{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:S4MU2OGCYCVXBH4LMLPC35ODJD","short_pith_number":"pith:S4MU2OGC","canonical_record":{"source":{"id":"2108.05935","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T19:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"ecf3c260d00b8662520b59b347cec70f607839b261769d97b053214685fdbb03","abstract_canon_sha256":"c99b4ec9c25af6a21fb7bf951396061bbe1ad21b5054783b2608f080c3cc71bf"},"schema_version":"1.0"},"canonical_sha256":"97194d38c2c0ab709f8b62de2df5c348dd15241ee67f67051bc4bc8a3b5c9898","source":{"kind":"arxiv","id":"2108.05935","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05935","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05935v2","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05935","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"pith_short_12","alias_value":"S4MU2OGCYCVX","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"pith_short_16","alias_value":"S4MU2OGCYCVXBH4L","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"pith_short_8","alias_value":"S4MU2OGC","created_at":"2026-07-05T03:11:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:S4MU2OGCYCVXBH4LMLPC35ODJD","target":"record","payload":{"canonical_record":{"source":{"id":"2108.05935","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T19:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"ecf3c260d00b8662520b59b347cec70f607839b261769d97b053214685fdbb03","abstract_canon_sha256":"c99b4ec9c25af6a21fb7bf951396061bbe1ad21b5054783b2608f080c3cc71bf"},"schema_version":"1.0"},"canonical_sha256":"97194d38c2c0ab709f8b62de2df5c348dd15241ee67f67051bc4bc8a3b5c9898","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:32.353149Z","signature_b64":"xfN2/uuxtsYASrd+gWVRtZUicYznRD1ZCjWl8vxmhcz8670SY9gb02RsPFzx0WxIuIGy+7nF33sJAwcVKvvADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97194d38c2c0ab709f8b62de2df5c348dd15241ee67f67051bc4bc8a3b5c9898","last_reissued_at":"2026-07-05T03:11:32.352583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:32.352583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.05935","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:11:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ILuc3zmbo7CygWbkoNgzIfEj2dPbHC71lNxKZhs/oOjOdWwlEV3wQY7NUYiyaKHksn7aA5qFzai1bPV02c/YAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:15:32.123560Z"},"content_sha256":"5f4fe654f2793ed639d89eb598e08c8f64cfc3e379bb4059fbdec53a5c666b33","schema_version":"1.0","event_id":"sha256:5f4fe654f2793ed639d89eb598e08c8f64cfc3e379bb4059fbdec53a5c666b33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:S4MU2OGCYCVXBH4LMLPC35ODJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhinav Jain, Aniya Aggarwal, Diptikalyan Saha, Hima Patel, Lokesh Nagalapatti, Naveen Panwar, Nitin Gupta, Pranay Lohia, Ruhi Sharma Mittal, Sameep Mehta, Sandeep Hans, Shanmukha Guttula, Shazia Afzal","submitted_at":"2021-08-12T19:22:27Z","abstract_excerpt":"The quality of training data has a huge impact on the efficiency, accuracy and complexity of machine learning tasks. Various tools and techniques are available that assess data quality with respect to general cleaning and profiling checks. However these techniques are not applicable to detect data issues in the context of machine learning tasks, like noisy labels, existence of overlapping classes etc. We attempt to re-look at the data quality issues in the context of building a machine learning pipeline and build a tool that can detect, explain and remediate issues in the data, and systematica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05935","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/2108.05935/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":"2026-07-05T03:11:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j8LXOArMXMdBxBnSXNsN0HKUrfMk8CwYQBP9rkH4hELuGGrUJEe2tBtHipjIe+23WKgbaujyC3Y2ryuUdqp3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:15:32.123938Z"},"content_sha256":"7e3ca73939188e9fbdde27700626973859436cf5e54287acf5ecf36fddfeda79","schema_version":"1.0","event_id":"sha256:7e3ca73939188e9fbdde27700626973859436cf5e54287acf5ecf36fddfeda79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S4MU2OGCYCVXBH4LMLPC35ODJD/bundle.json","state_url":"https://pith.science/pith/S4MU2OGCYCVXBH4LMLPC35ODJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S4MU2OGCYCVXBH4LMLPC35ODJD/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":"2026-07-09T02:15:32Z","links":{"resolver":"https://pith.science/pith/S4MU2OGCYCVXBH4LMLPC35ODJD","bundle":"https://pith.science/pith/S4MU2OGCYCVXBH4LMLPC35ODJD/bundle.json","state":"https://pith.science/pith/S4MU2OGCYCVXBH4LMLPC35ODJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S4MU2OGCYCVXBH4LMLPC35ODJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S4MU2OGCYCVXBH4LMLPC35ODJD","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":"c99b4ec9c25af6a21fb7bf951396061bbe1ad21b5054783b2608f080c3cc71bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T19:22:27Z","title_canon_sha256":"ecf3c260d00b8662520b59b347cec70f607839b261769d97b053214685fdbb03"},"schema_version":"1.0","source":{"id":"2108.05935","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05935","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05935v2","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05935","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"pith_short_12","alias_value":"S4MU2OGCYCVX","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"pith_short_16","alias_value":"S4MU2OGCYCVXBH4L","created_at":"2026-07-05T03:11:32Z"},{"alias_kind":"pith_short_8","alias_value":"S4MU2OGC","created_at":"2026-07-05T03:11:32Z"}],"graph_snapshots":[{"event_id":"sha256:7e3ca73939188e9fbdde27700626973859436cf5e54287acf5ecf36fddfeda79","target":"graph","created_at":"2026-07-05T03:11:32Z","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/2108.05935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of training data has a huge impact on the efficiency, accuracy and complexity of machine learning tasks. Various tools and techniques are available that assess data quality with respect to general cleaning and profiling checks. However these techniques are not applicable to detect data issues in the context of machine learning tasks, like noisy labels, existence of overlapping classes etc. We attempt to re-look at the data quality issues in the context of building a machine learning pipeline and build a tool that can detect, explain and remediate issues in the data, and systematica","authors_text":"Abhinav Jain, Aniya Aggarwal, Diptikalyan Saha, Hima Patel, Lokesh Nagalapatti, Naveen Panwar, Nitin Gupta, Pranay Lohia, Ruhi Sharma Mittal, Sameep Mehta, Sandeep Hans, Shanmukha Guttula, Shazia Afzal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T19:22:27Z","title":"Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05935","kind":"arxiv","version":2},"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":"sha256:5f4fe654f2793ed639d89eb598e08c8f64cfc3e379bb4059fbdec53a5c666b33","target":"record","created_at":"2026-07-05T03:11:32Z","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":"c99b4ec9c25af6a21fb7bf951396061bbe1ad21b5054783b2608f080c3cc71bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T19:22:27Z","title_canon_sha256":"ecf3c260d00b8662520b59b347cec70f607839b261769d97b053214685fdbb03"},"schema_version":"1.0","source":{"id":"2108.05935","kind":"arxiv","version":2}},"canonical_sha256":"97194d38c2c0ab709f8b62de2df5c348dd15241ee67f67051bc4bc8a3b5c9898","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97194d38c2c0ab709f8b62de2df5c348dd15241ee67f67051bc4bc8a3b5c9898","first_computed_at":"2026-07-05T03:11:32.352583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:32.352583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xfN2/uuxtsYASrd+gWVRtZUicYznRD1ZCjWl8vxmhcz8670SY9gb02RsPFzx0WxIuIGy+7nF33sJAwcVKvvADA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:32.353149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05935","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f4fe654f2793ed639d89eb598e08c8f64cfc3e379bb4059fbdec53a5c666b33","sha256:7e3ca73939188e9fbdde27700626973859436cf5e54287acf5ecf36fddfeda79"],"state_sha256":"ac7a91e05a05bd64f95ed4d12a977e4927b9ff8e86a31b81d7ebd9a209c84a65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"akwyxuTBBzl5OK+loFLeHXsYa3iu52h6rsf2FNxl3vjflseTjR8qfKRqPOr12TqKQTkEckC7d5QLwQiydHnyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:15:32.126023Z","bundle_sha256":"f46f1a98a8b3cb76d35c0991b97e5781d3c5dd3f361fe9d42d72e4a57f338e67"}}