{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T23F4EVK3NZTFVRCBCY5GI43CK","short_pith_number":"pith:T23F4EVK","schema_version":"1.0","canonical_sha256":"9eb65e12aadb7332d62208b1d3239b1282aa9ff61255caa03c474c5585e6343e","source":{"kind":"arxiv","id":"2004.02441","version":2},"attestation_state":"computed","paper":{"title":"TraDE: Transformers for Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander J. Smola, Jonas Mueller, Pratik Chaudhari, Rasool Fakoor","submitted_at":"2020-04-06T07:32:51Z","abstract_excerpt":"We present TraDE, a self-attention-based architecture for auto-regressive density estimation with continuous and discrete valued data. Our model is trained using a penalized maximum likelihood objective, which ensures that samples from the density estimate resemble the training data distribution. The use of self-attention means that the model need not retain conditional sufficient statistics during the auto-regressive process beyond what is needed for each covariate. On standard tabular and image data benchmarks, TraDE produces significantly better density estimates than existing approaches su"},"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":"2004.02441","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-06T07:32:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7991e0796c051043162334f81d6cb9b57edf120b21015b2ec99e4a68c2fc1cd5","abstract_canon_sha256":"dc1d5a901603d1290abbb9077a6a732abefc35431aeaab7ab305eca1b7f8d88e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:05.127938Z","signature_b64":"uDNHkm+D9t+AV1KUuaYhkjSVk7mA8XnPBdZjIhD37yK/llx14ik7rIiPWpUYFoizM4Go7IQzgp7lZv96Xp6kAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb65e12aadb7332d62208b1d3239b1282aa9ff61255caa03c474c5585e6343e","last_reissued_at":"2026-07-05T01:43:05.127552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:05.127552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TraDE: Transformers for Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander J. Smola, Jonas Mueller, Pratik Chaudhari, Rasool Fakoor","submitted_at":"2020-04-06T07:32:51Z","abstract_excerpt":"We present TraDE, a self-attention-based architecture for auto-regressive density estimation with continuous and discrete valued data. Our model is trained using a penalized maximum likelihood objective, which ensures that samples from the density estimate resemble the training data distribution. The use of self-attention means that the model need not retain conditional sufficient statistics during the auto-regressive process beyond what is needed for each covariate. On standard tabular and image data benchmarks, TraDE produces significantly better density estimates than existing approaches su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02441","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/2004.02441/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":"2004.02441","created_at":"2026-07-05T01:43:05.127612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02441v2","created_at":"2026-07-05T01:43:05.127612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02441","created_at":"2026-07-05T01:43:05.127612+00:00"},{"alias_kind":"pith_short_12","alias_value":"T23F4EVK3NZT","created_at":"2026-07-05T01:43:05.127612+00:00"},{"alias_kind":"pith_short_16","alias_value":"T23F4EVK3NZTFVRC","created_at":"2026-07-05T01:43:05.127612+00:00"},{"alias_kind":"pith_short_8","alias_value":"T23F4EVK","created_at":"2026-07-05T01:43:05.127612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK","json":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK.json","graph_json":"https://pith.science/api/pith-number/T23F4EVK3NZTFVRCBCY5GI43CK/graph.json","events_json":"https://pith.science/api/pith-number/T23F4EVK3NZTFVRCBCY5GI43CK/events.json","paper":"https://pith.science/paper/T23F4EVK"},"agent_actions":{"view_html":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK","download_json":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK.json","view_paper":"https://pith.science/paper/T23F4EVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02441&json=true","fetch_graph":"https://pith.science/api/pith-number/T23F4EVK3NZTFVRCBCY5GI43CK/graph.json","fetch_events":"https://pith.science/api/pith-number/T23F4EVK3NZTFVRCBCY5GI43CK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK/action/storage_attestation","attest_author":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK/action/author_attestation","sign_citation":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK/action/citation_signature","submit_replication":"https://pith.science/pith/T23F4EVK3NZTFVRCBCY5GI43CK/action/replication_record"}},"created_at":"2026-07-05T01:43:05.127612+00:00","updated_at":"2026-07-05T01:43:05.127612+00:00"}