{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4D5ZXTJHUAYASOIJH33VQFRG7I","short_pith_number":"pith:4D5ZXTJH","canonical_record":{"source":{"id":"2304.13761","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-04-26T18:04:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af8f891c2fd26126ca77ac3368a584798413a9655485d2aa5b556a31849d5851","abstract_canon_sha256":"e59220936e43ab82b4484eaa050c7468386b6bd859916cc9ef86599f14443c7a"},"schema_version":"1.0"},"canonical_sha256":"e0fb9bcd27a0300939093ef7581626fa1bcf4cc497dedf5afa9a2ccbe6fc7272","source":{"kind":"arxiv","id":"2304.13761","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13761","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13761v3","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13761","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"4D5ZXTJHUAYA","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"4D5ZXTJHUAYASOIJ","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"4D5ZXTJH","created_at":"2026-07-05T06:09:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4D5ZXTJHUAYASOIJH33VQFRG7I","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13761","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-04-26T18:04:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af8f891c2fd26126ca77ac3368a584798413a9655485d2aa5b556a31849d5851","abstract_canon_sha256":"e59220936e43ab82b4484eaa050c7468386b6bd859916cc9ef86599f14443c7a"},"schema_version":"1.0"},"canonical_sha256":"e0fb9bcd27a0300939093ef7581626fa1bcf4cc497dedf5afa9a2ccbe6fc7272","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:09.883838Z","signature_b64":"YHdFe7HrA2/Q1pjGb2K3EiC8R5bfvlYhdm2VYjySoEoOzeks3FEUvTJ4uk6XZL1AlJ1smhRJCzmRQa4d5Wu4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0fb9bcd27a0300939093ef7581626fa1bcf4cc497dedf5afa9a2ccbe6fc7272","last_reissued_at":"2026-07-05T06:09:09.883361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:09.883361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13761","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sunDPfXpWOcVoVcrM5gJoFb3uPc9T6+VLbL4+lwQ18s/rGPl6Y5+SvCnpTI7+MZyDrwbc6bZhUbStTwhyW8zBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:27:46.582888Z"},"content_sha256":"89f9abdbcec0373dbf311d4165551887f07f4ff18a075e6fde9e7b1d4fa42c29","schema_version":"1.0","event_id":"sha256:89f9abdbcec0373dbf311d4165551887f07f4ff18a075e6fde9e7b1d4fa42c29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4D5ZXTJHUAYASOIJH33VQFRG7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Robustness of Gradient-Boosted Decision Trees through One-Hot Encoding and Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Agus Sudjianto, Aijun Zhang, Runze Li, Shijie Cui","submitted_at":"2023-04-26T18:04:16Z","abstract_excerpt":"Gradient-boosted decision trees (GBDT) are widely used and highly effective machine learning approach for tabular data modeling. However, their complex structure may lead to low robustness against small covariate perturbation in unseen data. In this study, we apply one-hot encoding to convert a GBDT model into a linear framework, through encoding of each tree leaf to one dummy variable. This allows for the use of linear regression techniques, plus a novel risk decomposition for assessing the robustness of a GBDT model against covariate perturbations. We propose to enhance the robustness of GBD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13761","kind":"arxiv","version":3},"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/2304.13761/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":"2026-07-05T06:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5QRV1WQMqSQ82jkgOc7H5hA5z1c729NBn/DxsBtVf+OagyIIQ8FCBP7TOp/C8/DSq83QAx0vtx/EQHSk/JdWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:27:46.583263Z"},"content_sha256":"eb9a04ace54125f2595a04ce05846ee6d5eb1ecc364ec1645e3952c6ef84d159","schema_version":"1.0","event_id":"sha256:eb9a04ace54125f2595a04ce05846ee6d5eb1ecc364ec1645e3952c6ef84d159"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4D5ZXTJHUAYASOIJH33VQFRG7I/bundle.json","state_url":"https://pith.science/pith/4D5ZXTJHUAYASOIJH33VQFRG7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4D5ZXTJHUAYASOIJH33VQFRG7I/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":"2026-08-19T21:27:46Z","links":{"resolver":"https://pith.science/pith/4D5ZXTJHUAYASOIJH33VQFRG7I","bundle":"https://pith.science/pith/4D5ZXTJHUAYASOIJH33VQFRG7I/bundle.json","state":"https://pith.science/pith/4D5ZXTJHUAYASOIJH33VQFRG7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4D5ZXTJHUAYASOIJH33VQFRG7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4D5ZXTJHUAYASOIJH33VQFRG7I","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":"e59220936e43ab82b4484eaa050c7468386b6bd859916cc9ef86599f14443c7a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-04-26T18:04:16Z","title_canon_sha256":"af8f891c2fd26126ca77ac3368a584798413a9655485d2aa5b556a31849d5851"},"schema_version":"1.0","source":{"id":"2304.13761","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13761","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13761v3","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13761","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"4D5ZXTJHUAYA","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"4D5ZXTJHUAYASOIJ","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"4D5ZXTJH","created_at":"2026-07-05T06:09:09Z"}],"graph_snapshots":[{"event_id":"sha256:eb9a04ace54125f2595a04ce05846ee6d5eb1ecc364ec1645e3952c6ef84d159","target":"graph","created_at":"2026-07-05T06:09:09Z","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/2304.13761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient-boosted decision trees (GBDT) are widely used and highly effective machine learning approach for tabular data modeling. However, their complex structure may lead to low robustness against small covariate perturbation in unseen data. In this study, we apply one-hot encoding to convert a GBDT model into a linear framework, through encoding of each tree leaf to one dummy variable. This allows for the use of linear regression techniques, plus a novel risk decomposition for assessing the robustness of a GBDT model against covariate perturbations. We propose to enhance the robustness of GBD","authors_text":"Agus Sudjianto, Aijun Zhang, Runze Li, Shijie Cui","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-04-26T18:04:16Z","title":"Enhancing Robustness of Gradient-Boosted Decision Trees through One-Hot Encoding and Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13761","kind":"arxiv","version":3},"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":"sha256:89f9abdbcec0373dbf311d4165551887f07f4ff18a075e6fde9e7b1d4fa42c29","target":"record","created_at":"2026-07-05T06:09:09Z","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":"e59220936e43ab82b4484eaa050c7468386b6bd859916cc9ef86599f14443c7a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-04-26T18:04:16Z","title_canon_sha256":"af8f891c2fd26126ca77ac3368a584798413a9655485d2aa5b556a31849d5851"},"schema_version":"1.0","source":{"id":"2304.13761","kind":"arxiv","version":3}},"canonical_sha256":"e0fb9bcd27a0300939093ef7581626fa1bcf4cc497dedf5afa9a2ccbe6fc7272","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0fb9bcd27a0300939093ef7581626fa1bcf4cc497dedf5afa9a2ccbe6fc7272","first_computed_at":"2026-07-05T06:09:09.883361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:09.883361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YHdFe7HrA2/Q1pjGb2K3EiC8R5bfvlYhdm2VYjySoEoOzeks3FEUvTJ4uk6XZL1AlJ1smhRJCzmRQa4d5Wu4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:09.883838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13761","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89f9abdbcec0373dbf311d4165551887f07f4ff18a075e6fde9e7b1d4fa42c29","sha256:eb9a04ace54125f2595a04ce05846ee6d5eb1ecc364ec1645e3952c6ef84d159"],"state_sha256":"8dc873758d577505bbbed981d2d81c9fd763b970f7d5094f06c09dab4f6adf56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TDfDEJyyUz1OMmpVfJWKKBPmktfG8LwJc37C1X/pTGfTR0ufOmYAYloEZGPt6yyNzVPOVD25NWApzzLRDut3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:27:46.586781Z","bundle_sha256":"db807a25c86ad00420fef4cbcc01714a6144a16f765f39c0f7ed86d819b43450"}}