{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LVCBKI3RY4FKSD6M7JP2ULZFAT","short_pith_number":"pith:LVCBKI3R","schema_version":"1.0","canonical_sha256":"5d44152371c70aa90fccfa5faa2f2504e9e767c6f65d2dc44971aed3a40a5215","source":{"kind":"arxiv","id":"2605.25210","version":1},"attestation_state":"computed","paper":{"title":"Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanlin Zhu, Haoran Geng, Jitendra Malik, Pieter Abbeel, Somayeh Sojoudi, Xin Guo, Yixiao Huang, Ziheng Cheng","submitted_at":"2026-05-24T18:19:40Z","abstract_excerpt":"Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple environments in robotics with diffusion policies. This naturally leads to a multi-objective learning (MOL) problem. A key challenge is that achieving good Pareto trade-offs can require a generalist model class with substantially larger capacity than what suffices for solving any individual task, thereby increasing statistical cost since sample complexity typ"},"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":"2605.25210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T18:19:40Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ef1f312f15474da1dafaddcd7c0eac8d268d192166b629696979910d9d2a5cd4","abstract_canon_sha256":"97badd419200140e5285ac3dd082604dd381f67423b9225265f8f87be49e61ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:23.523458Z","signature_b64":"6zPUWpVjAaa4gMsHAmhKEl1xeFk6WQAT9fLxmuyhNbhQEhJ2sEwI5FJAM8+AqCL59zjB5BuaxZlMSoZTpvIEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d44152371c70aa90fccfa5faa2f2504e9e767c6f65d2dc44971aed3a40a5215","last_reissued_at":"2026-05-26T02:04:23.522646Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:23.522646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanlin Zhu, Haoran Geng, Jitendra Malik, Pieter Abbeel, Somayeh Sojoudi, Xin Guo, Yixiao Huang, Ziheng Cheng","submitted_at":"2026-05-24T18:19:40Z","abstract_excerpt":"Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple environments in robotics with diffusion policies. This naturally leads to a multi-objective learning (MOL) problem. A key challenge is that achieving good Pareto trade-offs can require a generalist model class with substantially larger capacity than what suffices for solving any individual task, thereby increasing statistical cost since sample complexity typ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25210","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/2605.25210/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":"2605.25210","created_at":"2026-05-26T02:04:23.522758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25210v1","created_at":"2026-05-26T02:04:23.522758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25210","created_at":"2026-05-26T02:04:23.522758+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVCBKI3RY4FK","created_at":"2026-05-26T02:04:23.522758+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVCBKI3RY4FKSD6M","created_at":"2026-05-26T02:04:23.522758+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVCBKI3R","created_at":"2026-05-26T02:04:23.522758+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/LVCBKI3RY4FKSD6M7JP2ULZFAT","json":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT.json","graph_json":"https://pith.science/api/pith-number/LVCBKI3RY4FKSD6M7JP2ULZFAT/graph.json","events_json":"https://pith.science/api/pith-number/LVCBKI3RY4FKSD6M7JP2ULZFAT/events.json","paper":"https://pith.science/paper/LVCBKI3R"},"agent_actions":{"view_html":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT","download_json":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT.json","view_paper":"https://pith.science/paper/LVCBKI3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25210&json=true","fetch_graph":"https://pith.science/api/pith-number/LVCBKI3RY4FKSD6M7JP2ULZFAT/graph.json","fetch_events":"https://pith.science/api/pith-number/LVCBKI3RY4FKSD6M7JP2ULZFAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT/action/storage_attestation","attest_author":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT/action/author_attestation","sign_citation":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT/action/citation_signature","submit_replication":"https://pith.science/pith/LVCBKI3RY4FKSD6M7JP2ULZFAT/action/replication_record"}},"created_at":"2026-05-26T02:04:23.522758+00:00","updated_at":"2026-05-26T02:04:23.522758+00:00"}