{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G5N4F7VR4S7HOT5ZXFU3YA7Z5P","short_pith_number":"pith:G5N4F7VR","schema_version":"1.0","canonical_sha256":"375bc2feb1e4be774fb9b969bc03f9ebf4de216bb1d0c0796c9eb6026a29cac7","source":{"kind":"arxiv","id":"2409.08248","version":2},"attestation_state":"computed","paper":{"title":"TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Kunhee Kim, NaHyeon Park","submitted_at":"2024-09-12T17:47:51Z","abstract_excerpt":"In this paper, we introduce TextBoost, an efficient one-shot personalization approach for text-to-image diffusion models. Traditional personalization methods typically involve fine-tuning extensive portions of the model, leading to substantial storage requirements and slow convergence. In contrast, we propose selectively fine-tuning only the text encoder, significantly improving computational and storage efficiency. To preserve the original semantic integrity, we develop a novel causality-preserving adaptation mechanism. Additionally, lightweight adapters are employed to locally refine text em"},"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":"2409.08248","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T17:47:51Z","cross_cats_sorted":[],"title_canon_sha256":"2e79b5387eb2b00085fd2e89408651bf014fe39a3b8f0f725b60d35bd6aea885","abstract_canon_sha256":"28c1449c6de594ebdcf28015314344a99f960e23a81c520b58a68fe9dc824777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:50.199808Z","signature_b64":"KxihABrFNPsWSrFozn8ZMeuikrEWl5CqxQ8mR4geDa/KA8a7QhFJmdmb30Rv2k412he5BHyhfAXGSVNv1cvZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375bc2feb1e4be774fb9b969bc03f9ebf4de216bb1d0c0796c9eb6026a29cac7","last_reissued_at":"2026-05-20T01:04:50.199081Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:50.199081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Kunhee Kim, NaHyeon Park","submitted_at":"2024-09-12T17:47:51Z","abstract_excerpt":"In this paper, we introduce TextBoost, an efficient one-shot personalization approach for text-to-image diffusion models. Traditional personalization methods typically involve fine-tuning extensive portions of the model, leading to substantial storage requirements and slow convergence. In contrast, we propose selectively fine-tuning only the text encoder, significantly improving computational and storage efficiency. To preserve the original semantic integrity, we develop a novel causality-preserving adaptation mechanism. Additionally, lightweight adapters are employed to locally refine text em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08248","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/2409.08248/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":"2409.08248","created_at":"2026-05-20T01:04:50.199207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08248v2","created_at":"2026-05-20T01:04:50.199207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08248","created_at":"2026-05-20T01:04:50.199207+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5N4F7VR4S7H","created_at":"2026-05-20T01:04:50.199207+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5N4F7VR4S7HOT5Z","created_at":"2026-05-20T01:04:50.199207+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5N4F7VR","created_at":"2026-05-20T01:04:50.199207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P","json":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P.json","graph_json":"https://pith.science/api/pith-number/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/graph.json","events_json":"https://pith.science/api/pith-number/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/events.json","paper":"https://pith.science/paper/G5N4F7VR"},"agent_actions":{"view_html":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P","download_json":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P.json","view_paper":"https://pith.science/paper/G5N4F7VR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08248&json=true","fetch_graph":"https://pith.science/api/pith-number/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/graph.json","fetch_events":"https://pith.science/api/pith-number/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/action/storage_attestation","attest_author":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/action/author_attestation","sign_citation":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/action/citation_signature","submit_replication":"https://pith.science/pith/G5N4F7VR4S7HOT5ZXFU3YA7Z5P/action/replication_record"}},"created_at":"2026-05-20T01:04:50.199207+00:00","updated_at":"2026-05-20T01:04:50.199207+00:00"}