{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:264DXOCGCNJSFP27AMHNCDCYDU","short_pith_number":"pith:264DXOCG","canonical_record":{"source":{"id":"2506.02811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T12:42:20Z","cross_cats_sorted":[],"title_canon_sha256":"3deb5468a3cdcf284287ba214086241bac76744de27686e510660100f4bc2a50","abstract_canon_sha256":"46591185b6365df2d61ce877d3a20cd4068129695400b6dbbcfb747ac6033c54"},"schema_version":"1.0"},"canonical_sha256":"d7b83bb846135322bf5f030ed10c581d01bc46379a5f9e209b1b9d5a20e1522c","source":{"kind":"arxiv","id":"2506.02811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02811","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02811v2","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02811","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"pith_short_12","alias_value":"264DXOCGCNJS","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"pith_short_16","alias_value":"264DXOCGCNJSFP27","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"pith_short_8","alias_value":"264DXOCG","created_at":"2026-06-30T00:15:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:264DXOCGCNJSFP27AMHNCDCYDU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T12:42:20Z","cross_cats_sorted":[],"title_canon_sha256":"3deb5468a3cdcf284287ba214086241bac76744de27686e510660100f4bc2a50","abstract_canon_sha256":"46591185b6365df2d61ce877d3a20cd4068129695400b6dbbcfb747ac6033c54"},"schema_version":"1.0"},"canonical_sha256":"d7b83bb846135322bf5f030ed10c581d01bc46379a5f9e209b1b9d5a20e1522c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:07.392546Z","signature_b64":"5dygLxtYbZDK29rAwhnbkDHzE2IAvI1/jOjoB7CLAJz117PnuX9ohAqkeBAm9M7kA3H7IOnocHc6AXnhIspxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b83bb846135322bf5f030ed10c581d01bc46379a5f9e209b1b9d5a20e1522c","last_reissued_at":"2026-06-30T00:15:07.392071Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:07.392071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02811","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":"2026-06-30T00:15:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jJe/29ampDNKAjUeOcd2vlZT83tPRF9VsFw25U5EzS/JL49VqXvYIdM2/FqxLatgej4UdYcqfdPxIxycG2UqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:21:24.404219Z"},"content_sha256":"967722784bee80a0e7ff44ab4becb877732c8efd0ef10d6eb53c505d525f0ac8","schema_version":"1.0","event_id":"sha256:967722784bee80a0e7ff44ab4becb877732c8efd0ef10d6eb53c505d525f0ac8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:264DXOCGCNJSFP27AMHNCDCYDU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CARTGen-IR: Synthetic Tabular Data Generation for Imbalanced Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ant\\'onio Pedro Pinheiro, Rita P. Ribeiro","submitted_at":"2025-06-03T12:42:20Z","abstract_excerpt":"Handling imbalanced target distributions in regression poses a persistent challenge, as the underrepresentation of relevant target values can significantly hinder model performance. Existing data-level solutions often adapt classification-oriented techniques, introducing arbitrary thresholds over the continuous target and leading to artificial and potentially misleading problem formulations. Deep generative models offer flexible sample synthesis but are computationally intensive and difficult to interpret. We propose a CART-based synthetic sampling method specifically designed for imbalanced r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02811","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/2506.02811/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":"2026-06-30T00:15:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5o8zwsHhwPvAaJy0Z/9cYguDI02dr7NeHQo536DpLph4dctEFfu6/9QO4e8cDSicJ/CVnc4g7X5z/pRgnhljBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:21:24.404788Z"},"content_sha256":"983c56428d01f16956fc9f575b5817f088dfd4a47e3a7a8d8e3e032acd5f08e3","schema_version":"1.0","event_id":"sha256:983c56428d01f16956fc9f575b5817f088dfd4a47e3a7a8d8e3e032acd5f08e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/264DXOCGCNJSFP27AMHNCDCYDU/bundle.json","state_url":"https://pith.science/pith/264DXOCGCNJSFP27AMHNCDCYDU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/264DXOCGCNJSFP27AMHNCDCYDU/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":"2026-08-07T23:21:24Z","links":{"resolver":"https://pith.science/pith/264DXOCGCNJSFP27AMHNCDCYDU","bundle":"https://pith.science/pith/264DXOCGCNJSFP27AMHNCDCYDU/bundle.json","state":"https://pith.science/pith/264DXOCGCNJSFP27AMHNCDCYDU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/264DXOCGCNJSFP27AMHNCDCYDU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:264DXOCGCNJSFP27AMHNCDCYDU","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":"46591185b6365df2d61ce877d3a20cd4068129695400b6dbbcfb747ac6033c54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T12:42:20Z","title_canon_sha256":"3deb5468a3cdcf284287ba214086241bac76744de27686e510660100f4bc2a50"},"schema_version":"1.0","source":{"id":"2506.02811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02811","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02811v2","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02811","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"pith_short_12","alias_value":"264DXOCGCNJS","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"pith_short_16","alias_value":"264DXOCGCNJSFP27","created_at":"2026-06-30T00:15:07Z"},{"alias_kind":"pith_short_8","alias_value":"264DXOCG","created_at":"2026-06-30T00:15:07Z"}],"graph_snapshots":[{"event_id":"sha256:983c56428d01f16956fc9f575b5817f088dfd4a47e3a7a8d8e3e032acd5f08e3","target":"graph","created_at":"2026-06-30T00:15:07Z","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/2506.02811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Handling imbalanced target distributions in regression poses a persistent challenge, as the underrepresentation of relevant target values can significantly hinder model performance. Existing data-level solutions often adapt classification-oriented techniques, introducing arbitrary thresholds over the continuous target and leading to artificial and potentially misleading problem formulations. Deep generative models offer flexible sample synthesis but are computationally intensive and difficult to interpret. We propose a CART-based synthetic sampling method specifically designed for imbalanced r","authors_text":"Ant\\'onio Pedro Pinheiro, Rita P. Ribeiro","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T12:42:20Z","title":"CARTGen-IR: Synthetic Tabular Data Generation for Imbalanced Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02811","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":"sha256:967722784bee80a0e7ff44ab4becb877732c8efd0ef10d6eb53c505d525f0ac8","target":"record","created_at":"2026-06-30T00:15:07Z","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":"46591185b6365df2d61ce877d3a20cd4068129695400b6dbbcfb747ac6033c54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T12:42:20Z","title_canon_sha256":"3deb5468a3cdcf284287ba214086241bac76744de27686e510660100f4bc2a50"},"schema_version":"1.0","source":{"id":"2506.02811","kind":"arxiv","version":2}},"canonical_sha256":"d7b83bb846135322bf5f030ed10c581d01bc46379a5f9e209b1b9d5a20e1522c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7b83bb846135322bf5f030ed10c581d01bc46379a5f9e209b1b9d5a20e1522c","first_computed_at":"2026-06-30T00:15:07.392071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:07.392071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5dygLxtYbZDK29rAwhnbkDHzE2IAvI1/jOjoB7CLAJz117PnuX9ohAqkeBAm9M7kA3H7IOnocHc6AXnhIspxDg==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:07.392546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:967722784bee80a0e7ff44ab4becb877732c8efd0ef10d6eb53c505d525f0ac8","sha256:983c56428d01f16956fc9f575b5817f088dfd4a47e3a7a8d8e3e032acd5f08e3"],"state_sha256":"5be07a49b7ab2eec0115cbde2fb55890d86c679d7109c2059fa70c68ff3478a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PyEbFnAHigHI35FdIE2dfMnNV0BaWkoFrK07m7woEZCMd39rEoaFBpAs5CMpEKsaXf5R3Wou3HsmLOO6T1sBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:21:24.410740Z","bundle_sha256":"39ccd2f85e70081823de0fa772c4789703a15951d78d7f9eedde1ef1970e368b"}}