{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OAROWUEDPMX7JIN4KWZVIKGS6F","short_pith_number":"pith:OAROWUED","canonical_record":{"source":{"id":"2412.14890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T14:21:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5fdf1aa3a00225c6472055569a4cd59b959f6635f2d389b89f0b8a7dc454d729","abstract_canon_sha256":"a7f823232fa831026f783c24069d53000136ca166927f873168c492a2c510ab6"},"schema_version":"1.0"},"canonical_sha256":"7022eb50837b2ff4a1bc55b35428d2f14c61fb0000fafbee9a09e34c036b55d1","source":{"kind":"arxiv","id":"2412.14890","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14890","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14890v1","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14890","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"OAROWUEDPMX7","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"OAROWUEDPMX7JIN4","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"OAROWUED","created_at":"2026-07-05T09:51:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OAROWUEDPMX7JIN4KWZVIKGS6F","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T14:21:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5fdf1aa3a00225c6472055569a4cd59b959f6635f2d389b89f0b8a7dc454d729","abstract_canon_sha256":"a7f823232fa831026f783c24069d53000136ca166927f873168c492a2c510ab6"},"schema_version":"1.0"},"canonical_sha256":"7022eb50837b2ff4a1bc55b35428d2f14c61fb0000fafbee9a09e34c036b55d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:53.952965Z","signature_b64":"uZiSykWuZL5zauVHYaEZMQkwUBSTC89P3P0a/PFpXIW7kyx2pUQMF64FUS/84T+44sODwDWRbn5naDpUr2G5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7022eb50837b2ff4a1bc55b35428d2f14c61fb0000fafbee9a09e34c036b55d1","last_reissued_at":"2026-07-05T09:51:53.952612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:53.952612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14890","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":"2026-07-05T09:51:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zND1UImiYkGxzSXYfKPjSJaifUvstJ0Q24x1g5lB+Mypm1PFYQTIsadQajPycWXL6Otu/peQpnyJp2mqfT91Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:15:24.068458Z"},"content_sha256":"fde82d8f9d0dfdabb67548bd8170cd419eccad9b14f6ab44df6fd8a9bae1ca25","schema_version":"1.0","event_id":"sha256:fde82d8f9d0dfdabb67548bd8170cd419eccad9b14f6ab44df6fd8a9bae1ca25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OAROWUEDPMX7JIN4KWZVIKGS6F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scale This, Not That: Investigating Key Dataset Attributes for Efficient Speech Enhancement Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenda Li, Leying Zhang, Wangyou Zhang, Yanmin Qian","submitted_at":"2024-12-19T14:21:51Z","abstract_excerpt":"Recent speech enhancement models have shown impressive performance gains by scaling up model complexity and training data. However, the impact of dataset variability (e.g. text, language, speaker, and noise) has been underexplored. Analyzing each attribute individually is often challenging, as multiple attributes are usually entangled in commonly used datasets, posing a significant obstacle in understanding the distinct contributions of each attribute to the model's performance. To address this challenge, we propose a generation-training-evaluation framework that leverages zero-shot text-to-sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14890","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/2412.14890/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":"2026-07-05T09:51:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTMjKpaXx4ezoEUVIQJHB6Nh670q9vxktweLs0YixcnDEV2hgalZIkRN8Cx+LXsR2gwWjjgpwVFRVTyqYXCqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:15:24.068976Z"},"content_sha256":"c0becdd49b280dc6ea838aad586159431599ed68e7c2302ae22993d2138ada54","schema_version":"1.0","event_id":"sha256:c0becdd49b280dc6ea838aad586159431599ed68e7c2302ae22993d2138ada54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAROWUEDPMX7JIN4KWZVIKGS6F/bundle.json","state_url":"https://pith.science/pith/OAROWUEDPMX7JIN4KWZVIKGS6F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAROWUEDPMX7JIN4KWZVIKGS6F/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":"2026-08-22T10:15:24Z","links":{"resolver":"https://pith.science/pith/OAROWUEDPMX7JIN4KWZVIKGS6F","bundle":"https://pith.science/pith/OAROWUEDPMX7JIN4KWZVIKGS6F/bundle.json","state":"https://pith.science/pith/OAROWUEDPMX7JIN4KWZVIKGS6F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAROWUEDPMX7JIN4KWZVIKGS6F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OAROWUEDPMX7JIN4KWZVIKGS6F","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":"a7f823232fa831026f783c24069d53000136ca166927f873168c492a2c510ab6","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T14:21:51Z","title_canon_sha256":"5fdf1aa3a00225c6472055569a4cd59b959f6635f2d389b89f0b8a7dc454d729"},"schema_version":"1.0","source":{"id":"2412.14890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14890","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14890v1","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14890","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"OAROWUEDPMX7","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"OAROWUEDPMX7JIN4","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"OAROWUED","created_at":"2026-07-05T09:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:c0becdd49b280dc6ea838aad586159431599ed68e7c2302ae22993d2138ada54","target":"graph","created_at":"2026-07-05T09:51:53Z","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/2412.14890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent speech enhancement models have shown impressive performance gains by scaling up model complexity and training data. However, the impact of dataset variability (e.g. text, language, speaker, and noise) has been underexplored. Analyzing each attribute individually is often challenging, as multiple attributes are usually entangled in commonly used datasets, posing a significant obstacle in understanding the distinct contributions of each attribute to the model's performance. To address this challenge, we propose a generation-training-evaluation framework that leverages zero-shot text-to-sp","authors_text":"Chenda Li, Leying Zhang, Wangyou Zhang, Yanmin Qian","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T14:21:51Z","title":"Scale This, Not That: Investigating Key Dataset Attributes for Efficient Speech Enhancement Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14890","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:fde82d8f9d0dfdabb67548bd8170cd419eccad9b14f6ab44df6fd8a9bae1ca25","target":"record","created_at":"2026-07-05T09:51:53Z","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":"a7f823232fa831026f783c24069d53000136ca166927f873168c492a2c510ab6","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T14:21:51Z","title_canon_sha256":"5fdf1aa3a00225c6472055569a4cd59b959f6635f2d389b89f0b8a7dc454d729"},"schema_version":"1.0","source":{"id":"2412.14890","kind":"arxiv","version":1}},"canonical_sha256":"7022eb50837b2ff4a1bc55b35428d2f14c61fb0000fafbee9a09e34c036b55d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7022eb50837b2ff4a1bc55b35428d2f14c61fb0000fafbee9a09e34c036b55d1","first_computed_at":"2026-07-05T09:51:53.952612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:53.952612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uZiSykWuZL5zauVHYaEZMQkwUBSTC89P3P0a/PFpXIW7kyx2pUQMF64FUS/84T+44sODwDWRbn5naDpUr2G5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:53.952965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fde82d8f9d0dfdabb67548bd8170cd419eccad9b14f6ab44df6fd8a9bae1ca25","sha256:c0becdd49b280dc6ea838aad586159431599ed68e7c2302ae22993d2138ada54"],"state_sha256":"8bfbba619f056c98c8f4fbe4810b5e03c261eb1c9301ff58c409fbb1d55f8e7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLmFfW1xo44GYLe6zbP+pq3XrytwE+saypBGcLUFuXuRrLUzH3SXeR17uvkUjGJJYK5KsBBJhoK+NgbylIvkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T10:15:24.073980Z","bundle_sha256":"25cd3adf7e33fb4baab3a512c9e0bbae007930d25b51d84e397c054c875c1a7a"}}