{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JVNSEV74DPY3OEZFMUQL7N3KNG","short_pith_number":"pith:JVNSEV74","schema_version":"1.0","canonical_sha256":"4d5b2257fc1bf1b713256520bfb76a69b94883f107cc6c76b0053300c1ba9898","source":{"kind":"arxiv","id":"2106.06989","version":2},"attestation_state":"computed","paper":{"title":"The DEformer: An Order-Agnostic Distribution Estimating Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anh Nguyen, Michael A. Alcorn","submitted_at":"2021-06-13T13:33:31Z","abstract_excerpt":"Order-agnostic autoregressive distribution (density) estimation (OADE), i.e., autoregressive distribution estimation where the features can occur in an arbitrary order, is a challenging problem in generative machine learning. Prior work on OADE has encoded feature identity by assigning each feature to a distinct fixed position in an input vector. As a result, architectures built for these inputs must strategically mask either the input or model weights to learn the various conditional distributions necessary for inferring the full joint distribution of the dataset in an order-agnostic way. In "},"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":"2106.06989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:33:31Z","cross_cats_sorted":[],"title_canon_sha256":"8d9f247b62e458edf15dd6f3dea7b933985b13714f65c9f70cb10a7f6f86ba9e","abstract_canon_sha256":"b940f81e6780eaa53c6c75aecf00c59dec437ff603fefc419101b0e3d2b293bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:58.555301Z","signature_b64":"dKN7ZIewvaaK4t/NLuFtpBahnUW+T83Z6BZIdNVcB/DNsQVgYKUbWYr6Z/baZ1h+SmRw7PY/5d7L+m+A/twyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d5b2257fc1bf1b713256520bfb76a69b94883f107cc6c76b0053300c1ba9898","last_reissued_at":"2026-07-05T02:56:58.554793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:58.554793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The DEformer: An Order-Agnostic Distribution Estimating Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anh Nguyen, Michael A. Alcorn","submitted_at":"2021-06-13T13:33:31Z","abstract_excerpt":"Order-agnostic autoregressive distribution (density) estimation (OADE), i.e., autoregressive distribution estimation where the features can occur in an arbitrary order, is a challenging problem in generative machine learning. Prior work on OADE has encoded feature identity by assigning each feature to a distinct fixed position in an input vector. As a result, architectures built for these inputs must strategically mask either the input or model weights to learn the various conditional distributions necessary for inferring the full joint distribution of the dataset in an order-agnostic way. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06989","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/2106.06989/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":"2106.06989","created_at":"2026-07-05T02:56:58.554870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06989v2","created_at":"2026-07-05T02:56:58.554870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06989","created_at":"2026-07-05T02:56:58.554870+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVNSEV74DPY3","created_at":"2026-07-05T02:56:58.554870+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVNSEV74DPY3OEZF","created_at":"2026-07-05T02:56:58.554870+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVNSEV74","created_at":"2026-07-05T02:56:58.554870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01444","citing_title":"Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG","json":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG.json","graph_json":"https://pith.science/api/pith-number/JVNSEV74DPY3OEZFMUQL7N3KNG/graph.json","events_json":"https://pith.science/api/pith-number/JVNSEV74DPY3OEZFMUQL7N3KNG/events.json","paper":"https://pith.science/paper/JVNSEV74"},"agent_actions":{"view_html":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG","download_json":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG.json","view_paper":"https://pith.science/paper/JVNSEV74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06989&json=true","fetch_graph":"https://pith.science/api/pith-number/JVNSEV74DPY3OEZFMUQL7N3KNG/graph.json","fetch_events":"https://pith.science/api/pith-number/JVNSEV74DPY3OEZFMUQL7N3KNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG/action/storage_attestation","attest_author":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG/action/author_attestation","sign_citation":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG/action/citation_signature","submit_replication":"https://pith.science/pith/JVNSEV74DPY3OEZFMUQL7N3KNG/action/replication_record"}},"created_at":"2026-07-05T02:56:58.554870+00:00","updated_at":"2026-07-05T02:56:58.554870+00:00"}