{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z5FEAEY7WCD32KOZ32I57IGZ6X","short_pith_number":"pith:Z5FEAEY7","schema_version":"1.0","canonical_sha256":"cf4a40131fb087bd29d9de91dfa0d9f5c96927c0fa6d4f6de83bb27ca8db31e4","source":{"kind":"arxiv","id":"2606.10368","version":1},"attestation_state":"computed","paper":{"title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Chenghan Lin, Chenrui Cui, Chunyu Qiang, Guochen Yu, Jianwu Dang, Longbiao Wang, Tianrui Wang, Xie Chen, Xingyu Ma, Xuanchen Li, Yuheng Lu, Yu Jiang, Zikang Huang, Ziyang Ma","submitted_at":"2026-06-09T03:27:30Z","abstract_excerpt":"Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens. In contrast, continuous-target language modelling performs generation in a continuous space, yet its potential for S2T remains unexplored. To bridge this gap, we propose ELF-S2T, an audio-conditioned continuous-target generative model for S2T. Built upon the pre-trained Embedded Language Flows (ELF) backbone, ELF-S2T processes speech via a frozen Whisper encoder and a single linear projector, prepending the resulting audio condition to the noisy text latent for in-context, flow-ma"},"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":"2606.10368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:27:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a53d0b74c66e49ab6775d192d77af9c6bddf4dab61ba855b77abd73e21d599a8","abstract_canon_sha256":"a61f2e4bec0f6474d4ed65d2b6fdb0baa8da1614b02c2d7494f48264b879b416"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:14.182250Z","signature_b64":"98k1H74Qk/W8HgqwC++VtPAduogagPS6PWvuOa24ntlsuqQ1/TPH6K6dv1+4Nun5lB0MlDL8FCcGHiP29ZJCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf4a40131fb087bd29d9de91dfa0d9f5c96927c0fa6d4f6de83bb27ca8db31e4","last_reissued_at":"2026-06-10T01:10:14.181329Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:14.181329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Chenghan Lin, Chenrui Cui, Chunyu Qiang, Guochen Yu, Jianwu Dang, Longbiao Wang, Tianrui Wang, Xie Chen, Xingyu Ma, Xuanchen Li, Yuheng Lu, Yu Jiang, Zikang Huang, Ziyang Ma","submitted_at":"2026-06-09T03:27:30Z","abstract_excerpt":"Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens. In contrast, continuous-target language modelling performs generation in a continuous space, yet its potential for S2T remains unexplored. To bridge this gap, we propose ELF-S2T, an audio-conditioned continuous-target generative model for S2T. Built upon the pre-trained Embedded Language Flows (ELF) backbone, ELF-S2T processes speech via a frozen Whisper encoder and a single linear projector, prepending the resulting audio condition to the noisy text latent for in-context, flow-ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10368","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/2606.10368/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":"2606.10368","created_at":"2026-06-10T01:10:14.181497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10368v1","created_at":"2026-06-10T01:10:14.181497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10368","created_at":"2026-06-10T01:10:14.181497+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5FEAEY7WCD3","created_at":"2026-06-10T01:10:14.181497+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5FEAEY7WCD32KOZ","created_at":"2026-06-10T01:10:14.181497+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5FEAEY7","created_at":"2026-06-10T01:10:14.181497+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/Z5FEAEY7WCD32KOZ32I57IGZ6X","json":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X.json","graph_json":"https://pith.science/api/pith-number/Z5FEAEY7WCD32KOZ32I57IGZ6X/graph.json","events_json":"https://pith.science/api/pith-number/Z5FEAEY7WCD32KOZ32I57IGZ6X/events.json","paper":"https://pith.science/paper/Z5FEAEY7"},"agent_actions":{"view_html":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X","download_json":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X.json","view_paper":"https://pith.science/paper/Z5FEAEY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10368&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5FEAEY7WCD32KOZ32I57IGZ6X/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5FEAEY7WCD32KOZ32I57IGZ6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X/action/storage_attestation","attest_author":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X/action/author_attestation","sign_citation":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X/action/citation_signature","submit_replication":"https://pith.science/pith/Z5FEAEY7WCD32KOZ32I57IGZ6X/action/replication_record"}},"created_at":"2026-06-10T01:10:14.181497+00:00","updated_at":"2026-06-10T01:10:14.181497+00:00"}