{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2PO6ZGLU64DVLJP3U2D6BXCA4Y","short_pith_number":"pith:2PO6ZGLU","schema_version":"1.0","canonical_sha256":"d3ddec9974f70755a5fba687e0dc40e606f030ec7ac8ab352f071fd51593fe5a","source":{"kind":"arxiv","id":"2301.12334","version":2},"attestation_state":"computed","paper":{"title":"Don't Play Favorites: Minority Guidance for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jong Chul Ye, Soobin Um, Suhyeon Lee","submitted_at":"2023-01-29T03:08:47Z","abstract_excerpt":"We explore the problem of generating minority samples using diffusion models. The minority samples are instances that lie on low-density regions of a data manifold. Generating a sufficient number of such minority instances is important, since they often contain some unique attributes of the data. However, the conventional generation process of the diffusion models mostly yields majority samples (that lie on high-density regions of the manifold) due to their high likelihoods, making themselves ineffective and time-consuming for the minority generating task. In this work, we present a novel fram"},"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":"2301.12334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T03:08:47Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"8184834d6872660e00c99072762ca7ce634cac167a2850d3afe4ff4b956eb586","abstract_canon_sha256":"c840b58f95e7d7991c5a5bfd64675ae57399d3351a5c8e9d92492429b24e9f58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:10.997645Z","signature_b64":"T0a2JUBjoXgogD/YdSgWpNr28Xd+hB3y5OIEvMX98hp1TMZvg96lw9DXEoIXivWk9sWq0bQ4A8NrlOo8inHfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3ddec9974f70755a5fba687e0dc40e606f030ec7ac8ab352f071fd51593fe5a","last_reissued_at":"2026-07-05T07:49:10.997206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:10.997206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Play Favorites: Minority Guidance for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jong Chul Ye, Soobin Um, Suhyeon Lee","submitted_at":"2023-01-29T03:08:47Z","abstract_excerpt":"We explore the problem of generating minority samples using diffusion models. The minority samples are instances that lie on low-density regions of a data manifold. Generating a sufficient number of such minority instances is important, since they often contain some unique attributes of the data. However, the conventional generation process of the diffusion models mostly yields majority samples (that lie on high-density regions of the manifold) due to their high likelihoods, making themselves ineffective and time-consuming for the minority generating task. In this work, we present a novel fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12334","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/2301.12334/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":"2301.12334","created_at":"2026-07-05T07:49:10.997265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12334v2","created_at":"2026-07-05T07:49:10.997265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12334","created_at":"2026-07-05T07:49:10.997265+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PO6ZGLU64DV","created_at":"2026-07-05T07:49:10.997265+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PO6ZGLU64DVLJP3","created_at":"2026-07-05T07:49:10.997265+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PO6ZGLU","created_at":"2026-07-05T07:49:10.997265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20299","citing_title":"Mechanisms of Misgeneralization in Physical Sequence Modeling","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y","json":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y.json","graph_json":"https://pith.science/api/pith-number/2PO6ZGLU64DVLJP3U2D6BXCA4Y/graph.json","events_json":"https://pith.science/api/pith-number/2PO6ZGLU64DVLJP3U2D6BXCA4Y/events.json","paper":"https://pith.science/paper/2PO6ZGLU"},"agent_actions":{"view_html":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y","download_json":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y.json","view_paper":"https://pith.science/paper/2PO6ZGLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12334&json=true","fetch_graph":"https://pith.science/api/pith-number/2PO6ZGLU64DVLJP3U2D6BXCA4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2PO6ZGLU64DVLJP3U2D6BXCA4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y/action/storage_attestation","attest_author":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y/action/author_attestation","sign_citation":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y/action/citation_signature","submit_replication":"https://pith.science/pith/2PO6ZGLU64DVLJP3U2D6BXCA4Y/action/replication_record"}},"created_at":"2026-07-05T07:49:10.997265+00:00","updated_at":"2026-07-05T07:49:10.997265+00:00"}