{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:X5HLWH7EJAFO5JJQW5ZFT64RY2","short_pith_number":"pith:X5HLWH7E","schema_version":"1.0","canonical_sha256":"bf4ebb1fe4480aeea530b77259fb91c698f43d0a69f1d0d714c7a00ffaf36e47","source":{"kind":"arxiv","id":"2112.03837","version":1},"attestation_state":"computed","paper":{"title":"Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haeju Lee, Joonyoung Kim, Kangwook Lee, Kee-Eung Kim, Oh Joon Kwon, Youngjune Lee","submitted_at":"2021-12-07T17:22:44Z","abstract_excerpt":"Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to address the fundamental distributional and semantic properties of dataset with black box models. For this reason, data-centric approaches are crucial for the automation of machine learning operation pipeline. In order to serve as the basis for this automation, we suggest a domain-agnostic pipeline for refining the quality of data in image classification problems. This pipeline contains data valuation, cleansing, and augme"},"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":"2112.03837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T17:22:44Z","cross_cats_sorted":[],"title_canon_sha256":"7d8ad4337764de275ca351c2f12678817eb413d4b993f784c1d240964ec6ff4f","abstract_canon_sha256":"b2989a4b1ae333cbe62cf72ee879a2319b96fded61b187e24ed4900279f5e6c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:50.322181Z","signature_b64":"Z5wA4mSBEzaqIem4TF2+xw7+PQrW7qacwpf1vo14doLYk1Mdk8YSqowqvXhmsFAPC96QEDPN+5ZRAcdkfUPrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4ebb1fe4480aeea530b77259fb91c698f43d0a69f1d0d714c7a00ffaf36e47","last_reissued_at":"2026-07-05T03:38:50.321799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:50.321799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haeju Lee, Joonyoung Kim, Kangwook Lee, Kee-Eung Kim, Oh Joon Kwon, Youngjune Lee","submitted_at":"2021-12-07T17:22:44Z","abstract_excerpt":"Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to address the fundamental distributional and semantic properties of dataset with black box models. For this reason, data-centric approaches are crucial for the automation of machine learning operation pipeline. In order to serve as the basis for this automation, we suggest a domain-agnostic pipeline for refining the quality of data in image classification problems. This pipeline contains data valuation, cleansing, and augme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03837","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/2112.03837/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":"2112.03837","created_at":"2026-07-05T03:38:50.321856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03837v1","created_at":"2026-07-05T03:38:50.321856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03837","created_at":"2026-07-05T03:38:50.321856+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5HLWH7EJAFO","created_at":"2026-07-05T03:38:50.321856+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5HLWH7EJAFO5JJQ","created_at":"2026-07-05T03:38:50.321856+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5HLWH7E","created_at":"2026-07-05T03:38:50.321856+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/X5HLWH7EJAFO5JJQW5ZFT64RY2","json":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2.json","graph_json":"https://pith.science/api/pith-number/X5HLWH7EJAFO5JJQW5ZFT64RY2/graph.json","events_json":"https://pith.science/api/pith-number/X5HLWH7EJAFO5JJQW5ZFT64RY2/events.json","paper":"https://pith.science/paper/X5HLWH7E"},"agent_actions":{"view_html":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2","download_json":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2.json","view_paper":"https://pith.science/paper/X5HLWH7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03837&json=true","fetch_graph":"https://pith.science/api/pith-number/X5HLWH7EJAFO5JJQW5ZFT64RY2/graph.json","fetch_events":"https://pith.science/api/pith-number/X5HLWH7EJAFO5JJQW5ZFT64RY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/action/storage_attestation","attest_author":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/action/author_attestation","sign_citation":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/action/citation_signature","submit_replication":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/action/replication_record"}},"created_at":"2026-07-05T03:38:50.321856+00:00","updated_at":"2026-07-05T03:38:50.321856+00:00"}