{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:X5HLWH7EJAFO5JJQW5ZFT64RY2","short_pith_number":"pith:X5HLWH7E","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"},"canonical_sha256":"bf4ebb1fe4480aeea530b77259fb91c698f43d0a69f1d0d714c7a00ffaf36e47","source":{"kind":"arxiv","id":"2112.03837","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03837","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03837v1","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03837","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"X5HLWH7EJAFO","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"X5HLWH7EJAFO5JJQ","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"X5HLWH7E","created_at":"2026-07-05T03:38:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:X5HLWH7EJAFO5JJQW5ZFT64RY2","target":"record","payload":{"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"},"canonical_sha256":"bf4ebb1fe4480aeea530b77259fb91c698f43d0a69f1d0d714c7a00ffaf36e47","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"},"source_kind":"arxiv","source_id":"2112.03837","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":"2026-07-05T03:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uq8BO/va0Cv0OEw527NLPFaYnrQIXtY4vLhgtMkmYr+qAWXH0qHwei1BiwlCQSUiJ9Qv3bI61gmzP5E8zDUaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T17:31:13.996075Z"},"content_sha256":"7223fc2531d3ddf59e59d63a72677c43ecbead14547240c2afebbc1a2476041b","schema_version":"1.0","event_id":"sha256:7223fc2531d3ddf59e59d63a72677c43ecbead14547240c2afebbc1a2476041b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:X5HLWH7EJAFO5JJQW5ZFT64RY2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odwHCYUsVL41mpb8kxtQiB87/asuj9+Q/oERoUZEJntHukHtfG/T7y8JKFXGZLRo4m5Vwuf4B0SBffktqtYCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T17:31:13.996464Z"},"content_sha256":"0cfa962e6be1e30bee47be46df5c84413223ad17611b09608c7d156e3e386e32","schema_version":"1.0","event_id":"sha256:0cfa962e6be1e30bee47be46df5c84413223ad17611b09608c7d156e3e386e32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/bundle.json","state_url":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/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":"2026-07-26T17:31:13Z","links":{"resolver":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2","bundle":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/bundle.json","state":"https://pith.science/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5HLWH7EJAFO5JJQW5ZFT64RY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X5HLWH7EJAFO5JJQW5ZFT64RY2","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":"b2989a4b1ae333cbe62cf72ee879a2319b96fded61b187e24ed4900279f5e6c1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T17:22:44Z","title_canon_sha256":"7d8ad4337764de275ca351c2f12678817eb413d4b993f784c1d240964ec6ff4f"},"schema_version":"1.0","source":{"id":"2112.03837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03837","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03837v1","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03837","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"X5HLWH7EJAFO","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"X5HLWH7EJAFO5JJQ","created_at":"2026-07-05T03:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"X5HLWH7E","created_at":"2026-07-05T03:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:0cfa962e6be1e30bee47be46df5c84413223ad17611b09608c7d156e3e386e32","target":"graph","created_at":"2026-07-05T03:38:50Z","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/2112.03837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haeju Lee, Joonyoung Kim, Kangwook Lee, Kee-Eung Kim, Oh Joon Kwon, Youngjune Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T17:22:44Z","title":"Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03837","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":"sha256:7223fc2531d3ddf59e59d63a72677c43ecbead14547240c2afebbc1a2476041b","target":"record","created_at":"2026-07-05T03:38:50Z","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":"b2989a4b1ae333cbe62cf72ee879a2319b96fded61b187e24ed4900279f5e6c1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T17:22:44Z","title_canon_sha256":"7d8ad4337764de275ca351c2f12678817eb413d4b993f784c1d240964ec6ff4f"},"schema_version":"1.0","source":{"id":"2112.03837","kind":"arxiv","version":1}},"canonical_sha256":"bf4ebb1fe4480aeea530b77259fb91c698f43d0a69f1d0d714c7a00ffaf36e47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf4ebb1fe4480aeea530b77259fb91c698f43d0a69f1d0d714c7a00ffaf36e47","first_computed_at":"2026-07-05T03:38:50.321799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:50.321799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z5wA4mSBEzaqIem4TF2+xw7+PQrW7qacwpf1vo14doLYk1Mdk8YSqowqvXhmsFAPC96QEDPN+5ZRAcdkfUPrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:50.322181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7223fc2531d3ddf59e59d63a72677c43ecbead14547240c2afebbc1a2476041b","sha256:0cfa962e6be1e30bee47be46df5c84413223ad17611b09608c7d156e3e386e32"],"state_sha256":"8b4ba458330ef9bb315126735e7d2e9406cc38d47b3a3ea8b4c452befa465829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O+WIyR8/0qjviSSGQWT/xWmLcFhydGJ44Unz8WoN7lgvBpaUT9uDr8YmF7VZsQLF7zbDJZT6r9amoKhd16kUCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T17:31:13.998832Z","bundle_sha256":"83c047824387d7b75802d0f25deee18f81d2c5e88b7c2ffd182b6bd6dc654409"}}