{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHWEVUTTTYGVE2MMYPKEYP6HPJ","short_pith_number":"pith:EHWEVUTT","schema_version":"1.0","canonical_sha256":"21ec4ad2739e0d52698cc3d44c3fc77a70fddc6a89d591e07b3d86287e1ed572","source":{"kind":"arxiv","id":"2402.12654","version":3},"attestation_state":"computed","paper":{"title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Muhammad Shakeel, Shinji Watanabe, Yifan Peng, Yui Sudo","submitted_at":"2024-02-20T02:04:38Z","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"},"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":"2402.12654","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T02:04:38Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9f650ad67c806d0e7883035df45a3e2a2ea33459699fa3fa8c2f848f9219307e","abstract_canon_sha256":"2408134ec47836de4566f88601480fdf0594003da59b4b634e156557da34b387"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:26.248916Z","signature_b64":"WwZaZwCpBCkJrjs0barQc0O7Lwh2sL+kSuulPrWQAXOyL5F6Bso38WBcLpCs5r0LZp8YnLwFhc3JZAmfuLy2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21ec4ad2739e0d52698cc3d44c3fc77a70fddc6a89d591e07b3d86287e1ed572","last_reissued_at":"2026-07-05T08:59:26.248376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:26.248376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Muhammad Shakeel, Shinji Watanabe, Yifan Peng, Yui Sudo","submitted_at":"2024-02-20T02:04:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12654","kind":"arxiv","version":3},"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/2402.12654/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":"2402.12654","created_at":"2026-07-05T08:59:26.248450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12654v3","created_at":"2026-07-05T08:59:26.248450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12654","created_at":"2026-07-05T08:59:26.248450+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHWEVUTTTYGV","created_at":"2026-07-05T08:59:26.248450+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHWEVUTTTYGVE2MM","created_at":"2026-07-05T08:59:26.248450+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHWEVUTT","created_at":"2026-07-05T08:59:26.248450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10736","citing_title":"BlasBench: An Open Benchmark for Irish Speech Recognition","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ","json":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ.json","graph_json":"https://pith.science/api/pith-number/EHWEVUTTTYGVE2MMYPKEYP6HPJ/graph.json","events_json":"https://pith.science/api/pith-number/EHWEVUTTTYGVE2MMYPKEYP6HPJ/events.json","paper":"https://pith.science/paper/EHWEVUTT"},"agent_actions":{"view_html":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ","download_json":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ.json","view_paper":"https://pith.science/paper/EHWEVUTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12654&json=true","fetch_graph":"https://pith.science/api/pith-number/EHWEVUTTTYGVE2MMYPKEYP6HPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EHWEVUTTTYGVE2MMYPKEYP6HPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ/action/storage_attestation","attest_author":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ/action/author_attestation","sign_citation":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ/action/citation_signature","submit_replication":"https://pith.science/pith/EHWEVUTTTYGVE2MMYPKEYP6HPJ/action/replication_record"}},"created_at":"2026-07-05T08:59:26.248450+00:00","updated_at":"2026-07-05T08:59:26.248450+00:00"}