{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VIH5QVCTSXJNTB6OVTD43HTJ7D","short_pith_number":"pith:VIH5QVCT","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"},"canonical_sha256":"aa0fd8545395d2d987ceacc7cd9e69f8c0268f78ee836414a4114e284a40a114","source":{"kind":"arxiv","id":"2606.21854","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VIH5QVCTSXJNTB6OVTD43HTJ7D","target":"record","payload":{"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"},"canonical_sha256":"aa0fd8545395d2d987ceacc7cd9e69f8c0268f78ee836414a4114e284a40a114","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"},"source_kind":"arxiv","source_id":"2606.21854","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3wcMv8QtZCdp1byjQd2yRgDqqvWj0LbEF8cdGA1mxymQdGmh1+jvBqKLTdSbm/i+1ECeghvyOna/erff/wZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T16:37:32.767177Z"},"content_sha256":"95c68a24d9913686cea3e3ec4b700e3af5082d1139325a7f2a3ee5bcbb372737","schema_version":"1.0","event_id":"sha256:95c68a24d9913686cea3e3ec4b700e3af5082d1139325a7f2a3ee5bcbb372737"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VIH5QVCTSXJNTB6OVTD43HTJ7D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTIuD++SGguMv87Dtt0lUmvrRmU/lvxuc/VFTeUVOIyleVFePI1+R0dfcLr5VS3HoBSRKhR+bJSZg66YJ+kwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T16:37:32.767574Z"},"content_sha256":"2fbd3a00580ff222da6545c38c9a3035009fefbf6a040f871ba4f0628a66dd22","schema_version":"1.0","event_id":"sha256:2fbd3a00580ff222da6545c38c9a3035009fefbf6a040f871ba4f0628a66dd22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/bundle.json","state_url":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-25T16:37:32Z","links":{"resolver":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D","bundle":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/bundle.json","state":"https://pith.science/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VIH5QVCTSXJNTB6OVTD43HTJ7D/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUBuDW7i6RNxX6HChNV1Y0jXQ8zvw33k4Hihf7HPbSL8ALvmqXOix0r4PaLJN7lE8t8a0HiOwKxNPtiMztb6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T16:37:32.769660Z","bundle_sha256":"7ac2fad279be612cdba61eb5343e95ee1d12fcfc5e37bba5a0fbbb75549fc4d0"}}