{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:L6NJFBXDUBJAH2BOZCCF7KMFPS","short_pith_number":"pith:L6NJFBXD","canonical_record":{"source":{"id":"2204.11131","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-23T19:29:23Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"a3a843233b7ae10831d45e7d75ec7b1dcdcfce91b7ddb48571110376d9c18217","abstract_canon_sha256":"2f4be6aac2f4c5d0acfdd9997cec748c7fd884b303f5265421ae36c014bd429e"},"schema_version":"1.0"},"canonical_sha256":"5f9a9286e3a05203e82ec8845fa9857c958a63c12a47d875e0c7446f52864a5f","source":{"kind":"arxiv","id":"2204.11131","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11131","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11131v2","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11131","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"L6NJFBXDUBJA","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"L6NJFBXDUBJAH2BO","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"L6NJFBXD","created_at":"2026-07-05T04:18:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:L6NJFBXDUBJAH2BOZCCF7KMFPS","target":"record","payload":{"canonical_record":{"source":{"id":"2204.11131","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-23T19:29:23Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"a3a843233b7ae10831d45e7d75ec7b1dcdcfce91b7ddb48571110376d9c18217","abstract_canon_sha256":"2f4be6aac2f4c5d0acfdd9997cec748c7fd884b303f5265421ae36c014bd429e"},"schema_version":"1.0"},"canonical_sha256":"5f9a9286e3a05203e82ec8845fa9857c958a63c12a47d875e0c7446f52864a5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:19.099193Z","signature_b64":"kxpEa9YnAfCm423hpJcUdb8aRNcmGw6S+hgYp49DDXY67mANuDiGYzUkAg58bjyEFx/XEyVWAKJVJ29hSB4OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f9a9286e3a05203e82ec8845fa9857c958a63c12a47d875e0c7446f52864a5f","last_reissued_at":"2026-07-05T04:18:19.098712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:19.098712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.11131","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":"2026-07-05T04:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BO08DiaT9s+x5o7YgsVzl/NuDn8iUGnqlSoqzVJQpCn9OFmDkxhhnoyqa5zj5jeoTJFyq1McUfpvo8RoPDGpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:23:49.874532Z"},"content_sha256":"9fc32415bf562eacc0dde500139ffa52550b5d776a83f0984f6d0eae822e260c","schema_version":"1.0","event_id":"sha256:9fc32415bf562eacc0dde500139ffa52550b5d776a83f0984f6d0eae822e260c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:L6NJFBXDUBJAH2BOZCCF7KMFPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Bojan Karla\\v{s}, Bo Li, Ce Zhang, David Dao, Matteo Interlandi, Sebastian Schelter, Wentao Wu","submitted_at":"2022-04-23T19:29:23Z","abstract_excerpt":"Developing modern machine learning (ML) applications is data-centric, of which one fundamental challenge is to understand the influence of data quality to ML training -- \"Which training examples are 'guilty' in making the trained ML model predictions inaccurate or unfair?\" Modeling data influence for ML training has attracted intensive interest over the last decade, and one popular framework is to compute the Shapley value of each training example with respect to utilities such as validation accuracy and fairness of the trained ML model. Unfortunately, despite recent intensive interest and res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11131","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/2204.11131/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":"2026-07-05T04:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mywx/W4AtLxUAGAy45JR0hd2T0yAQy/k83cwoYIOPjgGfF5Id9yTct9sY474RGjCwWqlmd2SyGJvJbATqQYGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:23:49.875037Z"},"content_sha256":"04a9f92051d99b3bdc7bf5f9c08f2363207493f4eb9b0704b6613073cb0dddef","schema_version":"1.0","event_id":"sha256:04a9f92051d99b3bdc7bf5f9c08f2363207493f4eb9b0704b6613073cb0dddef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS/bundle.json","state_url":"https://pith.science/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS/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":"2026-08-08T20:23:49Z","links":{"resolver":"https://pith.science/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS","bundle":"https://pith.science/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS/bundle.json","state":"https://pith.science/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6NJFBXDUBJAH2BOZCCF7KMFPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:L6NJFBXDUBJAH2BOZCCF7KMFPS","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":"2f4be6aac2f4c5d0acfdd9997cec748c7fd884b303f5265421ae36c014bd429e","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-23T19:29:23Z","title_canon_sha256":"a3a843233b7ae10831d45e7d75ec7b1dcdcfce91b7ddb48571110376d9c18217"},"schema_version":"1.0","source":{"id":"2204.11131","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11131","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11131v2","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11131","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"L6NJFBXDUBJA","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"L6NJFBXDUBJAH2BO","created_at":"2026-07-05T04:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"L6NJFBXD","created_at":"2026-07-05T04:18:19Z"}],"graph_snapshots":[{"event_id":"sha256:04a9f92051d99b3bdc7bf5f9c08f2363207493f4eb9b0704b6613073cb0dddef","target":"graph","created_at":"2026-07-05T04:18:19Z","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/2204.11131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing modern machine learning (ML) applications is data-centric, of which one fundamental challenge is to understand the influence of data quality to ML training -- \"Which training examples are 'guilty' in making the trained ML model predictions inaccurate or unfair?\" Modeling data influence for ML training has attracted intensive interest over the last decade, and one popular framework is to compute the Shapley value of each training example with respect to utilities such as validation accuracy and fairness of the trained ML model. Unfortunately, despite recent intensive interest and res","authors_text":"Bojan Karla\\v{s}, Bo Li, Ce Zhang, David Dao, Matteo Interlandi, Sebastian Schelter, Wentao Wu","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-23T19:29:23Z","title":"Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11131","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":"sha256:9fc32415bf562eacc0dde500139ffa52550b5d776a83f0984f6d0eae822e260c","target":"record","created_at":"2026-07-05T04:18:19Z","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":"2f4be6aac2f4c5d0acfdd9997cec748c7fd884b303f5265421ae36c014bd429e","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-23T19:29:23Z","title_canon_sha256":"a3a843233b7ae10831d45e7d75ec7b1dcdcfce91b7ddb48571110376d9c18217"},"schema_version":"1.0","source":{"id":"2204.11131","kind":"arxiv","version":2}},"canonical_sha256":"5f9a9286e3a05203e82ec8845fa9857c958a63c12a47d875e0c7446f52864a5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f9a9286e3a05203e82ec8845fa9857c958a63c12a47d875e0c7446f52864a5f","first_computed_at":"2026-07-05T04:18:19.098712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:19.098712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kxpEa9YnAfCm423hpJcUdb8aRNcmGw6S+hgYp49DDXY67mANuDiGYzUkAg58bjyEFx/XEyVWAKJVJ29hSB4OBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:19.099193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.11131","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fc32415bf562eacc0dde500139ffa52550b5d776a83f0984f6d0eae822e260c","sha256:04a9f92051d99b3bdc7bf5f9c08f2363207493f4eb9b0704b6613073cb0dddef"],"state_sha256":"4d2431ce5b7df4bccf84dfad646b1317a538f1b7957bf95d36e33beac2200244"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7y+ad+bkjz1/OUbrcyYWbZaWe3O1++g3Or7LL/D8DHd3pTaKKzuvRbZZ676rmgTSCf2pgUNXhmWDPv59OmKlBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:23:49.878444Z","bundle_sha256":"06aed2e8ec4d008918f62b998f868ed1755f4da54d877764de82565f94879e33"}}