{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4BA7WURLMLJZJPBHGOUOMHVSNV","short_pith_number":"pith:4BA7WURL","schema_version":"1.0","canonical_sha256":"e041fb522b62d394bc2733a8e61eb26d6aaa04553a16f12f8c09a05714214abb","source":{"kind":"arxiv","id":"1910.07737","version":1},"attestation_state":"computed","paper":{"title":"Autoregressive Models: What Are They Good For?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander C. Li, Murtaza Dalal, Rohan Taori","submitted_at":"2019-10-17T07:04:13Z","abstract_excerpt":"Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates. We investigate the use of AR models as density estimators in two settings -- as a learning signal for image translation, and as an outlier detector -- and find that these density estimates are much less reliable than previously thought. We examine the underlying optimization issues from both an empirical and theoretical perspective, and provide a toy example that illustrates the problem. Overwhelmingly, we find that density estimates do not correlate with percep"},"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":"1910.07737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T07:04:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b1e12cdffd261bb7113e59a0e326d51775cd906d90efb244b112236d7971637","abstract_canon_sha256":"081a95244e156e393f2cb5889983194cf3143d71a525a9187be0629c0e757097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:55.302788Z","signature_b64":"+JFSNFX9YZTQtZwbn27PVB57JKYaR1WQ2h5IXLazEw4vqBAcrtBreJ0nDblLwAcTQs64YJkL0YTmMF0nFl+3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e041fb522b62d394bc2733a8e61eb26d6aaa04553a16f12f8c09a05714214abb","last_reissued_at":"2026-07-05T00:12:55.302399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:55.302399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Models: What Are They Good For?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander C. Li, Murtaza Dalal, Rohan Taori","submitted_at":"2019-10-17T07:04:13Z","abstract_excerpt":"Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates. We investigate the use of AR models as density estimators in two settings -- as a learning signal for image translation, and as an outlier detector -- and find that these density estimates are much less reliable than previously thought. We examine the underlying optimization issues from both an empirical and theoretical perspective, and provide a toy example that illustrates the problem. Overwhelmingly, we find that density estimates do not correlate with percep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07737","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/1910.07737/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":"1910.07737","created_at":"2026-07-05T00:12:55.302457+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.07737v1","created_at":"2026-07-05T00:12:55.302457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07737","created_at":"2026-07-05T00:12:55.302457+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BA7WURLMLJZ","created_at":"2026-07-05T00:12:55.302457+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BA7WURLMLJZJPBH","created_at":"2026-07-05T00:12:55.302457+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BA7WURL","created_at":"2026-07-05T00:12:55.302457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06548","citing_title":"Continuous Latent Diffusion Language Model","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV","json":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV.json","graph_json":"https://pith.science/api/pith-number/4BA7WURLMLJZJPBHGOUOMHVSNV/graph.json","events_json":"https://pith.science/api/pith-number/4BA7WURLMLJZJPBHGOUOMHVSNV/events.json","paper":"https://pith.science/paper/4BA7WURL"},"agent_actions":{"view_html":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV","download_json":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV.json","view_paper":"https://pith.science/paper/4BA7WURL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.07737&json=true","fetch_graph":"https://pith.science/api/pith-number/4BA7WURLMLJZJPBHGOUOMHVSNV/graph.json","fetch_events":"https://pith.science/api/pith-number/4BA7WURLMLJZJPBHGOUOMHVSNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV/action/storage_attestation","attest_author":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV/action/author_attestation","sign_citation":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV/action/citation_signature","submit_replication":"https://pith.science/pith/4BA7WURLMLJZJPBHGOUOMHVSNV/action/replication_record"}},"created_at":"2026-07-05T00:12:55.302457+00:00","updated_at":"2026-07-05T00:12:55.302457+00:00"}