{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BBNXK25ILYKSNWI3THAFCUPEYW","short_pith_number":"pith:BBNXK25I","canonical_record":{"source":{"id":"2309.08127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T03:36:08Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"942afc083848e5cf19ab9fd3c4937ed2746a0d0afb24f5d0ea3db109c80dbda9","abstract_canon_sha256":"7d55240e0e62f17b5d7961d1457b1f457b09e7a9a376a84f6f06bad091289d34"},"schema_version":"1.0"},"canonical_sha256":"085b756ba85e1526d91b99c05151e4c599153fef9234a6da5815d8e8ef45bbab","source":{"kind":"arxiv","id":"2309.08127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08127","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08127v1","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08127","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"BBNXK25ILYKS","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"BBNXK25ILYKSNWI3","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"BBNXK25I","created_at":"2026-07-05T06:51:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BBNXK25ILYKSNWI3THAFCUPEYW","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T03:36:08Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"942afc083848e5cf19ab9fd3c4937ed2746a0d0afb24f5d0ea3db109c80dbda9","abstract_canon_sha256":"7d55240e0e62f17b5d7961d1457b1f457b09e7a9a376a84f6f06bad091289d34"},"schema_version":"1.0"},"canonical_sha256":"085b756ba85e1526d91b99c05151e4c599153fef9234a6da5815d8e8ef45bbab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:02.327806Z","signature_b64":"2sxq5uoOnA7pLcMUqwN+Qc2WD/nCLl/Ff1c+PLVnTv1zWMOjwnWR6/ejok+kvsmkBzG/iOjzRjgXXg7PdcYyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085b756ba85e1526d91b99c05151e4c599153fef9234a6da5815d8e8ef45bbab","last_reissued_at":"2026-07-05T06:51:02.327370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:02.327370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08127","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":"2026-07-05T06:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dpn1qF27dK+NoCYDss9qE4ADJXTd38a6aSKHP82HSOw2IJriTbhGglXX/NXHh/FjAliETaN7M023ydN/WPLLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:31:50.213393Z"},"content_sha256":"32ec5d2461164b9659c910e6729d80a5324e0fd4fa8f26067776e90f0198a58f","schema_version":"1.0","event_id":"sha256:32ec5d2461164b9659c910e6729d80a5324e0fd4fa8f26067776e90f0198a58f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BBNXK25ILYKSNWI3THAFCUPEYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity-based core-set selection for text-to-speech with linguistic and acoustic features","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki","submitted_at":"2023-09-15T03:36:08Z","abstract_excerpt":"This paper proposes a method for extracting a lightweight subset from a text-to-speech (TTS) corpus ensuring synthetic speech quality. In recent years, methods have been proposed for constructing large-scale TTS corpora by collecting diverse data from massive sources such as audiobooks and YouTube. Although these methods have gained significant attention for enhancing the expressive capabilities of TTS systems, they often prioritize collecting vast amounts of data without considering practical constraints like storage capacity and computation time in training, which limits the available data q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08127","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/2309.08127/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":"2026-07-05T06:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cb0FrlDx4j0DHuwSJ36RsIuMW1PynEXTh3vyKr7WJSzJDoeXwCjEh8dhLPzHxG5gdSJWNWBmQhIUpim0qBM0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:31:50.213777Z"},"content_sha256":"d51e6be1560a0bb3d5adc25780f00a14541781d83a32e353ad3959cb86041408","schema_version":"1.0","event_id":"sha256:d51e6be1560a0bb3d5adc25780f00a14541781d83a32e353ad3959cb86041408"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBNXK25ILYKSNWI3THAFCUPEYW/bundle.json","state_url":"https://pith.science/pith/BBNXK25ILYKSNWI3THAFCUPEYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBNXK25ILYKSNWI3THAFCUPEYW/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":"2026-07-07T12:31:50Z","links":{"resolver":"https://pith.science/pith/BBNXK25ILYKSNWI3THAFCUPEYW","bundle":"https://pith.science/pith/BBNXK25ILYKSNWI3THAFCUPEYW/bundle.json","state":"https://pith.science/pith/BBNXK25ILYKSNWI3THAFCUPEYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBNXK25ILYKSNWI3THAFCUPEYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BBNXK25ILYKSNWI3THAFCUPEYW","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":"7d55240e0e62f17b5d7961d1457b1f457b09e7a9a376a84f6f06bad091289d34","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T03:36:08Z","title_canon_sha256":"942afc083848e5cf19ab9fd3c4937ed2746a0d0afb24f5d0ea3db109c80dbda9"},"schema_version":"1.0","source":{"id":"2309.08127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08127","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08127v1","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08127","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"BBNXK25ILYKS","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"BBNXK25ILYKSNWI3","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"BBNXK25I","created_at":"2026-07-05T06:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:d51e6be1560a0bb3d5adc25780f00a14541781d83a32e353ad3959cb86041408","target":"graph","created_at":"2026-07-05T06:51:02Z","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/2309.08127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a method for extracting a lightweight subset from a text-to-speech (TTS) corpus ensuring synthetic speech quality. In recent years, methods have been proposed for constructing large-scale TTS corpora by collecting diverse data from massive sources such as audiobooks and YouTube. Although these methods have gained significant attention for enhancing the expressive capabilities of TTS systems, they often prioritize collecting vast amounts of data without considering practical constraints like storage capacity and computation time in training, which limits the available data q","authors_text":"Hiroshi Saruwatari, Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T03:36:08Z","title":"Diversity-based core-set selection for text-to-speech with linguistic and acoustic features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08127","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":"sha256:32ec5d2461164b9659c910e6729d80a5324e0fd4fa8f26067776e90f0198a58f","target":"record","created_at":"2026-07-05T06:51:02Z","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":"7d55240e0e62f17b5d7961d1457b1f457b09e7a9a376a84f6f06bad091289d34","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T03:36:08Z","title_canon_sha256":"942afc083848e5cf19ab9fd3c4937ed2746a0d0afb24f5d0ea3db109c80dbda9"},"schema_version":"1.0","source":{"id":"2309.08127","kind":"arxiv","version":1}},"canonical_sha256":"085b756ba85e1526d91b99c05151e4c599153fef9234a6da5815d8e8ef45bbab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"085b756ba85e1526d91b99c05151e4c599153fef9234a6da5815d8e8ef45bbab","first_computed_at":"2026-07-05T06:51:02.327370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:02.327370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2sxq5uoOnA7pLcMUqwN+Qc2WD/nCLl/Ff1c+PLVnTv1zWMOjwnWR6/ejok+kvsmkBzG/iOjzRjgXXg7PdcYyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:02.327806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32ec5d2461164b9659c910e6729d80a5324e0fd4fa8f26067776e90f0198a58f","sha256:d51e6be1560a0bb3d5adc25780f00a14541781d83a32e353ad3959cb86041408"],"state_sha256":"38b8403b3548d5053b869b3ca063092a7fc10af30f7cbc1fc4901a3059b91275"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"evgedqN4IllDrQGXE/CMcZL3nsWr+aYapDGD6fRv913+LPcLlmp1TMflCWHy0u/AkUI2Ieu/1QAexdG4I6wJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:31:50.215828Z","bundle_sha256":"52d09981f687dad9031397ac60a045515fdbf508bbcb559970375b3acc88f811"}}