{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OETW6E432HWV6RIYBGV5MLYIXF","short_pith_number":"pith:OETW6E43","canonical_record":{"source":{"id":"2506.23859","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-30T13:55:10Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"47a9f66f7710b6402a48e14c6c951b998efcc7fc2851a797ed5ed2d09f9de38e","abstract_canon_sha256":"816d4f04f7de7a057182f68ffb9c554adff5943ecf375642813a76c3d9359dd6"},"schema_version":"1.0"},"canonical_sha256":"71276f139bd1ed5f451809abd62f08b945c3977c9f17ce9df936458ebf303d8b","source":{"kind":"arxiv","id":"2506.23859","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23859","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23859v2","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23859","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"OETW6E432HWV","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"OETW6E432HWV6RIY","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"OETW6E43","created_at":"2026-07-05T11:55:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OETW6E432HWV6RIYBGV5MLYIXF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23859","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-30T13:55:10Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"47a9f66f7710b6402a48e14c6c951b998efcc7fc2851a797ed5ed2d09f9de38e","abstract_canon_sha256":"816d4f04f7de7a057182f68ffb9c554adff5943ecf375642813a76c3d9359dd6"},"schema_version":"1.0"},"canonical_sha256":"71276f139bd1ed5f451809abd62f08b945c3977c9f17ce9df936458ebf303d8b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:41.043820Z","signature_b64":"RXDJshI/+nvrzjERodhKII8QuaxPaMYkrSx+QDAg8nq4vxviVAD0XjZOtd1LsAepB9tDJuQKEatcoms/lQ67Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71276f139bd1ed5f451809abd62f08b945c3977c9f17ce9df936458ebf303d8b","last_reissued_at":"2026-07-05T11:55:41.043290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:41.043290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23859","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eMnK2is46COZbwbya7PAjEyJ0k8iHdIP1iu/Q9J4FaJzbbXACBJYpUUwZC3lbcFbDk9VnUw+N3U7Y/YGHfORAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:46.490460Z"},"content_sha256":"8275066ba43bb7eb3f10eb1f2c9a17cef01d1ec0578b09f3901350f8a5ca24b9","schema_version":"1.0","event_id":"sha256:8275066ba43bb7eb3f10eb1f2c9a17cef01d1ec0578b09f3901350f8a5ca24b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OETW6E432HWV6RIYBGV5MLYIXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More: Data Curation Matters in Scaling Speech Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Anurag Kumar, Chenda Li, Kohei Saijo, Marvin Sach, Robin Scheibler, Samuele Cornell, Shinji Watanabe, Tim Fingscheidt, Wangyou Zhang, Wei Wang, Yanmin Qian, Yihui Fu, Zhaoheng Ni","submitted_at":"2025-06-30T13:55:10Z","abstract_excerpt":"The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance, an observation empirically validated across numerous tasks in other domains. However, recent studies reveal diminishing returns when scaling speech enhancement data. We focus on a critical factor: prevalent quality issues in ``clean'' training labels within large-scale datasets. This work re-examines this phenomenon and demonstrates that, within large-scale training sets, prioritizing high-quality training data is mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23859","kind":"arxiv","version":2},"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/2506.23859/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":"2026-07-05T11:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gga/npFigokwiF3rju99dM1u1PCRacWrDC0xtkhn80plCJDaFLV7yfjoESgaxRBEdaxGjUmosZAhgYhaLb8hCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:46.490878Z"},"content_sha256":"4ccc976611e45c323782f4239e142a2527ba51997f53200f4f7f5de8b66ff0ee","schema_version":"1.0","event_id":"sha256:4ccc976611e45c323782f4239e142a2527ba51997f53200f4f7f5de8b66ff0ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OETW6E432HWV6RIYBGV5MLYIXF/bundle.json","state_url":"https://pith.science/pith/OETW6E432HWV6RIYBGV5MLYIXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OETW6E432HWV6RIYBGV5MLYIXF/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":"2026-07-06T20:58:46Z","links":{"resolver":"https://pith.science/pith/OETW6E432HWV6RIYBGV5MLYIXF","bundle":"https://pith.science/pith/OETW6E432HWV6RIYBGV5MLYIXF/bundle.json","state":"https://pith.science/pith/OETW6E432HWV6RIYBGV5MLYIXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OETW6E432HWV6RIYBGV5MLYIXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OETW6E432HWV6RIYBGV5MLYIXF","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":"816d4f04f7de7a057182f68ffb9c554adff5943ecf375642813a76c3d9359dd6","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-30T13:55:10Z","title_canon_sha256":"47a9f66f7710b6402a48e14c6c951b998efcc7fc2851a797ed5ed2d09f9de38e"},"schema_version":"1.0","source":{"id":"2506.23859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23859","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23859v2","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23859","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"OETW6E432HWV","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"OETW6E432HWV6RIY","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"OETW6E43","created_at":"2026-07-05T11:55:41Z"}],"graph_snapshots":[{"event_id":"sha256:4ccc976611e45c323782f4239e142a2527ba51997f53200f4f7f5de8b66ff0ee","target":"graph","created_at":"2026-07-05T11:55:41Z","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/2506.23859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance, an observation empirically validated across numerous tasks in other domains. However, recent studies reveal diminishing returns when scaling speech enhancement data. We focus on a critical factor: prevalent quality issues in ``clean'' training labels within large-scale datasets. This work re-examines this phenomenon and demonstrates that, within large-scale training sets, prioritizing high-quality training data is mo","authors_text":"Anurag Kumar, Chenda Li, Kohei Saijo, Marvin Sach, Robin Scheibler, Samuele Cornell, Shinji Watanabe, Tim Fingscheidt, Wangyou Zhang, Wei Wang, Yanmin Qian, Yihui Fu, Zhaoheng Ni","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-30T13:55:10Z","title":"Less is More: Data Curation Matters in Scaling Speech Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23859","kind":"arxiv","version":2},"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":"sha256:8275066ba43bb7eb3f10eb1f2c9a17cef01d1ec0578b09f3901350f8a5ca24b9","target":"record","created_at":"2026-07-05T11:55:41Z","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":"816d4f04f7de7a057182f68ffb9c554adff5943ecf375642813a76c3d9359dd6","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-30T13:55:10Z","title_canon_sha256":"47a9f66f7710b6402a48e14c6c951b998efcc7fc2851a797ed5ed2d09f9de38e"},"schema_version":"1.0","source":{"id":"2506.23859","kind":"arxiv","version":2}},"canonical_sha256":"71276f139bd1ed5f451809abd62f08b945c3977c9f17ce9df936458ebf303d8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71276f139bd1ed5f451809abd62f08b945c3977c9f17ce9df936458ebf303d8b","first_computed_at":"2026-07-05T11:55:41.043290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:41.043290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXDJshI/+nvrzjERodhKII8QuaxPaMYkrSx+QDAg8nq4vxviVAD0XjZOtd1LsAepB9tDJuQKEatcoms/lQ67Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:41.043820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8275066ba43bb7eb3f10eb1f2c9a17cef01d1ec0578b09f3901350f8a5ca24b9","sha256:4ccc976611e45c323782f4239e142a2527ba51997f53200f4f7f5de8b66ff0ee"],"state_sha256":"54311b398916d1e8118b196a79fe75feb05a0461279941b7b6931e596e58687f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+9R8gJTj6HnIS3sKxuEBX5k7aEODtJvhiD4utUdlOBdyrEXLlzedo6wuRanZSRnkG97pM73dAAgdr4T/fVDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:58:46.492873Z","bundle_sha256":"bc124dd4c6b39735ba05967044ca3949c85c2524237f15ab42de30400fdf6221"}}