{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L5QFEJGYRHMLQGFRNA7TZQ5W2C","short_pith_number":"pith:L5QFEJGY","schema_version":"1.0","canonical_sha256":"5f605224d889d8b818b1683f3cc3b6d0b93b1b63fb8e849717d46b7b494628bb","source":{"kind":"arxiv","id":"2503.02969","version":2},"attestation_state":"computed","paper":{"title":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Li, Siqi Ouyang, Xi Xu","submitted_at":"2025-03-04T19:51:29Z","abstract_excerpt":"Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead, can be balanced. Most prior works assume pre-segmented speech, limiting their real-world applicability. In this paper, we propose InfiniSST, a novel approach that formulates SST as a multi-turn dialogue task, enabling seamless translation of unbounded speech. We construct translation trajectories and robust segments from MuST-C with multi-latency augmentation "},"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":"2503.02969","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T19:51:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3621ee25ac83c76e5fedd5a449481033814ec4a7edbc5502eb41bf7113d7a5b4","abstract_canon_sha256":"1513234b6467705dc730e752396649491c5d2605449923c359713d8b1ba01b83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:43.751510Z","signature_b64":"hxFhYiRlroi2WJfyz44FCaWc0YDuc9c5hJ2fx3UNLjntuIMicIdk/rm2a03ctpKcOusC0jW18VUq5GLbqJ14CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f605224d889d8b818b1683f3cc3b6d0b93b1b63fb8e849717d46b7b494628bb","last_reissued_at":"2026-07-05T11:21:43.751000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:43.751000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Li, Siqi Ouyang, Xi Xu","submitted_at":"2025-03-04T19:51:29Z","abstract_excerpt":"Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead, can be balanced. Most prior works assume pre-segmented speech, limiting their real-world applicability. In this paper, we propose InfiniSST, a novel approach that formulates SST as a multi-turn dialogue task, enabling seamless translation of unbounded speech. We construct translation trajectories and robust segments from MuST-C with multi-latency augmentation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02969","kind":"arxiv","version":2},"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/2503.02969/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":"2503.02969","created_at":"2026-07-05T11:21:43.751062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02969v2","created_at":"2026-07-05T11:21:43.751062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02969","created_at":"2026-07-05T11:21:43.751062+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5QFEJGYRHML","created_at":"2026-07-05T11:21:43.751062+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5QFEJGYRHMLQGFR","created_at":"2026-07-05T11:21:43.751062+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5QFEJGY","created_at":"2026-07-05T11:21:43.751062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18828","citing_title":"MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation task","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C","json":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C.json","graph_json":"https://pith.science/api/pith-number/L5QFEJGYRHMLQGFRNA7TZQ5W2C/graph.json","events_json":"https://pith.science/api/pith-number/L5QFEJGYRHMLQGFRNA7TZQ5W2C/events.json","paper":"https://pith.science/paper/L5QFEJGY"},"agent_actions":{"view_html":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C","download_json":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C.json","view_paper":"https://pith.science/paper/L5QFEJGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02969&json=true","fetch_graph":"https://pith.science/api/pith-number/L5QFEJGYRHMLQGFRNA7TZQ5W2C/graph.json","fetch_events":"https://pith.science/api/pith-number/L5QFEJGYRHMLQGFRNA7TZQ5W2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C/action/storage_attestation","attest_author":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C/action/author_attestation","sign_citation":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C/action/citation_signature","submit_replication":"https://pith.science/pith/L5QFEJGYRHMLQGFRNA7TZQ5W2C/action/replication_record"}},"created_at":"2026-07-05T11:21:43.751062+00:00","updated_at":"2026-07-05T11:21:43.751062+00:00"}