{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z5FEAEY7WCD32KOZ32I57IGZ6X","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":"a61f2e4bec0f6474d4ed65d2b6fdb0baa8da1614b02c2d7494f48264b879b416","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:27:30Z","title_canon_sha256":"a53d0b74c66e49ab6775d192d77af9c6bddf4dab61ba855b77abd73e21d599a8"},"schema_version":"1.0","source":{"id":"2606.10368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10368","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10368v1","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10368","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z5FEAEY7WCD3","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"Z5FEAEY7WCD32KOZ","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"Z5FEAEY7","created_at":"2026-06-10T01:10:14Z"}],"graph_snapshots":[{"event_id":"sha256:83148bc281ea8b3462b3b5521cc0197a80a8b27f15fcb7ec77a452aa265e0cc9","target":"graph","created_at":"2026-06-10T01:10:14Z","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/2606.10368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:27:30Z","title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10368","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:f729f55ce0ce08a6bfc1cba67551ae97dea525e5b6cfdf487af606280af92b51","target":"record","created_at":"2026-06-10T01:10:14Z","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":"a61f2e4bec0f6474d4ed65d2b6fdb0baa8da1614b02c2d7494f48264b879b416","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:27:30Z","title_canon_sha256":"a53d0b74c66e49ab6775d192d77af9c6bddf4dab61ba855b77abd73e21d599a8"},"schema_version":"1.0","source":{"id":"2606.10368","kind":"arxiv","version":1}},"canonical_sha256":"cf4a40131fb087bd29d9de91dfa0d9f5c96927c0fa6d4f6de83bb27ca8db31e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf4a40131fb087bd29d9de91dfa0d9f5c96927c0fa6d4f6de83bb27ca8db31e4","first_computed_at":"2026-06-10T01:10:14.181329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:14.181329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"98k1H74Qk/W8HgqwC++VtPAduogagPS6PWvuOa24ntlsuqQ1/TPH6K6dv1+4Nun5lB0MlDL8FCcGHiP29ZJCCQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:14.182250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f729f55ce0ce08a6bfc1cba67551ae97dea525e5b6cfdf487af606280af92b51","sha256:83148bc281ea8b3462b3b5521cc0197a80a8b27f15fcb7ec77a452aa265e0cc9"],"state_sha256":"7ce0716427ff87caab2d3fbb10831f8f8b1d8f141434fd90f2dfe27504e1d7fd"}