{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VIH5QVCTSXJNTB6OVTD43HTJ7D","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":"78da6e3409ff6d2f70517962fb745fb8cc363e9b9a175db4759f8b0bda1197c7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T03:21:57Z","title_canon_sha256":"a601d4aa86cbe0a08a19a163b39e5994f90a8aba1517f443dc7c2814dddd0a8f"},"schema_version":"1.0","source":{"id":"2606.21854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21854","created_at":"2026-06-23T02:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21854v1","created_at":"2026-06-23T02:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21854","created_at":"2026-06-23T02:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"VIH5QVCTSXJN","created_at":"2026-06-23T02:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"VIH5QVCTSXJNTB6O","created_at":"2026-06-23T02:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"VIH5QVCT","created_at":"2026-06-23T02:13:00Z"}],"graph_snapshots":[{"event_id":"sha256:2fbd3a00580ff222da6545c38c9a3035009fefbf6a040f871ba4f0628a66dd22","target":"graph","created_at":"2026-06-23T02:13:00Z","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/2606.21854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T03:21:57Z","title":"ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21854","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":"sha256:95c68a24d9913686cea3e3ec4b700e3af5082d1139325a7f2a3ee5bcbb372737","target":"record","created_at":"2026-06-23T02:13:00Z","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":"78da6e3409ff6d2f70517962fb745fb8cc363e9b9a175db4759f8b0bda1197c7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T03:21:57Z","title_canon_sha256":"a601d4aa86cbe0a08a19a163b39e5994f90a8aba1517f443dc7c2814dddd0a8f"},"schema_version":"1.0","source":{"id":"2606.21854","kind":"arxiv","version":1}},"canonical_sha256":"aa0fd8545395d2d987ceacc7cd9e69f8c0268f78ee836414a4114e284a40a114","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa0fd8545395d2d987ceacc7cd9e69f8c0268f78ee836414a4114e284a40a114","first_computed_at":"2026-06-23T02:13:00.979681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:00.979681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BcTSyToCIIoPm9xJU9BfDKF/EJ4KDzBRqeaQPhit2uKlShBdcNXEvTBJFp4jjIqkt4Zrp1tA7LbPTWnu2xLWDg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:00.980079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95c68a24d9913686cea3e3ec4b700e3af5082d1139325a7f2a3ee5bcbb372737","sha256:2fbd3a00580ff222da6545c38c9a3035009fefbf6a040f871ba4f0628a66dd22"],"state_sha256":"79d9559e0dd9125fa1df1a071b44774753d3b29ee3225c5e93574e09f07fe480"}