{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3USWZBGBZGAUGQBE4ASUD7UKUK","short_pith_number":"pith:3USWZBGB","canonical_record":{"source":{"id":"2210.11327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T15:02:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75f7becb2f65b3e33e14d2834302c7e31b2020006f38b07763fd528eb10cf72e","abstract_canon_sha256":"bc4b9ca0ef69634006e2f5d555cfec6e054e84584d4dacc65a9417d33d54000b"},"schema_version":"1.0"},"canonical_sha256":"dd256c84c1c981434024e02541fe8aa2b34ebba370a916447c21c09fb110364d","source":{"kind":"arxiv","id":"2210.11327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11327","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11327v2","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11327","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"3USWZBGBZGAU","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"3USWZBGBZGAUGQBE","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"3USWZBGB","created_at":"2026-07-05T07:48:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3USWZBGBZGAUGQBE4ASUD7UKUK","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T15:02:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75f7becb2f65b3e33e14d2834302c7e31b2020006f38b07763fd528eb10cf72e","abstract_canon_sha256":"bc4b9ca0ef69634006e2f5d555cfec6e054e84584d4dacc65a9417d33d54000b"},"schema_version":"1.0"},"canonical_sha256":"dd256c84c1c981434024e02541fe8aa2b34ebba370a916447c21c09fb110364d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:15.798692Z","signature_b64":"asTnVG6dsKHeJgG3SkJSahUha036tmw0+Kb7q0rRjC3x5CJiecjCUc+DATV5azBWW1kpazDrM9YRXVORr73uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd256c84c1c981434024e02541fe8aa2b34ebba370a916447c21c09fb110364d","last_reissued_at":"2026-07-05T07:48:15.798194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:15.798194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11327","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":"2026-07-05T07:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05zogUfPrQYQ/f0oKYuXISsYQ+a/gjFJ+zq4zpSiSsJLKynxnz54FnM6/SStl3tQFzB20Mt0CXeGnCg6tOI4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:47:09.133399Z"},"content_sha256":"a623e1cb64e31870751d33e50d21e8b0d44c8bae52064e22208c26fb28e1b01b","schema_version":"1.0","event_id":"sha256:a623e1cb64e31870751d33e50d21e8b0d44c8bae52064e22208c26fb28e1b01b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3USWZBGBZGAUGQBE4ASUD7UKUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Data Quality with Training Dynamics of Gradient Boosting Decision Trees","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Juan Mart\\'in Rom\\'an, Lucas de Angelis Oliveira, Luis Argerich, Mathias Esteban, Moacir Antonelli Ponti, Valentina Garcia","submitted_at":"2022-10-20T15:02:49Z","abstract_excerpt":"Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each example might have different contribution towards learning. This motivates studies to better understanding of the role of data instances with respect to their contribution in good metrics in models. In this paper we propose a method based on metrics computed from training dynamics of Gradient Boosting Decision Trees (GBDTs) to assess the behavior of each training example. We focus on datasets containing mostly tabular o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11327","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/2210.11327/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":"2026-07-05T07:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzP2ReWbzQHl80ZL6E3w1QcRMu4kL0vfUkRVnJmqOoK5/m7y1LOsno4xo9fngsDo799c+IoQ7tw+EZnb4szODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:47:09.134163Z"},"content_sha256":"bb6b4f22d14f9c3d4d25befa09b35298ebd7f1ac0a29375d5457d7df2dca12e3","schema_version":"1.0","event_id":"sha256:bb6b4f22d14f9c3d4d25befa09b35298ebd7f1ac0a29375d5457d7df2dca12e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3USWZBGBZGAUGQBE4ASUD7UKUK/bundle.json","state_url":"https://pith.science/pith/3USWZBGBZGAUGQBE4ASUD7UKUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3USWZBGBZGAUGQBE4ASUD7UKUK/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":"2026-08-18T08:47:09Z","links":{"resolver":"https://pith.science/pith/3USWZBGBZGAUGQBE4ASUD7UKUK","bundle":"https://pith.science/pith/3USWZBGBZGAUGQBE4ASUD7UKUK/bundle.json","state":"https://pith.science/pith/3USWZBGBZGAUGQBE4ASUD7UKUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3USWZBGBZGAUGQBE4ASUD7UKUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3USWZBGBZGAUGQBE4ASUD7UKUK","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":"bc4b9ca0ef69634006e2f5d555cfec6e054e84584d4dacc65a9417d33d54000b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T15:02:49Z","title_canon_sha256":"75f7becb2f65b3e33e14d2834302c7e31b2020006f38b07763fd528eb10cf72e"},"schema_version":"1.0","source":{"id":"2210.11327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11327","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11327v2","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11327","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"3USWZBGBZGAU","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"3USWZBGBZGAUGQBE","created_at":"2026-07-05T07:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"3USWZBGB","created_at":"2026-07-05T07:48:15Z"}],"graph_snapshots":[{"event_id":"sha256:bb6b4f22d14f9c3d4d25befa09b35298ebd7f1ac0a29375d5457d7df2dca12e3","target":"graph","created_at":"2026-07-05T07:48:15Z","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/2210.11327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each example might have different contribution towards learning. This motivates studies to better understanding of the role of data instances with respect to their contribution in good metrics in models. In this paper we propose a method based on metrics computed from training dynamics of Gradient Boosting Decision Trees (GBDTs) to assess the behavior of each training example. We focus on datasets containing mostly tabular o","authors_text":"Juan Mart\\'in Rom\\'an, Lucas de Angelis Oliveira, Luis Argerich, Mathias Esteban, Moacir Antonelli Ponti, Valentina Garcia","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T15:02:49Z","title":"Improving Data Quality with Training Dynamics of Gradient Boosting Decision Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11327","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:a623e1cb64e31870751d33e50d21e8b0d44c8bae52064e22208c26fb28e1b01b","target":"record","created_at":"2026-07-05T07:48:15Z","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":"bc4b9ca0ef69634006e2f5d555cfec6e054e84584d4dacc65a9417d33d54000b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T15:02:49Z","title_canon_sha256":"75f7becb2f65b3e33e14d2834302c7e31b2020006f38b07763fd528eb10cf72e"},"schema_version":"1.0","source":{"id":"2210.11327","kind":"arxiv","version":2}},"canonical_sha256":"dd256c84c1c981434024e02541fe8aa2b34ebba370a916447c21c09fb110364d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd256c84c1c981434024e02541fe8aa2b34ebba370a916447c21c09fb110364d","first_computed_at":"2026-07-05T07:48:15.798194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:15.798194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"asTnVG6dsKHeJgG3SkJSahUha036tmw0+Kb7q0rRjC3x5CJiecjCUc+DATV5azBWW1kpazDrM9YRXVORr73uDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:15.798692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a623e1cb64e31870751d33e50d21e8b0d44c8bae52064e22208c26fb28e1b01b","sha256:bb6b4f22d14f9c3d4d25befa09b35298ebd7f1ac0a29375d5457d7df2dca12e3"],"state_sha256":"ec7495796fe1cc0168f5b03063e4fc143e129abdb7fbb4d9d54ff0bf84ccdbad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6wH5g6ksbF9oJBaXCnRuq/TN96pVbIpGmk03w/22ClisJjT1JiJuGMwtNFazNDKCnEXty4gJmiKm6ZVf5LowAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:47:09.140468Z","bundle_sha256":"9bc353127b145a59ea0172a6e8eb288f5bb741cc25d20a4257e5f269626742e2"}}