{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LTOPQUWJAP5MLZ7E5MMMPQEC5N","short_pith_number":"pith:LTOPQUWJ","canonical_record":{"source":{"id":"2112.06409","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T03:57:36Z","cross_cats_sorted":[],"title_canon_sha256":"a24fe6cf794f6b6284561b8a4e8651e729b3bd78f5262246785c8b5fd8116543","abstract_canon_sha256":"1848e623c127493214c2c241a578bdc92cbd8d1c8b16a81e3bd95373f7200c12"},"schema_version":"1.0"},"canonical_sha256":"5cdcf852c903fac5e7e4eb18c7c082eb5c88e664b309f6e4f1eab120f6c99164","source":{"kind":"arxiv","id":"2112.06409","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06409","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06409v3","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06409","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"LTOPQUWJAP5M","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"LTOPQUWJAP5MLZ7E","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"LTOPQUWJ","created_at":"2026-07-05T05:28:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LTOPQUWJAP5MLZ7E5MMMPQEC5N","target":"record","payload":{"canonical_record":{"source":{"id":"2112.06409","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T03:57:36Z","cross_cats_sorted":[],"title_canon_sha256":"a24fe6cf794f6b6284561b8a4e8651e729b3bd78f5262246785c8b5fd8116543","abstract_canon_sha256":"1848e623c127493214c2c241a578bdc92cbd8d1c8b16a81e3bd95373f7200c12"},"schema_version":"1.0"},"canonical_sha256":"5cdcf852c903fac5e7e4eb18c7c082eb5c88e664b309f6e4f1eab120f6c99164","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:05.705664Z","signature_b64":"SuIcr9B+XaG29u7CHoLDrpPI7u5yvApL2MNQlrbT3MA/O/o+d2Fm7diOpW5HZPO/ydDXDPRA7GgKzotOS8CPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cdcf852c903fac5e7e4eb18c7c082eb5c88e664b309f6e4f1eab120f6c99164","last_reissued_at":"2026-07-05T05:28:05.705229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:05.705229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.06409","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/A2dEG76jy9S3VrbXvmyOo3lG+SabNLDpa6xU6Iy/R8lbqhy8FUJO53wp5v8c7HEVV/wcIrzGJ3Ym612GbMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:20:38.985922Z"},"content_sha256":"85adf1d21a879d62a75cec55068a8e014771aa14e00c829bbf1b6b959f0352a3","schema_version":"1.0","event_id":"sha256:85adf1d21a879d62a75cec55068a8e014771aa14e00c829bbf1b6b959f0352a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LTOPQUWJAP5MLZ7E5MMMPQEC5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hwanjun Song, Jae-Gil Lee, Steven Euijong Whang, Yuji Roh","submitted_at":"2021-12-13T03:57:36Z","abstract_excerpt":"Data-centric AI is at the center of a fundamental shift in software engineering where machine learning becomes the new software, powered by big data and computing infrastructure. Here software engineering needs to be re-thought where data becomes a first-class citizen on par with code. One striking observation is that a significant portion of the machine learning process is spent on data preparation. Without good data, even the best machine learning algorithms cannot perform well. As a result, data-centric AI practices are now becoming mainstream. Unfortunately, many datasets in the real world"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06409","kind":"arxiv","version":3},"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/2112.06409/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":"2026-07-05T05:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sE08xo5tBF3965EuOXx9zi5/oRgE8dJ46NYacKvvN3dmb/5oUPcRC+lfaXS3seqvM9dNOUKMOx6KPGW4E3upAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:20:38.986411Z"},"content_sha256":"97ff87fb9e052de7346c9e48f723ce83f4590e88300b612f5edec8a7abf2e584","schema_version":"1.0","event_id":"sha256:97ff87fb9e052de7346c9e48f723ce83f4590e88300b612f5edec8a7abf2e584"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N/bundle.json","state_url":"https://pith.science/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N/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":"2026-08-08T07:20:38Z","links":{"resolver":"https://pith.science/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N","bundle":"https://pith.science/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N/bundle.json","state":"https://pith.science/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTOPQUWJAP5MLZ7E5MMMPQEC5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LTOPQUWJAP5MLZ7E5MMMPQEC5N","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":"1848e623c127493214c2c241a578bdc92cbd8d1c8b16a81e3bd95373f7200c12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T03:57:36Z","title_canon_sha256":"a24fe6cf794f6b6284561b8a4e8651e729b3bd78f5262246785c8b5fd8116543"},"schema_version":"1.0","source":{"id":"2112.06409","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06409","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06409v3","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06409","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"LTOPQUWJAP5M","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"LTOPQUWJAP5MLZ7E","created_at":"2026-07-05T05:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"LTOPQUWJ","created_at":"2026-07-05T05:28:05Z"}],"graph_snapshots":[{"event_id":"sha256:97ff87fb9e052de7346c9e48f723ce83f4590e88300b612f5edec8a7abf2e584","target":"graph","created_at":"2026-07-05T05:28:05Z","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/2112.06409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-centric AI is at the center of a fundamental shift in software engineering where machine learning becomes the new software, powered by big data and computing infrastructure. Here software engineering needs to be re-thought where data becomes a first-class citizen on par with code. One striking observation is that a significant portion of the machine learning process is spent on data preparation. Without good data, even the best machine learning algorithms cannot perform well. As a result, data-centric AI practices are now becoming mainstream. Unfortunately, many datasets in the real world","authors_text":"Hwanjun Song, Jae-Gil Lee, Steven Euijong Whang, Yuji Roh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T03:57:36Z","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06409","kind":"arxiv","version":3},"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":"sha256:85adf1d21a879d62a75cec55068a8e014771aa14e00c829bbf1b6b959f0352a3","target":"record","created_at":"2026-07-05T05:28:05Z","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":"1848e623c127493214c2c241a578bdc92cbd8d1c8b16a81e3bd95373f7200c12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T03:57:36Z","title_canon_sha256":"a24fe6cf794f6b6284561b8a4e8651e729b3bd78f5262246785c8b5fd8116543"},"schema_version":"1.0","source":{"id":"2112.06409","kind":"arxiv","version":3}},"canonical_sha256":"5cdcf852c903fac5e7e4eb18c7c082eb5c88e664b309f6e4f1eab120f6c99164","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cdcf852c903fac5e7e4eb18c7c082eb5c88e664b309f6e4f1eab120f6c99164","first_computed_at":"2026-07-05T05:28:05.705229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:28:05.705229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SuIcr9B+XaG29u7CHoLDrpPI7u5yvApL2MNQlrbT3MA/O/o+d2Fm7diOpW5HZPO/ydDXDPRA7GgKzotOS8CPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:28:05.705664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06409","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85adf1d21a879d62a75cec55068a8e014771aa14e00c829bbf1b6b959f0352a3","sha256:97ff87fb9e052de7346c9e48f723ce83f4590e88300b612f5edec8a7abf2e584"],"state_sha256":"b98d2f04432cedb14230da0d884eefd1cdfa39e8e7e3c987ff894807387ddd93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k37vLT/wx4dJyzXtS1WBIs221CBXKQ5F36PAms7aq7J3WrzhmKcTpD93XL8Y1JkNNe5tX2g7lqE9957p85hvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:20:38.990876Z","bundle_sha256":"c1db78255eaf384a4ad88dab6ac6572d6e3306593f02791fbd338a9cb5cd17c0"}}