{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4244NEWJA3D5JWIJO4ZUNGUBBB","short_pith_number":"pith:4244NEWJ","schema_version":"1.0","canonical_sha256":"e6b9c692c906c7d4d9097733469a81086a9a6c01011693aa7b247b23bec0e2e8","source":{"kind":"arxiv","id":"2102.09249","version":1},"attestation_state":"computed","paper":{"title":"Composable Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johan Leduc, Nicolas Grislain","submitted_at":"2021-02-18T10:11:29Z","abstract_excerpt":"Generative modeling has recently seen many exciting developments with the advent of deep generative architectures such as Variational Auto-Encoders (VAE) or Generative Adversarial Networks (GAN). The ability to draw synthetic i.i.d. observations with the same joint probability distribution as a given dataset has a wide range of applications including representation learning, compression or imputation. It appears that it also has many applications in privacy preserving data analysis, especially when used in conjunction with differential privacy techniques. This paper focuses on synthetic data g"},"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":"2102.09249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T10:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"bf0f9f680b65971dfe321fc1d29690eae328495741717f3811b321e75026875f","abstract_canon_sha256":"e211bbb1ee0785a87a7b2629b938a750b949eb6a7ebc49d07c93fb334225f637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:20.958515Z","signature_b64":"1XAULD/HH76VA4pz9l/aieszYmNlnp7XLl1F4KF0pm+PCzc+dmZmiO2U58y8Flq0NcxBI0PoIMk3Tnb3yIf8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b9c692c906c7d4d9097733469a81086a9a6c01011693aa7b247b23bec0e2e8","last_reissued_at":"2026-07-05T02:16:20.957979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:20.957979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composable Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johan Leduc, Nicolas Grislain","submitted_at":"2021-02-18T10:11:29Z","abstract_excerpt":"Generative modeling has recently seen many exciting developments with the advent of deep generative architectures such as Variational Auto-Encoders (VAE) or Generative Adversarial Networks (GAN). The ability to draw synthetic i.i.d. observations with the same joint probability distribution as a given dataset has a wide range of applications including representation learning, compression or imputation. It appears that it also has many applications in privacy preserving data analysis, especially when used in conjunction with differential privacy techniques. This paper focuses on synthetic data g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09249","kind":"arxiv","version":1},"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/2102.09249/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":"2102.09249","created_at":"2026-07-05T02:16:20.958052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09249v1","created_at":"2026-07-05T02:16:20.958052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09249","created_at":"2026-07-05T02:16:20.958052+00:00"},{"alias_kind":"pith_short_12","alias_value":"4244NEWJA3D5","created_at":"2026-07-05T02:16:20.958052+00:00"},{"alias_kind":"pith_short_16","alias_value":"4244NEWJA3D5JWIJ","created_at":"2026-07-05T02:16:20.958052+00:00"},{"alias_kind":"pith_short_8","alias_value":"4244NEWJ","created_at":"2026-07-05T02:16:20.958052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06647","citing_title":"Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB","json":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB.json","graph_json":"https://pith.science/api/pith-number/4244NEWJA3D5JWIJO4ZUNGUBBB/graph.json","events_json":"https://pith.science/api/pith-number/4244NEWJA3D5JWIJO4ZUNGUBBB/events.json","paper":"https://pith.science/paper/4244NEWJ"},"agent_actions":{"view_html":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB","download_json":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB.json","view_paper":"https://pith.science/paper/4244NEWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09249&json=true","fetch_graph":"https://pith.science/api/pith-number/4244NEWJA3D5JWIJO4ZUNGUBBB/graph.json","fetch_events":"https://pith.science/api/pith-number/4244NEWJA3D5JWIJO4ZUNGUBBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB/action/storage_attestation","attest_author":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB/action/author_attestation","sign_citation":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB/action/citation_signature","submit_replication":"https://pith.science/pith/4244NEWJA3D5JWIJO4ZUNGUBBB/action/replication_record"}},"created_at":"2026-07-05T02:16:20.958052+00:00","updated_at":"2026-07-05T02:16:20.958052+00:00"}