{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q6WGSB7VKR2FOO6ZVK3HMLPUZ6","short_pith_number":"pith:Q6WGSB7V","schema_version":"1.0","canonical_sha256":"87ac6907f55474573bd9aab6762df4cf973a0a8516278da08ae65123c39df9ce","source":{"kind":"arxiv","id":"2209.15421","version":2},"attestation_state":"computed","paper":{"title":"TabDDPM: Modelling Tabular Data with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akim Kotelnikov, Artem Babenko, Dmitry Baranchuk, Ivan Rubachev","submitted_at":"2022-09-30T12:26:14Z","abstract_excerpt":"Denoising diffusion probabilistic models are currently becoming the leading paradigm of generative modeling for many important data modalities. Being the most prevalent in the computer vision community, diffusion models have also recently gained some attention in other domains, including speech, NLP, and graph-like data. In this work, we investigate if the framework of diffusion models can be advantageous for general tabular problems, where datapoints are typically represented by vectors of heterogeneous features. The inherent heterogeneity of tabular data makes it quite challenging for accura"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.15421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T12:26:14Z","cross_cats_sorted":[],"title_canon_sha256":"5827d6ef4f71f3acf48863e06754b897516398b564a30a6fb11b0c3733b4901c","abstract_canon_sha256":"6567ec067ae965132f9ab340076e59e4af03d701d14d034021b4666bf05e0618"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:43.230215Z","signature_b64":"NbZ5DPZwK3/tMRbVoCnobREpHehMkpUBOzyWx5m47J5xYew2hRsvoDbVOX0S2t9MgHUkTvucH0/qXFsjcxWPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87ac6907f55474573bd9aab6762df4cf973a0a8516278da08ae65123c39df9ce","last_reissued_at":"2026-07-05T09:16:43.229741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:43.229741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabDDPM: Modelling Tabular Data with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akim Kotelnikov, Artem Babenko, Dmitry Baranchuk, Ivan Rubachev","submitted_at":"2022-09-30T12:26:14Z","abstract_excerpt":"Denoising diffusion probabilistic models are currently becoming the leading paradigm of generative modeling for many important data modalities. Being the most prevalent in the computer vision community, diffusion models have also recently gained some attention in other domains, including speech, NLP, and graph-like data. In this work, we investigate if the framework of diffusion models can be advantageous for general tabular problems, where datapoints are typically represented by vectors of heterogeneous features. The inherent heterogeneity of tabular data makes it quite challenging for accura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15421","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/2209.15421/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.15421","created_at":"2026-07-05T09:16:43.229792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15421v2","created_at":"2026-07-05T09:16:43.229792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15421","created_at":"2026-07-05T09:16:43.229792+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6WGSB7VKR2F","created_at":"2026-07-05T09:16:43.229792+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6WGSB7VKR2FOO6Z","created_at":"2026-07-05T09:16:43.229792+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6WGSB7V","created_at":"2026-07-05T09:16:43.229792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31904","citing_title":"Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03251","citing_title":"Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2305.18593","citing_title":"On Diffusion Modeling for Anomaly Detection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08875","citing_title":"When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05257","citing_title":"Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16817","citing_title":"Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22688","citing_title":"COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC","ref_index":161,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6","json":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6.json","graph_json":"https://pith.science/api/pith-number/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/graph.json","events_json":"https://pith.science/api/pith-number/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/events.json","paper":"https://pith.science/paper/Q6WGSB7V"},"agent_actions":{"view_html":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6","download_json":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6.json","view_paper":"https://pith.science/paper/Q6WGSB7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15421&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/action/storage_attestation","attest_author":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/action/author_attestation","sign_citation":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/action/citation_signature","submit_replication":"https://pith.science/pith/Q6WGSB7VKR2FOO6ZVK3HMLPUZ6/action/replication_record"}},"created_at":"2026-07-05T09:16:43.229792+00:00","updated_at":"2026-07-05T09:16:43.229792+00:00"}