{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z3NB4S2HBXJEPTBW5WJJZZWAEY","short_pith_number":"pith:Z3NB4S2H","canonical_record":{"source":{"id":"2411.10982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T06:37:54Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"f2a02905a004360f6a77c7752dc856e416dbef6a718722e52e9ec034b34e6660","abstract_canon_sha256":"90a4a28941c8f30dcbf6dd538eb188df1c78b251a2c6495dc1a306b9a8fd7d06"},"schema_version":"1.0"},"canonical_sha256":"ceda1e4b470dd247cc36ed929ce6c026001c83a5130442daeba388b3e9729eb0","source":{"kind":"arxiv","id":"2411.10982","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10982","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10982v2","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10982","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"Z3NB4S2HBXJE","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"Z3NB4S2HBXJEPTBW","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"Z3NB4S2H","created_at":"2026-07-05T09:37:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z3NB4S2HBXJEPTBW5WJJZZWAEY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T06:37:54Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"f2a02905a004360f6a77c7752dc856e416dbef6a718722e52e9ec034b34e6660","abstract_canon_sha256":"90a4a28941c8f30dcbf6dd538eb188df1c78b251a2c6495dc1a306b9a8fd7d06"},"schema_version":"1.0"},"canonical_sha256":"ceda1e4b470dd247cc36ed929ce6c026001c83a5130442daeba388b3e9729eb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:58.601632Z","signature_b64":"O+WCxR+cMnXF7uMoM4SS/rRYh0YuVpIxoBS+6SLO2JRbek8Bzt4/4yjQjjabkLbFfpI7bHblv/4q6kvZ295bBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceda1e4b470dd247cc36ed929ce6c026001c83a5130442daeba388b3e9729eb0","last_reissued_at":"2026-07-05T09:37:58.601124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:58.601124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10982","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":"2026-07-05T09:37:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2A0rZtUWPyGbo9LJ/zmP+uWqDXeqhEKyDLaz/y6F+P3iCR28fmDVoiPj5PGEg1bjc+TUVH7qddSZ+zbGU/N5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:27:36.796018Z"},"content_sha256":"4e677a28ec297926443ab0b95694a192ddbecfd94bd853e8197b3b71c60eb115","schema_version":"1.0","event_id":"sha256:4e677a28ec297926443ab0b95694a192ddbecfd94bd853e8197b3b71c60eb115"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z3NB4S2HBXJEPTBW5WJJZZWAEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Agus Sudjianto, Anwesha Bhattacharyya, Arun Prakash R, Joel Vaughan, Maorong Rao, Nengfeng Zhou, Yaqun Wang, Yueyang Shen","submitted_at":"2024-11-17T06:37:54Z","abstract_excerpt":"We propose and study a minimalist approach towards synthetic tabular data generation. The model consists of a minimalistic unsupervised SparsePCA encoder (with contingent clustering step or log transformation to handle nonlinearity) and XGboost decoder which is SOTA for structured data regression and classification tasks. We study and contrast the methodologies with (variational) autoencoders in several toy low dimensional scenarios to derive necessary intuitions. The framework is applied to high dimensional simulated credit scoring data which parallels real-life financial applications. We app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10982","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/2411.10982/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":"2026-07-05T09:37:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjmQit4XjldzyleN04gyGIkygeMGaZNHGXm5gbppxi9h8dyK2rriEfUtoGEAKUrcyTn6xCGxGvv/RWCkZ6+FDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:27:36.796644Z"},"content_sha256":"3ad969f039cbbe791010268679e4e2725e3a371a68b508f6c785c226bc5bd338","schema_version":"1.0","event_id":"sha256:3ad969f039cbbe791010268679e4e2725e3a371a68b508f6c785c226bc5bd338"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY/bundle.json","state_url":"https://pith.science/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY/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":"2026-08-20T04:27:36Z","links":{"resolver":"https://pith.science/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY","bundle":"https://pith.science/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY/bundle.json","state":"https://pith.science/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3NB4S2HBXJEPTBW5WJJZZWAEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z3NB4S2HBXJEPTBW5WJJZZWAEY","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":"90a4a28941c8f30dcbf6dd538eb188df1c78b251a2c6495dc1a306b9a8fd7d06","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T06:37:54Z","title_canon_sha256":"f2a02905a004360f6a77c7752dc856e416dbef6a718722e52e9ec034b34e6660"},"schema_version":"1.0","source":{"id":"2411.10982","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10982","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10982v2","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10982","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"Z3NB4S2HBXJE","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"Z3NB4S2HBXJEPTBW","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"Z3NB4S2H","created_at":"2026-07-05T09:37:58Z"}],"graph_snapshots":[{"event_id":"sha256:3ad969f039cbbe791010268679e4e2725e3a371a68b508f6c785c226bc5bd338","target":"graph","created_at":"2026-07-05T09:37:58Z","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/2411.10982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose and study a minimalist approach towards synthetic tabular data generation. The model consists of a minimalistic unsupervised SparsePCA encoder (with contingent clustering step or log transformation to handle nonlinearity) and XGboost decoder which is SOTA for structured data regression and classification tasks. We study and contrast the methodologies with (variational) autoencoders in several toy low dimensional scenarios to derive necessary intuitions. The framework is applied to high dimensional simulated credit scoring data which parallels real-life financial applications. We app","authors_text":"Agus Sudjianto, Anwesha Bhattacharyya, Arun Prakash R, Joel Vaughan, Maorong Rao, Nengfeng Zhou, Yaqun Wang, Yueyang Shen","cross_cats":["stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T06:37:54Z","title":"Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10982","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":"sha256:4e677a28ec297926443ab0b95694a192ddbecfd94bd853e8197b3b71c60eb115","target":"record","created_at":"2026-07-05T09:37:58Z","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":"90a4a28941c8f30dcbf6dd538eb188df1c78b251a2c6495dc1a306b9a8fd7d06","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T06:37:54Z","title_canon_sha256":"f2a02905a004360f6a77c7752dc856e416dbef6a718722e52e9ec034b34e6660"},"schema_version":"1.0","source":{"id":"2411.10982","kind":"arxiv","version":2}},"canonical_sha256":"ceda1e4b470dd247cc36ed929ce6c026001c83a5130442daeba388b3e9729eb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceda1e4b470dd247cc36ed929ce6c026001c83a5130442daeba388b3e9729eb0","first_computed_at":"2026-07-05T09:37:58.601124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:58.601124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+WCxR+cMnXF7uMoM4SS/rRYh0YuVpIxoBS+6SLO2JRbek8Bzt4/4yjQjjabkLbFfpI7bHblv/4q6kvZ295bBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:58.601632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10982","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e677a28ec297926443ab0b95694a192ddbecfd94bd853e8197b3b71c60eb115","sha256:3ad969f039cbbe791010268679e4e2725e3a371a68b508f6c785c226bc5bd338"],"state_sha256":"1015e1d76190304131ab205e9d7c1c7d81efbf08634e5590167d477e89eefd0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fyh4PkyhTnt8Dyf8ll/MN0JFcm9UePGhWsdUyxWIlBiKj2HHBhncrqTRPb0kk4hwrMA63L2Fcx8AQ74LQRdFCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:27:36.800086Z","bundle_sha256":"d2630d452c2098c06b807765491d2fcb0c451c4cc452e8fae6fa38d3a8e78dd6"}}