{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQZWSQSA5QUKST6BWDGBQ6O5TF","short_pith_number":"pith:XQZWSQSA","schema_version":"1.0","canonical_sha256":"bc33694240ec28a94fc1b0cc1879dd994a05493e39878b9eb79ebc6ce1151206","source":{"kind":"arxiv","id":"2405.18347","version":2},"attestation_state":"computed","paper":{"title":"Dataset Growth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baigui Sun, Hao Tang, Hongxun Yao, Kai Wang, Lei Shang, Radu Timofte, Xiaojiang Peng, Yang You, Yukun Zhou, Zangwei Zheng, Zebang Cheng, Zhaopan Xu, Ziheng Qin","submitted_at":"2024-05-28T16:43:57Z","abstract_excerpt":"Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are from different sources with various qualities, and it is impractical to do manual cleaning against noise and redundancy given today's data scale. There are existing techniques for cleaning/selecting the collected data. However, these methods are mainly proposed for offline settings that target one of the cleanness and redundancy problems. In practice, data are growing exponentially with both problems. This leads to r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.18347","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T16:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"33f002e6020f03fb1a7c76d391732683fb0b42b7bd7b04a9d4ab522b5ab10c99","abstract_canon_sha256":"59259d2488843cef125be378e22471209c59a3922baabbc9f3b80de8c80d6523"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:20.771731Z","signature_b64":"BjZkhTiWfDH2fGmkF+xwCJYhkDqB40pUZPcy5SM9UFCzx++L1RP7mzwO0P3RYW6delRL6VhRg5A3IOI2Ao2qAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc33694240ec28a94fc1b0cc1879dd994a05493e39878b9eb79ebc6ce1151206","last_reissued_at":"2026-07-05T08:47:20.771209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:20.771209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Growth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baigui Sun, Hao Tang, Hongxun Yao, Kai Wang, Lei Shang, Radu Timofte, Xiaojiang Peng, Yang You, Yukun Zhou, Zangwei Zheng, Zebang Cheng, Zhaopan Xu, Ziheng Qin","submitted_at":"2024-05-28T16:43:57Z","abstract_excerpt":"Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are from different sources with various qualities, and it is impractical to do manual cleaning against noise and redundancy given today's data scale. There are existing techniques for cleaning/selecting the collected data. However, these methods are mainly proposed for offline settings that target one of the cleanness and redundancy problems. In practice, data are growing exponentially with both problems. This leads to r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18347","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/2405.18347/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.18347","created_at":"2026-07-05T08:47:20.771272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18347v2","created_at":"2026-07-05T08:47:20.771272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18347","created_at":"2026-07-05T08:47:20.771272+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQZWSQSA5QUK","created_at":"2026-07-05T08:47:20.771272+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQZWSQSA5QUKST6B","created_at":"2026-07-05T08:47:20.771272+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQZWSQSA","created_at":"2026-07-05T08:47:20.771272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF","json":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF.json","graph_json":"https://pith.science/api/pith-number/XQZWSQSA5QUKST6BWDGBQ6O5TF/graph.json","events_json":"https://pith.science/api/pith-number/XQZWSQSA5QUKST6BWDGBQ6O5TF/events.json","paper":"https://pith.science/paper/XQZWSQSA"},"agent_actions":{"view_html":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF","download_json":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF.json","view_paper":"https://pith.science/paper/XQZWSQSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18347&json=true","fetch_graph":"https://pith.science/api/pith-number/XQZWSQSA5QUKST6BWDGBQ6O5TF/graph.json","fetch_events":"https://pith.science/api/pith-number/XQZWSQSA5QUKST6BWDGBQ6O5TF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF/action/storage_attestation","attest_author":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF/action/author_attestation","sign_citation":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF/action/citation_signature","submit_replication":"https://pith.science/pith/XQZWSQSA5QUKST6BWDGBQ6O5TF/action/replication_record"}},"created_at":"2026-07-05T08:47:20.771272+00:00","updated_at":"2026-07-05T08:47:20.771272+00:00"}