{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VBTPVQHQWV6ZNNGWG7KCICBVO5","short_pith_number":"pith:VBTPVQHQ","schema_version":"1.0","canonical_sha256":"a866fac0f0b57d96b4d637d4240835777a3beeccc26a0e8a5e3cbdbaa1f27411","source":{"kind":"arxiv","id":"2412.02352","version":1},"attestation_state":"computed","paper":{"title":"LoRA Diffusion: Zero-Shot LoRA Synthesis for Diffusion Model Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Hojel, Ethan Smith, Jianbo Wu, Paramita Mishra, Rami Seid","submitted_at":"2024-12-03T10:17:15Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) and other parameter-efficient fine-tuning (PEFT) methods provide low-memory, storage-efficient solutions for personalizing text-to-image models. However, these methods offer little to no improvement in wall-clock training time or the number of steps needed for convergence compared to full model fine-tuning. While PEFT methods assume that shifts in generated distributions (from base to fine-tuned models) can be effectively modeled through weight changes in a low-rank subspace, they fail to leverage knowledge of common use cases, which typically focus on capturing spec"},"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":"2412.02352","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T10:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"3e14c59d97169ecda8f8b9caaf7b723b5724d5420c603ff1f4e9a43cfa84b5c2","abstract_canon_sha256":"43992251b72933033e4e115962bc9cfe8d480d732bf0b9b3117062b261f2f356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:48.565406Z","signature_b64":"MpJcjl0ynfJ1nuhlkAyOHAp4zmPww0RJSk9BevZTSTQOm0P0Q4/ukaViCHOSkT/75yEjMLufPl4xv78Qdpt1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a866fac0f0b57d96b4d637d4240835777a3beeccc26a0e8a5e3cbdbaa1f27411","last_reissued_at":"2026-07-05T09:43:48.565002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:48.565002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoRA Diffusion: Zero-Shot LoRA Synthesis for Diffusion Model Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Hojel, Ethan Smith, Jianbo Wu, Paramita Mishra, Rami Seid","submitted_at":"2024-12-03T10:17:15Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) and other parameter-efficient fine-tuning (PEFT) methods provide low-memory, storage-efficient solutions for personalizing text-to-image models. However, these methods offer little to no improvement in wall-clock training time or the number of steps needed for convergence compared to full model fine-tuning. While PEFT methods assume that shifts in generated distributions (from base to fine-tuned models) can be effectively modeled through weight changes in a low-rank subspace, they fail to leverage knowledge of common use cases, which typically focus on capturing spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02352","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/2412.02352/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":"2412.02352","created_at":"2026-07-05T09:43:48.565052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02352v1","created_at":"2026-07-05T09:43:48.565052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02352","created_at":"2026-07-05T09:43:48.565052+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBTPVQHQWV6Z","created_at":"2026-07-05T09:43:48.565052+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBTPVQHQWV6ZNNGW","created_at":"2026-07-05T09:43:48.565052+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBTPVQHQ","created_at":"2026-07-05T09:43:48.565052+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/VBTPVQHQWV6ZNNGWG7KCICBVO5","json":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5.json","graph_json":"https://pith.science/api/pith-number/VBTPVQHQWV6ZNNGWG7KCICBVO5/graph.json","events_json":"https://pith.science/api/pith-number/VBTPVQHQWV6ZNNGWG7KCICBVO5/events.json","paper":"https://pith.science/paper/VBTPVQHQ"},"agent_actions":{"view_html":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5","download_json":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5.json","view_paper":"https://pith.science/paper/VBTPVQHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02352&json=true","fetch_graph":"https://pith.science/api/pith-number/VBTPVQHQWV6ZNNGWG7KCICBVO5/graph.json","fetch_events":"https://pith.science/api/pith-number/VBTPVQHQWV6ZNNGWG7KCICBVO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5/action/storage_attestation","attest_author":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5/action/author_attestation","sign_citation":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5/action/citation_signature","submit_replication":"https://pith.science/pith/VBTPVQHQWV6ZNNGWG7KCICBVO5/action/replication_record"}},"created_at":"2026-07-05T09:43:48.565052+00:00","updated_at":"2026-07-05T09:43:48.565052+00:00"}