{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EKQPGE2IXGSDHQQX5KQ73IK4L5","short_pith_number":"pith:EKQPGE2I","canonical_record":{"source":{"id":"2407.05593","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T04:15:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"922ed00247da8b5093bf4b84e86a495e8488e8c06e5d88b4b2a55c3755efa0d3","abstract_canon_sha256":"c45bff1d007a7762b671834482decd519616186b807c39b63b9c2d8aa89c75bf"},"schema_version":"1.0"},"canonical_sha256":"22a0f31348b9a433c217eaa1fda15c5f6bf9997687cfeab302e4b93a382cac53","source":{"kind":"arxiv","id":"2407.05593","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05593","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05593v5","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05593","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"pith_short_12","alias_value":"EKQPGE2IXGSD","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"pith_short_16","alias_value":"EKQPGE2IXGSDHQQX","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"pith_short_8","alias_value":"EKQPGE2I","created_at":"2026-07-05T11:41:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EKQPGE2IXGSDHQQX5KQ73IK4L5","target":"record","payload":{"canonical_record":{"source":{"id":"2407.05593","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T04:15:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"922ed00247da8b5093bf4b84e86a495e8488e8c06e5d88b4b2a55c3755efa0d3","abstract_canon_sha256":"c45bff1d007a7762b671834482decd519616186b807c39b63b9c2d8aa89c75bf"},"schema_version":"1.0"},"canonical_sha256":"22a0f31348b9a433c217eaa1fda15c5f6bf9997687cfeab302e4b93a382cac53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:34.736361Z","signature_b64":"gy9jtugOhZIku8ua8fuKpqI8zu5x7CoxZDJUK28NdxI2WE/JBFqmst5YF7d57n1gJ89FGC4dqUaol3EsfMK6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22a0f31348b9a433c217eaa1fda15c5f6bf9997687cfeab302e4b93a382cac53","last_reissued_at":"2026-07-05T11:41:34.735878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:34.735878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.05593","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:41:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1diNXSgZFzjzmrzBzmTM+i6cy+e1c8/q2Kcjh9PHkMkwV385G1YaFqFNvNGdVU8sQb9/kL91jgDb0yDUF9jdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:28:03.933590Z"},"content_sha256":"f45b7727fbc267da9d65b47d0352edf28d1865fd61065b5bfe01ed5486ce27ea","schema_version":"1.0","event_id":"sha256:f45b7727fbc267da9d65b47d0352edf28d1865fd61065b5bfe01ed5486ce27ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EKQPGE2IXGSDHQQX5KQ73IK4L5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unmasking Trees for Tabular Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Calvin McCarter","submitted_at":"2024-07-08T04:15:43Z","abstract_excerpt":"Despite much work on advanced deep learning and generative modeling techniques for tabular data generation and imputation, traditional methods have continued to win on imputation benchmarks. We herein present UnmaskingTrees, a simple method for tabular imputation (and generation) employing gradient-boosted decision trees which are used to incrementally unmask individual features. On a benchmark for out-of-the-box performance on 27 small tabular datasets, UnmaskingTrees offers leading performance on imputation; state-of-the-art performance on generation given data with missingness; and competit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05593","kind":"arxiv","version":5},"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/2407.05593/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":"2026-07-05T11:41:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgfx5IRZWq7ASzUijRO6iKyzDmO8vO+4PlmBoVs2XpLwyeihZ8T8qxD15big087V9EAqdG664bQ3i1WdF9WsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:28:03.934090Z"},"content_sha256":"78fc9d4607cfa61635c3eeb4900c62d7c17b2ffc2c75d33b7060eed030889844","schema_version":"1.0","event_id":"sha256:78fc9d4607cfa61635c3eeb4900c62d7c17b2ffc2c75d33b7060eed030889844"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5/bundle.json","state_url":"https://pith.science/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5/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":"2026-08-18T18:28:03Z","links":{"resolver":"https://pith.science/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5","bundle":"https://pith.science/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5/bundle.json","state":"https://pith.science/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKQPGE2IXGSDHQQX5KQ73IK4L5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EKQPGE2IXGSDHQQX5KQ73IK4L5","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":"c45bff1d007a7762b671834482decd519616186b807c39b63b9c2d8aa89c75bf","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T04:15:43Z","title_canon_sha256":"922ed00247da8b5093bf4b84e86a495e8488e8c06e5d88b4b2a55c3755efa0d3"},"schema_version":"1.0","source":{"id":"2407.05593","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05593","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05593v5","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05593","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"pith_short_12","alias_value":"EKQPGE2IXGSD","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"pith_short_16","alias_value":"EKQPGE2IXGSDHQQX","created_at":"2026-07-05T11:41:34Z"},{"alias_kind":"pith_short_8","alias_value":"EKQPGE2I","created_at":"2026-07-05T11:41:34Z"}],"graph_snapshots":[{"event_id":"sha256:78fc9d4607cfa61635c3eeb4900c62d7c17b2ffc2c75d33b7060eed030889844","target":"graph","created_at":"2026-07-05T11:41:34Z","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/2407.05593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite much work on advanced deep learning and generative modeling techniques for tabular data generation and imputation, traditional methods have continued to win on imputation benchmarks. We herein present UnmaskingTrees, a simple method for tabular imputation (and generation) employing gradient-boosted decision trees which are used to incrementally unmask individual features. On a benchmark for out-of-the-box performance on 27 small tabular datasets, UnmaskingTrees offers leading performance on imputation; state-of-the-art performance on generation given data with missingness; and competit","authors_text":"Calvin McCarter","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T04:15:43Z","title":"Unmasking Trees for Tabular Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05593","kind":"arxiv","version":5},"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:f45b7727fbc267da9d65b47d0352edf28d1865fd61065b5bfe01ed5486ce27ea","target":"record","created_at":"2026-07-05T11:41:34Z","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":"c45bff1d007a7762b671834482decd519616186b807c39b63b9c2d8aa89c75bf","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T04:15:43Z","title_canon_sha256":"922ed00247da8b5093bf4b84e86a495e8488e8c06e5d88b4b2a55c3755efa0d3"},"schema_version":"1.0","source":{"id":"2407.05593","kind":"arxiv","version":5}},"canonical_sha256":"22a0f31348b9a433c217eaa1fda15c5f6bf9997687cfeab302e4b93a382cac53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22a0f31348b9a433c217eaa1fda15c5f6bf9997687cfeab302e4b93a382cac53","first_computed_at":"2026-07-05T11:41:34.735878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:34.735878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gy9jtugOhZIku8ua8fuKpqI8zu5x7CoxZDJUK28NdxI2WE/JBFqmst5YF7d57n1gJ89FGC4dqUaol3EsfMK6Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:34.736361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05593","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f45b7727fbc267da9d65b47d0352edf28d1865fd61065b5bfe01ed5486ce27ea","sha256:78fc9d4607cfa61635c3eeb4900c62d7c17b2ffc2c75d33b7060eed030889844"],"state_sha256":"c64717121c5b27bdea887a6bfd94444db0353537ad3775f3239b124d3f669ebb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SN6WjTj+TLcYscwyytxhxGAl+roJn/0BfWfcfNe7CP7O1gzgPC8lXY0DNHjDQJo3am9Pt6VEiOKjUAeqMAfzDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:28:03.937457Z","bundle_sha256":"69345b558b2b94af9c63f5a418fcb619073fcc7bf3268a45fabb8c22f6c177ed"}}