{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VF5SRR4GCNCIOIDEID2GKOJPPE","short_pith_number":"pith:VF5SRR4G","schema_version":"1.0","canonical_sha256":"a97b28c786134487206440f465392f79330987150a4ae4f44233da0f0164969f","source":{"kind":"arxiv","id":"2303.08767","version":3},"attestation_state":"computed","paper":{"title":"Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Inhwa Han, Jong Chul Ye, Serin Yang, Taesung Kwon","submitted_at":"2023-03-15T17:07:45Z","abstract_excerpt":"Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity. While previous approaches like DreamBooth and Textual Inversion have proposed model or latent representation personalization to maintain the content, their reliance on multiple reference images and complex training limits their practicality. In this paper, we present a simple yet highly effective approach to personalization using highly personalized (HiPer) text embedding by decomposing the CLIP embe"},"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":"2303.08767","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-15T17:07:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb50554835d864c08c47f2cf803f75e083c131e92c5fd47aeb24882d075fe74b","abstract_canon_sha256":"136c0fce115a04d11b4e01f69bda7e6b11e3783afb61e5574a2d41d02b038da0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:33.013693Z","signature_b64":"8R87C3cm0xmRPkTiuWDn2YkCKl7d0J3U6fGOZyWedilcdeESg9vp6UEVZYhPe9k0v9E6XNNvBN950mNIjgG/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97b28c786134487206440f465392f79330987150a4ae4f44233da0f0164969f","last_reissued_at":"2026-07-05T06:02:33.013180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:33.013180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Inhwa Han, Jong Chul Ye, Serin Yang, Taesung Kwon","submitted_at":"2023-03-15T17:07:45Z","abstract_excerpt":"Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity. While previous approaches like DreamBooth and Textual Inversion have proposed model or latent representation personalization to maintain the content, their reliance on multiple reference images and complex training limits their practicality. In this paper, we present a simple yet highly effective approach to personalization using highly personalized (HiPer) text embedding by decomposing the CLIP embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08767","kind":"arxiv","version":3},"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/2303.08767/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":"2303.08767","created_at":"2026-07-05T06:02:33.013242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08767v3","created_at":"2026-07-05T06:02:33.013242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08767","created_at":"2026-07-05T06:02:33.013242+00:00"},{"alias_kind":"pith_short_12","alias_value":"VF5SRR4GCNCI","created_at":"2026-07-05T06:02:33.013242+00:00"},{"alias_kind":"pith_short_16","alias_value":"VF5SRR4GCNCIOIDE","created_at":"2026-07-05T06:02:33.013242+00:00"},{"alias_kind":"pith_short_8","alias_value":"VF5SRR4G","created_at":"2026-07-05T06:02:33.013242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.08090","citing_title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE","json":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE.json","graph_json":"https://pith.science/api/pith-number/VF5SRR4GCNCIOIDEID2GKOJPPE/graph.json","events_json":"https://pith.science/api/pith-number/VF5SRR4GCNCIOIDEID2GKOJPPE/events.json","paper":"https://pith.science/paper/VF5SRR4G"},"agent_actions":{"view_html":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE","download_json":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE.json","view_paper":"https://pith.science/paper/VF5SRR4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08767&json=true","fetch_graph":"https://pith.science/api/pith-number/VF5SRR4GCNCIOIDEID2GKOJPPE/graph.json","fetch_events":"https://pith.science/api/pith-number/VF5SRR4GCNCIOIDEID2GKOJPPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE/action/storage_attestation","attest_author":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE/action/author_attestation","sign_citation":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE/action/citation_signature","submit_replication":"https://pith.science/pith/VF5SRR4GCNCIOIDEID2GKOJPPE/action/replication_record"}},"created_at":"2026-07-05T06:02:33.013242+00:00","updated_at":"2026-07-05T06:02:33.013242+00:00"}