{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BNPUQQLWBDHYRSY4FPJ7JCHFVC","short_pith_number":"pith:BNPUQQLW","schema_version":"1.0","canonical_sha256":"0b5f48417608cf88cb1c2bd3f488e5a8b0c642e028be4abf27d3310974cd6739","source":{"kind":"arxiv","id":"2602.11072","version":2},"attestation_state":"computed","paper":{"title":"Simultaneous Speech-to-Speech Translation Without Aligned Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexandre D\\'efossez, Neil Zeghidour, Romain Fabre, Tom Labiausse, Yannick Est\\`eve","submitted_at":"2026-02-11T17:41:01Z","abstract_excerpt":"Simultaneous speech translation requires translating source speech into a target language in real-time while handling non-monotonic word dependencies. Traditional approaches rely on supervised training with word-level aligned data, which is difficult to collect at scale and thus depends on synthetic alignments using language-specific heuristics that are suboptimal. We propose Hibiki-Zero, which eliminates the need for word-level alignments entirely. This fundamentally simplifies the training pipeline and enables seamless scaling to diverse languages with varying grammatical structures, removin"},"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":"2602.11072","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-11T17:41:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"7a8097a3d0218535ab9863d492831e6bdd838f0a84969b7705720a248b16f576","abstract_canon_sha256":"e03a57822e322a1fde553414833bb3d06af02b518a9d6039a502e2edc6f33570"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:21.896282Z","signature_b64":"rSmztSv2ZtU+mV5NyRfXFjTXLk/QUKsOrQHlZ2pqZ6IuNsTTeJPkNZf03dXUQQPUC+l/eZsKLnOkeWUQGyHhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b5f48417608cf88cb1c2bd3f488e5a8b0c642e028be4abf27d3310974cd6739","last_reissued_at":"2026-07-23T01:24:21.895265Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:21.895265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simultaneous Speech-to-Speech Translation Without Aligned Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexandre D\\'efossez, Neil Zeghidour, Romain Fabre, Tom Labiausse, Yannick Est\\`eve","submitted_at":"2026-02-11T17:41:01Z","abstract_excerpt":"Simultaneous speech translation requires translating source speech into a target language in real-time while handling non-monotonic word dependencies. Traditional approaches rely on supervised training with word-level aligned data, which is difficult to collect at scale and thus depends on synthetic alignments using language-specific heuristics that are suboptimal. We propose Hibiki-Zero, which eliminates the need for word-level alignments entirely. This fundamentally simplifies the training pipeline and enables seamless scaling to diverse languages with varying grammatical structures, removin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11072","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/2602.11072/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":"2602.11072","created_at":"2026-07-23T01:24:21.895757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11072v2","created_at":"2026-07-23T01:24:21.895757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11072","created_at":"2026-07-23T01:24:21.895757+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNPUQQLWBDHY","created_at":"2026-07-23T01:24:21.895757+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNPUQQLWBDHYRSY4","created_at":"2026-07-23T01:24:21.895757+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNPUQQLW","created_at":"2026-07-23T01:24:21.895757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.13121","citing_title":"NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09916","citing_title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC","json":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC.json","graph_json":"https://pith.science/api/pith-number/BNPUQQLWBDHYRSY4FPJ7JCHFVC/graph.json","events_json":"https://pith.science/api/pith-number/BNPUQQLWBDHYRSY4FPJ7JCHFVC/events.json","paper":"https://pith.science/paper/BNPUQQLW"},"agent_actions":{"view_html":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC","download_json":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC.json","view_paper":"https://pith.science/paper/BNPUQQLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11072&json=true","fetch_graph":"https://pith.science/api/pith-number/BNPUQQLWBDHYRSY4FPJ7JCHFVC/graph.json","fetch_events":"https://pith.science/api/pith-number/BNPUQQLWBDHYRSY4FPJ7JCHFVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC/action/storage_attestation","attest_author":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC/action/author_attestation","sign_citation":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC/action/citation_signature","submit_replication":"https://pith.science/pith/BNPUQQLWBDHYRSY4FPJ7JCHFVC/action/replication_record"}},"created_at":"2026-07-23T01:24:21.895757+00:00","updated_at":"2026-07-23T01:24:21.895757+00:00"}