{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DOWPI2N64BTIHOYZ7QF6C5XWRB","short_pith_number":"pith:DOWPI2N6","schema_version":"1.0","canonical_sha256":"1bacf469bee06683bb19fc0be176f6884bb45bcbac54fb71955561f8cfbbc9d6","source":{"kind":"arxiv","id":"2402.10095","version":3},"attestation_state":"computed","paper":{"title":"Classification Diffusion Models: Revitalizing Density Ratio Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Noam Elata, Shahar Yadin, Tomer Michaeli","submitted_at":"2024-02-15T16:49:42Z","abstract_excerpt":"A prominent family of methods for learning data distributions relies on density ratio estimation (DRE), where a model is trained to $\\textit{classify}$ between data samples and samples from some reference distribution. DRE-based models can directly output the likelihood for any given input, a highly desired property that is lacking in most generative techniques. Nevertheless, to date, DRE methods have failed in accurately capturing the distributions of complex high-dimensional data, like images, and have thus been drawing reduced research attention in recent years. In this work we present $\\te"},"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":"2402.10095","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T16:49:42Z","cross_cats_sorted":[],"title_canon_sha256":"c984112c036e995aed7091eaf525fd97bb3ead5e1487fe853dcfdedbf352df2e","abstract_canon_sha256":"fdc1668db9e66fc4e99b94ee57074153ef576d19df4db072e13eb2ce760bd2d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:13.986974Z","signature_b64":"JgXX3G6VPuuTtotPPDurxk4VB4I3ou2qpJRRmlRq2/zi8Tl/qw8y0pi5mzL9zQMzkbyHJsx5HOrKcwirZ540DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bacf469bee06683bb19fc0be176f6884bb45bcbac54fb71955561f8cfbbc9d6","last_reissued_at":"2026-07-05T09:29:13.986560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:13.986560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification Diffusion Models: Revitalizing Density Ratio Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Noam Elata, Shahar Yadin, Tomer Michaeli","submitted_at":"2024-02-15T16:49:42Z","abstract_excerpt":"A prominent family of methods for learning data distributions relies on density ratio estimation (DRE), where a model is trained to $\\textit{classify}$ between data samples and samples from some reference distribution. DRE-based models can directly output the likelihood for any given input, a highly desired property that is lacking in most generative techniques. Nevertheless, to date, DRE methods have failed in accurately capturing the distributions of complex high-dimensional data, like images, and have thus been drawing reduced research attention in recent years. In this work we present $\\te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10095","kind":"arxiv","version":3},"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/2402.10095/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":"2402.10095","created_at":"2026-07-05T09:29:13.986619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10095v3","created_at":"2026-07-05T09:29:13.986619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10095","created_at":"2026-07-05T09:29:13.986619+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOWPI2N64BTI","created_at":"2026-07-05T09:29:13.986619+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOWPI2N64BTIHOYZ","created_at":"2026-07-05T09:29:13.986619+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOWPI2N6","created_at":"2026-07-05T09:29:13.986619+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/DOWPI2N64BTIHOYZ7QF6C5XWRB","json":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB.json","graph_json":"https://pith.science/api/pith-number/DOWPI2N64BTIHOYZ7QF6C5XWRB/graph.json","events_json":"https://pith.science/api/pith-number/DOWPI2N64BTIHOYZ7QF6C5XWRB/events.json","paper":"https://pith.science/paper/DOWPI2N6"},"agent_actions":{"view_html":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB","download_json":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB.json","view_paper":"https://pith.science/paper/DOWPI2N6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10095&json=true","fetch_graph":"https://pith.science/api/pith-number/DOWPI2N64BTIHOYZ7QF6C5XWRB/graph.json","fetch_events":"https://pith.science/api/pith-number/DOWPI2N64BTIHOYZ7QF6C5XWRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB/action/storage_attestation","attest_author":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB/action/author_attestation","sign_citation":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB/action/citation_signature","submit_replication":"https://pith.science/pith/DOWPI2N64BTIHOYZ7QF6C5XWRB/action/replication_record"}},"created_at":"2026-07-05T09:29:13.986619+00:00","updated_at":"2026-07-05T09:29:13.986619+00:00"}