{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ALPKNNUBR3X2YT45F5ECA6R2GM","short_pith_number":"pith:ALPKNNUB","schema_version":"1.0","canonical_sha256":"02dea6b6818eefac4f9d2f48207a3a330a5e61251b0d7d3218db73cc8c88ab73","source":{"kind":"arxiv","id":"2412.17622","version":2},"attestation_state":"computed","paper":{"title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cheuk Ting Li, Farzan Farnia, Parham Rezaei","submitted_at":"2024-12-23T14:48:17Z","abstract_excerpt":"The availability of multiple training algorithms and architectures for generative models requires a selection mechanism to form a single model over a group of well-trained generation models. The selection task is commonly addressed by identifying the model that maximizes an evaluation score based on the diversity and quality of the generated data. However, such a best-model identification approach overlooks the possibility that a mixture of available models can outperform each individual model. In this work, we numerically show that a mixture of generative models on benchmark image datasets ca"},"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":"2412.17622","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T14:48:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae56d24577e14aba5686cc0f136cf0109884c3e28ff0c93b3fee3a5e121d827b","abstract_canon_sha256":"364388c27ab33ad332f01fa8a060e035f4901e865fc89fe7683823badddd8d4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:41.185973Z","signature_b64":"NrMmiP8h/bOZDphV0Vk+4qyVQQxKg00+b7v0lm7u423wQUqGn8WzvlI8tDqUlcQcmaJLJ+x2pFe7QFQinqXuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02dea6b6818eefac4f9d2f48207a3a330a5e61251b0d7d3218db73cc8c88ab73","last_reissued_at":"2026-07-05T10:37:41.185404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:41.185404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cheuk Ting Li, Farzan Farnia, Parham Rezaei","submitted_at":"2024-12-23T14:48:17Z","abstract_excerpt":"The availability of multiple training algorithms and architectures for generative models requires a selection mechanism to form a single model over a group of well-trained generation models. The selection task is commonly addressed by identifying the model that maximizes an evaluation score based on the diversity and quality of the generated data. However, such a best-model identification approach overlooks the possibility that a mixture of available models can outperform each individual model. In this work, we numerically show that a mixture of generative models on benchmark image datasets ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17622","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/2412.17622/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":"2412.17622","created_at":"2026-07-05T10:37:41.185462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17622v2","created_at":"2026-07-05T10:37:41.185462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17622","created_at":"2026-07-05T10:37:41.185462+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALPKNNUBR3X2","created_at":"2026-07-05T10:37:41.185462+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALPKNNUBR3X2YT45","created_at":"2026-07-05T10:37:41.185462+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALPKNNUB","created_at":"2026-07-05T10:37:41.185462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02557","citing_title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM","json":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM.json","graph_json":"https://pith.science/api/pith-number/ALPKNNUBR3X2YT45F5ECA6R2GM/graph.json","events_json":"https://pith.science/api/pith-number/ALPKNNUBR3X2YT45F5ECA6R2GM/events.json","paper":"https://pith.science/paper/ALPKNNUB"},"agent_actions":{"view_html":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM","download_json":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM.json","view_paper":"https://pith.science/paper/ALPKNNUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17622&json=true","fetch_graph":"https://pith.science/api/pith-number/ALPKNNUBR3X2YT45F5ECA6R2GM/graph.json","fetch_events":"https://pith.science/api/pith-number/ALPKNNUBR3X2YT45F5ECA6R2GM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM/action/storage_attestation","attest_author":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM/action/author_attestation","sign_citation":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM/action/citation_signature","submit_replication":"https://pith.science/pith/ALPKNNUBR3X2YT45F5ECA6R2GM/action/replication_record"}},"created_at":"2026-07-05T10:37:41.185462+00:00","updated_at":"2026-07-05T10:37:41.185462+00:00"}