{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ARAEYOPYGHAQP4FWUYMKVFWGP3","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":"b3943bf4d00bfa70030b0a2345da19be67c118c649791fcbcb932ab7b7ef1f9e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T02:24:44Z","title_canon_sha256":"8b8aba6c2082a11d8ef657be6cf319f757d145de72b4805d768f24cf6ec76314"},"schema_version":"1.0","source":{"id":"2506.10299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10299","created_at":"2026-07-05T11:20:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10299v1","created_at":"2026-07-05T11:20:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10299","created_at":"2026-07-05T11:20:21Z"},{"alias_kind":"pith_short_12","alias_value":"ARAEYOPYGHAQ","created_at":"2026-07-05T11:20:21Z"},{"alias_kind":"pith_short_16","alias_value":"ARAEYOPYGHAQP4FW","created_at":"2026-07-05T11:20:21Z"},{"alias_kind":"pith_short_8","alias_value":"ARAEYOPY","created_at":"2026-07-05T11:20:21Z"}],"graph_snapshots":[{"event_id":"sha256:6cb4265f659a427f4ccfcdb096831b1287b1aa67880db8b8ecd7127db8eab399","target":"graph","created_at":"2026-07-05T11:20:21Z","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/2506.10299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-to-speech translation (S2ST) has been advanced with large language models (LLMs), which are fine-tuned on discrete speech units. In such approaches, modality adaptation from text to speech has been an issue. LLMs are trained on text-only data, which presents challenges to adapt them to speech modality with limited speech-to-speech data. To address the training difficulty, we propose scheduled interleaved speech--text training in this study. We use interleaved speech--text units instead of speech units during training, where aligned text tokens are interleaved at the word level. We gradu","authors_text":"Emiru Tsunoo, Hassan Shahmohammadi, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi, Yuki Ito","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T02:24:44Z","title":"Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10299","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:dc19bb2feb8ed92b73852d661acb0ef7345d63c40f260b83216d0faa20246918","target":"record","created_at":"2026-07-05T11:20:21Z","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":"b3943bf4d00bfa70030b0a2345da19be67c118c649791fcbcb932ab7b7ef1f9e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T02:24:44Z","title_canon_sha256":"8b8aba6c2082a11d8ef657be6cf319f757d145de72b4805d768f24cf6ec76314"},"schema_version":"1.0","source":{"id":"2506.10299","kind":"arxiv","version":1}},"canonical_sha256":"04404c39f831c107f0b6a618aa96c67ec54abd3dc39143d7bd02a65d4855959e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04404c39f831c107f0b6a618aa96c67ec54abd3dc39143d7bd02a65d4855959e","first_computed_at":"2026-07-05T11:20:21.106424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:21.106424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5MjN0dP49IpaaGvDjh7NzBDE2zxkvyYp3uUdi/c4kiiO0dY9EQwOHsR/De4oeC3i1TpN6mE+1coUN1vbl2iDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:21.107016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc19bb2feb8ed92b73852d661acb0ef7345d63c40f260b83216d0faa20246918","sha256:6cb4265f659a427f4ccfcdb096831b1287b1aa67880db8b8ecd7127db8eab399"],"state_sha256":"6d627e8bfa73bf81d9886e9fc6d03101ba8670d1a3cecea6ed2306c14064e18c"}