{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VIH5QVCTSXJNTB6OVTD43HTJ7D","short_pith_number":"pith:VIH5QVCT","schema_version":"1.0","canonical_sha256":"aa0fd8545395d2d987ceacc7cd9e69f8c0268f78ee836414a4114e284a40a114","source":{"kind":"arxiv","id":"2606.21854","version":1},"attestation_state":"computed","paper":{"title":"ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alberto Abad, Alexander Polok, Carlos Carvalho, Chenda Li, Chyi-Jiunn Lin, Da-Hee Yang, Francisco Teixeira, Jiatong Shi, Jinchuan Tian, Masao Someki, Nelson Enrique Yalta Soplin, Samuele Cornell, Shinji Watanabe, Siddhant Arora, Wangyou Zhang, Wei Wang, William Chen","submitted_at":"2026-06-20T03:21:57Z","abstract_excerpt":"Recent speech research involves increasingly large datasets, complex models, and diverse experimental workflows. However, existing frameworks require substantial engineering effort to support such experiments. We present ESPnet3, a speech and audio research framework built on a modular system architecture with configuration-driven dataset composition and unified Python-based workflows. ESPnet3 introduces a DataOrganizer abstraction for flexible dataset integration and dataset sharding for memory-efficient large-scale training, while allowing recipe-specific logic through lightweight stage over"},"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":"2606.21854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T03:21:57Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a601d4aa86cbe0a08a19a163b39e5994f90a8aba1517f443dc7c2814dddd0a8f","abstract_canon_sha256":"78da6e3409ff6d2f70517962fb745fb8cc363e9b9a175db4759f8b0bda1197c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:00.980079Z","signature_b64":"BcTSyToCIIoPm9xJU9BfDKF/EJ4KDzBRqeaQPhit2uKlShBdcNXEvTBJFp4jjIqkt4Zrp1tA7LbPTWnu2xLWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa0fd8545395d2d987ceacc7cd9e69f8c0268f78ee836414a4114e284a40a114","last_reissued_at":"2026-06-23T02:13:00.979681Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:00.979681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alberto Abad, Alexander Polok, Carlos Carvalho, Chenda Li, Chyi-Jiunn Lin, Da-Hee Yang, Francisco Teixeira, Jiatong Shi, Jinchuan Tian, Masao Someki, Nelson Enrique Yalta Soplin, Samuele Cornell, Shinji Watanabe, Siddhant Arora, Wangyou Zhang, Wei Wang, William Chen","submitted_at":"2026-06-20T03:21:57Z","abstract_excerpt":"Recent speech research involves increasingly large datasets, complex models, and diverse experimental workflows. However, existing frameworks require substantial engineering effort to support such experiments. We present ESPnet3, a speech and audio research framework built on a modular system architecture with configuration-driven dataset composition and unified Python-based workflows. ESPnet3 introduces a DataOrganizer abstraction for flexible dataset integration and dataset sharding for memory-efficient large-scale training, while allowing recipe-specific logic through lightweight stage over"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21854","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/2606.21854/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":"2606.21854","created_at":"2026-06-23T02:13:00.979739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21854v1","created_at":"2026-06-23T02:13:00.979739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21854","created_at":"2026-06-23T02:13:00.979739+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIH5QVCTSXJN","created_at":"2026-06-23T02:13:00.979739+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIH5QVCTSXJNTB6O","created_at":"2026-06-23T02:13:00.979739+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIH5QVCT","created_at":"2026-06-23T02:13:00.979739+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/VIH5QVCTSXJNTB6OVTD43HTJ7D","json":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D.json","graph_json":"https://pith.science/api/pith-number/VIH5QVCTSXJNTB6OVTD43HTJ7D/graph.json","events_json":"https://pith.science/api/pith-number/VIH5QVCTSXJNTB6OVTD43HTJ7D/events.json","paper":"https://pith.science/paper/VIH5QVCT"},"agent_actions":{"view_html":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D","download_json":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D.json","view_paper":"https://pith.science/paper/VIH5QVCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21854&json=true","fetch_graph":"https://pith.science/api/pith-number/VIH5QVCTSXJNTB6OVTD43HTJ7D/graph.json","fetch_events":"https://pith.science/api/pith-number/VIH5QVCTSXJNTB6OVTD43HTJ7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/action/storage_attestation","attest_author":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/action/author_attestation","sign_citation":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/action/citation_signature","submit_replication":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/action/replication_record"}},"created_at":"2026-06-23T02:13:00.979739+00:00","updated_at":"2026-06-23T02:13:00.979739+00:00"}