinyu Li, Junkun Chen, Ming Tang, Ruchao Fan","submitted_at":"2026-07-14T18:07:18Z","abstract_excerpt":"Simultaneous speech translation (SimulST) requires incremental translation under strict latency constraints, yet remains challenging for decoder-only LLM systems due to limited context and cross-lingual reordering. Recent approaches often introduce architectural changes or explicit read/write policies to control output timing, which can be brittle in conversational speech where segmentation boundaries are ambiguous. We present a simple data-driven alternative: fixed-length chunks for cumulative streaming decoding with a rewind-based committed prefix, and teacher-labeled prefix-to-prefix (P2P) "},"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":"2607.13158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T18:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"2bbf0d96119652999d59ab4060c97e04b32f36a3205ea7512de6451eabe67bbd","abstract_canon_sha256":"c08ec85c10fab283ee9374b9e36c8b124cea6f733c7f66803bf916f6df9c8ced"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:00.520198Z","signature_b64":"QqM3SlD8+BxNQ1yXsxHb7XOSrKlF+5p9xhbrJLBAdb1UzvsrSSGPM2lK0gIjBAAYU+54V07b1xCu+Rvc8gzKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3549520d725ea3fd3a7c81274d6a9b79b1b1a3815599e050c51440438cc5802e","last_reissued_at":"2026-07-16T00:22:00.519335Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:00.519335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdel Heba, Hoda Gholami, Jian Xue, Jinyu Li, Junkun Chen, Ming Tang, Ruchao Fan","submitted_at":"2026-07-14T18:07:18Z","abstract_excerpt":"Simultaneous speech translation (SimulST) requires incremental translation under strict latency constraints, yet remains challenging for decoder-only LLM systems due to limited context and cross-lingual reordering. Recent approaches often introduce architectural changes or explicit read/write policies to control output timing, which can be brittle in conversational speech where segmentation boundaries are ambiguous. We present a simple data-driven alternative: fixed-length chunks for cumulative streaming decoding with a rewind-based committed prefix, and teacher-labeled prefix-to-prefix (P2P) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13158","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/2607.13158/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":"2607.13158","created_at":"2026-07-16T00:22:00.519742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13158v1","created_at":"2026-07-16T00:22:00.519742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13158","created_at":"2026-07-16T00:22:00.519742+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVEVEDLSL2R7","created_at":"2026-07-16T00:22:00.519742+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVEVEDLSL2R72OT4","created_at":"2026-07-16T00:22:00.519742+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVEVEDLS","created_at":"2026-07-16T00:22:00.519742+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/GVEVEDLSL2R72OT4QETU22U3PG","json":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG.json","graph_json":"https://pith.science/api/pith-number/GVEVEDLSL2R72OT4QETU22U3PG/graph.json","events_json":"https://pith.science/api/pith-number/GVEVEDLSL2R72OT4QETU22U3PG/events.json","paper":"https://pith.science/paper/GVEVEDLS"},"agent_actions":{"view_html":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG","download_json":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG.json","view_paper":"https://pith.science/paper/GVEVEDLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13158&json=true","fetch_graph":"https://pith.science/api/pith-number/GVEVEDLSL2R72OT4QETU22U3PG/graph.json","fetch_events":"https://pith.science/api/pith-number/GVEVEDLSL2R72OT4QETU22U3PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG/action/storage_attestation","attest_author":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG/action/author_attestation","sign_citation":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG/action/citation_signature","submit_replication":"https://pith.science/pith/GVEVEDLSL2R72OT4QETU22U3PG/action/replication_record"}},"created_at":"2026-07-16T00:22:00.519742+00:00","updated_at":"2026-07-16T00:22:00.519742+00:00"}