{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OLIQVWRQNY3PWHHUILY3U2IYAL","short_pith_number":"pith:OLIQVWRQ","schema_version":"1.0","canonical_sha256":"72d10ada306e36fb1cf442f1ba691802d83111cc315f2723d19bb9f9a4b09841","source":{"kind":"arxiv","id":"2312.03011","version":2},"attestation_state":"computed","paper":{"title":"InstructBooth: Instruction-following Personalized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daewon Chae, Jinkyu Kim, Kimin Lee, Nokyung Park","submitted_at":"2023-12-04T20:34:46Z","abstract_excerpt":"Personalizing text-to-image models using a limited set of images for a specific object has been explored in subject-specific image generation. However, existing methods often face challenges in aligning with text prompts due to overfitting to the limited training images. In this work, we introduce InstructBooth, a novel method designed to enhance image-text alignment in personalized text-to-image models without sacrificing the personalization ability. Our approach first personalizes text-to-image models with a small number of subject-specific images using a unique identifier. After personaliza"},"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":"2312.03011","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T20:34:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93bce3de619589d596906c4a699c1b07ab282290ac2e356d8427e4d319963e96","abstract_canon_sha256":"a3302716a09b1cf37b6a3c2069034b7deedc1a3e83107a4f5dbe1eb728d35f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:31.334125Z","signature_b64":"z9pGuPLRp7Jvq88lRkud1xnFszXWQlMRbcXJ1dlZdRogz76HVMKmCIb3n+K94z30/2/tDfT5spwKGdBiXe8NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72d10ada306e36fb1cf442f1ba691802d83111cc315f2723d19bb9f9a4b09841","last_reissued_at":"2026-07-05T07:45:31.333625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:31.333625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructBooth: Instruction-following Personalized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daewon Chae, Jinkyu Kim, Kimin Lee, Nokyung Park","submitted_at":"2023-12-04T20:34:46Z","abstract_excerpt":"Personalizing text-to-image models using a limited set of images for a specific object has been explored in subject-specific image generation. However, existing methods often face challenges in aligning with text prompts due to overfitting to the limited training images. In this work, we introduce InstructBooth, a novel method designed to enhance image-text alignment in personalized text-to-image models without sacrificing the personalization ability. Our approach first personalizes text-to-image models with a small number of subject-specific images using a unique identifier. After personaliza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03011","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/2312.03011/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":"2312.03011","created_at":"2026-07-05T07:45:31.333686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03011v2","created_at":"2026-07-05T07:45:31.333686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03011","created_at":"2026-07-05T07:45:31.333686+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLIQVWRQNY3P","created_at":"2026-07-05T07:45:31.333686+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLIQVWRQNY3PWHHU","created_at":"2026-07-05T07:45:31.333686+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLIQVWRQ","created_at":"2026-07-05T07:45:31.333686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10029","citing_title":"Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL","json":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL.json","graph_json":"https://pith.science/api/pith-number/OLIQVWRQNY3PWHHUILY3U2IYAL/graph.json","events_json":"https://pith.science/api/pith-number/OLIQVWRQNY3PWHHUILY3U2IYAL/events.json","paper":"https://pith.science/paper/OLIQVWRQ"},"agent_actions":{"view_html":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL","download_json":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL.json","view_paper":"https://pith.science/paper/OLIQVWRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03011&json=true","fetch_graph":"https://pith.science/api/pith-number/OLIQVWRQNY3PWHHUILY3U2IYAL/graph.json","fetch_events":"https://pith.science/api/pith-number/OLIQVWRQNY3PWHHUILY3U2IYAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL/action/storage_attestation","attest_author":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL/action/author_attestation","sign_citation":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL/action/citation_signature","submit_replication":"https://pith.science/pith/OLIQVWRQNY3PWHHUILY3U2IYAL/action/replication_record"}},"created_at":"2026-07-05T07:45:31.333686+00:00","updated_at":"2026-07-05T07:45:31.333686+00:00"}