{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7N46RRKUTD7FJHAT2W3ASSRGG3","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":"6ee8b968aa4594ad7eab7da7a5548732a0efcbebd1d2b806d65ed6241e5eb9ac","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-07T14:27:46Z","title_canon_sha256":"772a6f935d83054d61b1c5b92021af58b4e6e3928a542d6ab943cd5739879bdb"},"schema_version":"1.0","source":{"id":"2505.04457","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04457","created_at":"2026-07-05T11:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04457v4","created_at":"2026-07-05T11:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04457","created_at":"2026-07-05T11:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"7N46RRKUTD7F","created_at":"2026-07-05T11:41:41Z"},{"alias_kind":"pith_short_16","alias_value":"7N46RRKUTD7FJHAT","created_at":"2026-07-05T11:41:41Z"},{"alias_kind":"pith_short_8","alias_value":"7N46RRKU","created_at":"2026-07-05T11:41:41Z"}],"graph_snapshots":[{"event_id":"sha256:780f2bd9f3241c4f51fa9bc3700f1990e6057721b9f94b3311f221ff8b421a02","target":"graph","created_at":"2026-07-05T11:41:41Z","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/2505.04457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training data cleaning is a new application for generative model-based speech restoration (SR). This paper introduces Miipher-2, an SR model designed for million-hour scale data, for training data cleaning for large-scale generative models like large language models. Key challenges addressed include generalization to unseen languages, operation without explicit conditioning (e.g., text, speaker ID), and computational efficiency. Miipher-2 utilizes a frozen, pre-trained Universal Speech Model (USM), supporting over 300 languages, as a robust, conditioning-free feature extractor. To optimize eff","authors_text":"Haruko Ishikawa, Heiga Zen, Michiel Bacchiani, Robin Scheibler, Shigeki Karita, Yuma Koizumi","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-07T14:27:46Z","title":"Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04457","kind":"arxiv","version":4},"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":"sha256:99cb7bc3d61737de77410c635b88cdf9ed41dbad339cdbecd27d86f74326fadb","target":"record","created_at":"2026-07-05T11:41:41Z","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":"6ee8b968aa4594ad7eab7da7a5548732a0efcbebd1d2b806d65ed6241e5eb9ac","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-07T14:27:46Z","title_canon_sha256":"772a6f935d83054d61b1c5b92021af58b4e6e3928a542d6ab943cd5739879bdb"},"schema_version":"1.0","source":{"id":"2505.04457","kind":"arxiv","version":4}},"canonical_sha256":"fb79e8c55498fe549c13d5b6094a2636f2460109742fc275f69b3122d9c23a49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb79e8c55498fe549c13d5b6094a2636f2460109742fc275f69b3122d9c23a49","first_computed_at":"2026-07-05T11:41:41.697877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:41.697877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vnuwulh2mmYD/uPdRt2oKoMWSGH4/4RsSbnq8aXELFAHRK9312ptsa/xNSZ7VRFkjUdWJ318yshVW8ILegWgCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:41.698419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04457","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99cb7bc3d61737de77410c635b88cdf9ed41dbad339cdbecd27d86f74326fadb","sha256:780f2bd9f3241c4f51fa9bc3700f1990e6057721b9f94b3311f221ff8b421a02"],"state_sha256":"953d34b05782a91098b97009033a84cdcb91703bda86381f621a2da5bce587e2"}