{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EHWEVUTTTYGVE2MMYPKEYP6HPJ","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":"2408134ec47836de4566f88601480fdf0594003da59b4b634e156557da34b387","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T02:04:38Z","title_canon_sha256":"9f650ad67c806d0e7883035df45a3e2a2ea33459699fa3fa8c2f848f9219307e"},"schema_version":"1.0","source":{"id":"2402.12654","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12654","created_at":"2026-07-05T08:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12654v3","created_at":"2026-07-05T08:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12654","created_at":"2026-07-05T08:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"EHWEVUTTTYGV","created_at":"2026-07-05T08:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"EHWEVUTTTYGVE2MM","created_at":"2026-07-05T08:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"EHWEVUTT","created_at":"2026-07-05T08:59:26Z"}],"graph_snapshots":[{"event_id":"sha256:f8c607567d771ccd8eda07a6219f6cb4236f02856f3967a308144ec94ee941cb","target":"graph","created_at":"2026-07-05T08:59:26Z","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/2402.12654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been an increasing interest in large speech models that can perform multiple tasks in a single model. Such models usually adopt an encoder-decoder or decoder-only architecture due to their popularity and good performance in many domains. However, autoregressive models can be slower during inference compared to non-autoregressive models and also have potential risks of hallucination. Though prior studies observed promising results of non-autoregressive models for certain tasks at small scales, it remains unclear if they can be scaled to speech-to-text generation in diverse languages a","authors_text":"Muhammad Shakeel, Shinji Watanabe, Yifan Peng, Yui Sudo","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T02:04:38Z","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12654","kind":"arxiv","version":3},"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:fc5c77a681b5a2b3411d43910164080047594e2a30c879547743c8e040c3ae25","target":"record","created_at":"2026-07-05T08:59:26Z","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":"2408134ec47836de4566f88601480fdf0594003da59b4b634e156557da34b387","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T02:04:38Z","title_canon_sha256":"9f650ad67c806d0e7883035df45a3e2a2ea33459699fa3fa8c2f848f9219307e"},"schema_version":"1.0","source":{"id":"2402.12654","kind":"arxiv","version":3}},"canonical_sha256":"21ec4ad2739e0d52698cc3d44c3fc77a70fddc6a89d591e07b3d86287e1ed572","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21ec4ad2739e0d52698cc3d44c3fc77a70fddc6a89d591e07b3d86287e1ed572","first_computed_at":"2026-07-05T08:59:26.248376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:26.248376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WwZaZwCpBCkJrjs0barQc0O7Lwh2sL+kSuulPrWQAXOyL5F6Bso38WBcLpCs5r0LZp8YnLwFhc3JZAmfuLy2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:26.248916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12654","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc5c77a681b5a2b3411d43910164080047594e2a30c879547743c8e040c3ae25","sha256:f8c607567d771ccd8eda07a6219f6cb4236f02856f3967a308144ec94ee941cb"],"state_sha256":"949c2bc0a17025c0347f1b1ef1df1763a65e2ffc6007c1e9607f72086935cf74"}