{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OHOJAM7EM2LZL2WPPT4NJJUNEO","short_pith_number":"pith:OHOJAM7E","schema_version":"1.0","canonical_sha256":"71dc9033e4669795eacf7cf8d4a68d239cb79117ed038966abc0af9c31bcfd04","source":{"kind":"arxiv","id":"2410.03930","version":3},"attestation_state":"computed","paper":{"title":"Reverb: Open-Source ASR and Diarization from Rev","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Corey Miller, Danny Chen, J\\'an Profant, Jean-Philippe Robichaud, Jennifer Drexler Fox, Martin Ratajczak, Miguel \\'Angel del R\\'io Fern\\'andez, Mig\\\"uel Jett\\'e, Nan Qin, Natalie Delworth, Nishchal Bhandari, Ond\\v{r}ej Novotn\\'y, Quinten McNamara","submitted_at":"2024-10-04T21:13:58Z","abstract_excerpt":"Today, we are open-sourcing our core speech recognition and diarization models for non-commercial use. We are releasing both a full production pipeline for developers as well as pared-down research models for experimentation. Rev hopes that these releases will spur research and innovation in the fast-moving domain of voice technology. The speech recognition models released today outperform all existing open source speech recognition models across a variety of long-form speech recognition domains."},"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":"2410.03930","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T21:13:58Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d61c6561d8e3e3182c76d0ff6113563dd49f7f6e60b4092b82ce4e612e8bdba0","abstract_canon_sha256":"e7b923771cfcc69e2362cf625c9d0f03b0fd679162953e4ee16ec7a2885ce21c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:10.405834Z","signature_b64":"Q0j4ZEpL49husO1jRLMiipp8R+swN8DdOZpoK5rYe1tkKbN3lqVWVBBL/QT5AJORKh1+BGJJEtoQDnMJa96vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71dc9033e4669795eacf7cf8d4a68d239cb79117ed038966abc0af9c31bcfd04","last_reissued_at":"2026-07-05T10:19:10.405309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:10.405309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reverb: Open-Source ASR and Diarization from Rev","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Corey Miller, Danny Chen, J\\'an Profant, Jean-Philippe Robichaud, Jennifer Drexler Fox, Martin Ratajczak, Miguel \\'Angel del R\\'io Fern\\'andez, Mig\\\"uel Jett\\'e, Nan Qin, Natalie Delworth, Nishchal Bhandari, Ond\\v{r}ej Novotn\\'y, Quinten McNamara","submitted_at":"2024-10-04T21:13:58Z","abstract_excerpt":"Today, we are open-sourcing our core speech recognition and diarization models for non-commercial use. We are releasing both a full production pipeline for developers as well as pared-down research models for experimentation. Rev hopes that these releases will spur research and innovation in the fast-moving domain of voice technology. The speech recognition models released today outperform all existing open source speech recognition models across a variety of long-form speech recognition domains."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03930","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/2410.03930/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":"2410.03930","created_at":"2026-07-05T10:19:10.405384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03930v3","created_at":"2026-07-05T10:19:10.405384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03930","created_at":"2026-07-05T10:19:10.405384+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHOJAM7EM2LZ","created_at":"2026-07-05T10:19:10.405384+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHOJAM7EM2LZL2WP","created_at":"2026-07-05T10:19:10.405384+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHOJAM7E","created_at":"2026-07-05T10:19:10.405384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO","json":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO.json","graph_json":"https://pith.science/api/pith-number/OHOJAM7EM2LZL2WPPT4NJJUNEO/graph.json","events_json":"https://pith.science/api/pith-number/OHOJAM7EM2LZL2WPPT4NJJUNEO/events.json","paper":"https://pith.science/paper/OHOJAM7E"},"agent_actions":{"view_html":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO","download_json":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO.json","view_paper":"https://pith.science/paper/OHOJAM7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03930&json=true","fetch_graph":"https://pith.science/api/pith-number/OHOJAM7EM2LZL2WPPT4NJJUNEO/graph.json","fetch_events":"https://pith.science/api/pith-number/OHOJAM7EM2LZL2WPPT4NJJUNEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO/action/storage_attestation","attest_author":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO/action/author_attestation","sign_citation":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO/action/citation_signature","submit_replication":"https://pith.science/pith/OHOJAM7EM2LZL2WPPT4NJJUNEO/action/replication_record"}},"created_at":"2026-07-05T10:19:10.405384+00:00","updated_at":"2026-07-05T10:19:10.405384+00:00"}