{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DBCA6VM67DSPQJDMKO3BOIB3HF","short_pith_number":"pith:DBCA6VM6","canonical_record":{"source":{"id":"2101.01441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-05T10:23:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0fa94f9b4756ff30fc650da824ceb6ae2e304f6f93e7e450853f2ae16684bf41","abstract_canon_sha256":"19ac17ea93cd9d7869730a271a8cf17aad0afb743f0e1156fd116609febc72fc"},"schema_version":"1.0"},"canonical_sha256":"18440f559ef8e4f8246c53b617203b395a2b2eeef07a604edaa451e9f0822f20","source":{"kind":"arxiv","id":"2101.01441","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01441","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01441v1","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01441","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"DBCA6VM67DSP","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"DBCA6VM67DSPQJDM","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"DBCA6VM6","created_at":"2026-07-05T02:04:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DBCA6VM67DSPQJDMKO3BOIB3HF","target":"record","payload":{"canonical_record":{"source":{"id":"2101.01441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-05T10:23:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0fa94f9b4756ff30fc650da824ceb6ae2e304f6f93e7e450853f2ae16684bf41","abstract_canon_sha256":"19ac17ea93cd9d7869730a271a8cf17aad0afb743f0e1156fd116609febc72fc"},"schema_version":"1.0"},"canonical_sha256":"18440f559ef8e4f8246c53b617203b395a2b2eeef07a604edaa451e9f0822f20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:33.186447Z","signature_b64":"uyR1YOEExuayjx8x/aTH15LM/tWufcPvudSDCfIPbdofOs7Byd0eneiepWeMRh1Nvnx1u9cULZEFUpgjPqaeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18440f559ef8e4f8246c53b617203b395a2b2eeef07a604edaa451e9f0822f20","last_reissued_at":"2026-07-05T02:04:33.186090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:33.186090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.01441","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":"2026-07-05T02:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pY7+gK7tFV/rKqS1b6LwHCOxYthB0UNLvZHGapNg5S6ZFDp5GdPnKEw08ydDCrBXTh8oqeZHmy3Q87KJEWFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:19.385145Z"},"content_sha256":"b2ae97b074ea98e4d39ca9230ba101698c5145728d9d1ccfffee531636932812","schema_version":"1.0","event_id":"sha256:b2ae97b074ea98e4d39ca9230ba101698c5145728d9d1ccfffee531636932812"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DBCA6VM67DSPQJDMKO3BOIB3HF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality Measures and Efficient Evaluation Algorithms for Large-Scale High-Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyeongmin Cho, Sangkyun Lee","submitted_at":"2021-01-05T10:23:08Z","abstract_excerpt":"Machine learning has been proven to be effective in various application areas, such as object and speech recognition on mobile systems. Since a critical key to machine learning success is the availability of large training data, many datasets are being disclosed and published online. From a data consumer or manager point of view, measuring data quality is an important first step in the learning process. We need to determine which datasets to use, update, and maintain. However, not many practical ways to measure data quality are available today, especially when it comes to large-scale high-dime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01441","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/2101.01441/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":"2026-07-05T02:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bUBKUvLnDwpg6QpSPYuncWM3VEkgndOXXYoCigwifT2aYOuc8NvDvgzzNEir3N5XuOc71SCiaN3U0on7c8/HAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:19.385540Z"},"content_sha256":"68e05fc1e2a2c16817f97f0efef8a18004fd5348e0d0ef95c98670d55757475a","schema_version":"1.0","event_id":"sha256:68e05fc1e2a2c16817f97f0efef8a18004fd5348e0d0ef95c98670d55757475a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBCA6VM67DSPQJDMKO3BOIB3HF/bundle.json","state_url":"https://pith.science/pith/DBCA6VM67DSPQJDMKO3BOIB3HF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBCA6VM67DSPQJDMKO3BOIB3HF/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":"2026-07-06T15:09:19Z","links":{"resolver":"https://pith.science/pith/DBCA6VM67DSPQJDMKO3BOIB3HF","bundle":"https://pith.science/pith/DBCA6VM67DSPQJDMKO3BOIB3HF/bundle.json","state":"https://pith.science/pith/DBCA6VM67DSPQJDMKO3BOIB3HF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBCA6VM67DSPQJDMKO3BOIB3HF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DBCA6VM67DSPQJDMKO3BOIB3HF","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":"19ac17ea93cd9d7869730a271a8cf17aad0afb743f0e1156fd116609febc72fc","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-05T10:23:08Z","title_canon_sha256":"0fa94f9b4756ff30fc650da824ceb6ae2e304f6f93e7e450853f2ae16684bf41"},"schema_version":"1.0","source":{"id":"2101.01441","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01441","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01441v1","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01441","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"DBCA6VM67DSP","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"DBCA6VM67DSPQJDM","created_at":"2026-07-05T02:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"DBCA6VM6","created_at":"2026-07-05T02:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:68e05fc1e2a2c16817f97f0efef8a18004fd5348e0d0ef95c98670d55757475a","target":"graph","created_at":"2026-07-05T02:04:33Z","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/2101.01441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning has been proven to be effective in various application areas, such as object and speech recognition on mobile systems. Since a critical key to machine learning success is the availability of large training data, many datasets are being disclosed and published online. From a data consumer or manager point of view, measuring data quality is an important first step in the learning process. We need to determine which datasets to use, update, and maintain. However, not many practical ways to measure data quality are available today, especially when it comes to large-scale high-dime","authors_text":"Hyeongmin Cho, Sangkyun Lee","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-05T10:23:08Z","title":"Data Quality Measures and Efficient Evaluation Algorithms for Large-Scale High-Dimensional Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01441","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:b2ae97b074ea98e4d39ca9230ba101698c5145728d9d1ccfffee531636932812","target":"record","created_at":"2026-07-05T02:04:33Z","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":"19ac17ea93cd9d7869730a271a8cf17aad0afb743f0e1156fd116609febc72fc","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-05T10:23:08Z","title_canon_sha256":"0fa94f9b4756ff30fc650da824ceb6ae2e304f6f93e7e450853f2ae16684bf41"},"schema_version":"1.0","source":{"id":"2101.01441","kind":"arxiv","version":1}},"canonical_sha256":"18440f559ef8e4f8246c53b617203b395a2b2eeef07a604edaa451e9f0822f20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18440f559ef8e4f8246c53b617203b395a2b2eeef07a604edaa451e9f0822f20","first_computed_at":"2026-07-05T02:04:33.186090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:04:33.186090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uyR1YOEExuayjx8x/aTH15LM/tWufcPvudSDCfIPbdofOs7Byd0eneiepWeMRh1Nvnx1u9cULZEFUpgjPqaeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:04:33.186447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.01441","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2ae97b074ea98e4d39ca9230ba101698c5145728d9d1ccfffee531636932812","sha256:68e05fc1e2a2c16817f97f0efef8a18004fd5348e0d0ef95c98670d55757475a"],"state_sha256":"d3b0fc861e9c8d4c5758ff2140fb0204c47def3e270b5f7ced551641e85522c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2hRd8/5xilmR10aGUZaLta1ETFnHiSgEzYf6hRqJILvQaY9DXbYu+Ma2ttuQBKYFJ31xo1BFQTWOEHbTW8FAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:09:19.387558Z","bundle_sha256":"53352e07300c91e6d05113903769e8fe76bfca15b13e8279ccbd490aa620ad1b"}}