{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WZX36C43GZC32WCN2YP2IQ5V42","short_pith_number":"pith:WZX36C43","schema_version":"1.0","canonical_sha256":"b66fbf0b9b3645bd584dd61fa443b5e6a47e02d622f33e6f24ba28df629ce128","source":{"kind":"arxiv","id":"2410.03941","version":1},"attestation_state":"computed","paper":{"title":"AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Artur Kasymov, Maciej Zi\\k{e}ba, Marcin Sendera, Micha{\\l} Stypu{\\l}kowski, Przemys{\\l}aw Spurek","submitted_at":"2024-10-04T21:57:11Z","abstract_excerpt":"Low-rank adaptation (LoRA) is a fine-tuning technique that can be applied to conditional generative diffusion models. LoRA utilizes a small number of context examples to adapt the model to a specific domain, character, style, or concept. However, due to the limited data utilized during training, the fine-tuned model performance is often characterized by strong context bias and a low degree of variability in the generated images. To solve this issue, we introduce AutoLoRA, a novel guidance technique for diffusion models fine-tuned with the LoRA approach. Inspired by other guidance techniques, A"},"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":"2410.03941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T21:57:11Z","cross_cats_sorted":[],"title_canon_sha256":"122a64f223f914176afcde45c3afdefd19544243b240dcc719c755ab88ebbcd5","abstract_canon_sha256":"7105cef306923574da1a1aaabba62167a7def0e97b3ded1f12ed19242e8b1183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:26.767374Z","signature_b64":"VMHY43DpBUHDicdSeC46862ZNIQpr66ltMGzja1MFsSIpN8ATyWqfMNb0RL5YJe27kDVYqekTxblLAia3uvmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b66fbf0b9b3645bd584dd61fa443b5e6a47e02d622f33e6f24ba28df629ce128","last_reissued_at":"2026-07-05T09:16:26.766846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:26.766846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Artur Kasymov, Maciej Zi\\k{e}ba, Marcin Sendera, Micha{\\l} Stypu{\\l}kowski, Przemys{\\l}aw Spurek","submitted_at":"2024-10-04T21:57:11Z","abstract_excerpt":"Low-rank adaptation (LoRA) is a fine-tuning technique that can be applied to conditional generative diffusion models. LoRA utilizes a small number of context examples to adapt the model to a specific domain, character, style, or concept. However, due to the limited data utilized during training, the fine-tuned model performance is often characterized by strong context bias and a low degree of variability in the generated images. To solve this issue, we introduce AutoLoRA, a novel guidance technique for diffusion models fine-tuned with the LoRA approach. Inspired by other guidance techniques, A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03941","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/2410.03941/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":"2410.03941","created_at":"2026-07-05T09:16:26.766903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03941v1","created_at":"2026-07-05T09:16:26.766903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03941","created_at":"2026-07-05T09:16:26.766903+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZX36C43GZC3","created_at":"2026-07-05T09:16:26.766903+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZX36C43GZC32WCN","created_at":"2026-07-05T09:16:26.766903+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZX36C43","created_at":"2026-07-05T09:16:26.766903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23727","citing_title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42","json":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42.json","graph_json":"https://pith.science/api/pith-number/WZX36C43GZC32WCN2YP2IQ5V42/graph.json","events_json":"https://pith.science/api/pith-number/WZX36C43GZC32WCN2YP2IQ5V42/events.json","paper":"https://pith.science/paper/WZX36C43"},"agent_actions":{"view_html":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42","download_json":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42.json","view_paper":"https://pith.science/paper/WZX36C43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03941&json=true","fetch_graph":"https://pith.science/api/pith-number/WZX36C43GZC32WCN2YP2IQ5V42/graph.json","fetch_events":"https://pith.science/api/pith-number/WZX36C43GZC32WCN2YP2IQ5V42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42/action/storage_attestation","attest_author":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42/action/author_attestation","sign_citation":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42/action/citation_signature","submit_replication":"https://pith.science/pith/WZX36C43GZC32WCN2YP2IQ5V42/action/replication_record"}},"created_at":"2026-07-05T09:16:26.766903+00:00","updated_at":"2026-07-05T09:16:26.766903+00:00"}