{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RREOOFJOLZB4AMNL6VFROUAXRC","short_pith_number":"pith:RREOOFJO","schema_version":"1.0","canonical_sha256":"8c48e7152e5e43c031abf54b175017889bf7eb7b1c3fec010e0f4b62a791f68c","source":{"kind":"arxiv","id":"2410.10058","version":1},"attestation_state":"computed","paper":{"title":"Learning to Customize Text-to-Image Diffusion In Diverse Context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Qiu, Taewook Kim, Wei Chen","submitted_at":"2024-10-14T00:53:59Z","abstract_excerpt":"Most text-to-image customization techniques fine-tune models on a small set of \\emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to generalize to new contexts in future text prompts. Existing customization methods are built on the success of effectively representing personal concepts as textual embeddings. Thus, in this work, we resort to diversifying the context of these personal concepts \\emph{solely} within the textual space by simply creating a contextually rich set of text prompts, together "},"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":"2410.10058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T00:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"d0f18c494a54bd5b4d438cc516e162d6ddb4fbdfc19b567e4677d050440a26e1","abstract_canon_sha256":"c6dde7a37df4e880da598f0c45ec3479759e4d84b8e782de7505ce2686797ba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:10.464277Z","signature_b64":"a9nS3uJgnqSui7C6Yopo/VdOiJP2uvkIl+WTfy7ZyS4ByEIWxLtXB0asIaw8mSmESc3I+PFDSFqEg6TRjUNVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c48e7152e5e43c031abf54b175017889bf7eb7b1c3fec010e0f4b62a791f68c","last_reissued_at":"2026-07-05T09:20:10.463825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:10.463825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Customize Text-to-Image Diffusion In Diverse Context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Qiu, Taewook Kim, Wei Chen","submitted_at":"2024-10-14T00:53:59Z","abstract_excerpt":"Most text-to-image customization techniques fine-tune models on a small set of \\emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to generalize to new contexts in future text prompts. Existing customization methods are built on the success of effectively representing personal concepts as textual embeddings. Thus, in this work, we resort to diversifying the context of these personal concepts \\emph{solely} within the textual space by simply creating a contextually rich set of text prompts, together "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10058","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/2410.10058/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":"2410.10058","created_at":"2026-07-05T09:20:10.463880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10058v1","created_at":"2026-07-05T09:20:10.463880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10058","created_at":"2026-07-05T09:20:10.463880+00:00"},{"alias_kind":"pith_short_12","alias_value":"RREOOFJOLZB4","created_at":"2026-07-05T09:20:10.463880+00:00"},{"alias_kind":"pith_short_16","alias_value":"RREOOFJOLZB4AMNL","created_at":"2026-07-05T09:20:10.463880+00:00"},{"alias_kind":"pith_short_8","alias_value":"RREOOFJO","created_at":"2026-07-05T09:20:10.463880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10855","citing_title":"Sparse Fine-Tuning of Transformers for Generative Tasks","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC","json":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC.json","graph_json":"https://pith.science/api/pith-number/RREOOFJOLZB4AMNL6VFROUAXRC/graph.json","events_json":"https://pith.science/api/pith-number/RREOOFJOLZB4AMNL6VFROUAXRC/events.json","paper":"https://pith.science/paper/RREOOFJO"},"agent_actions":{"view_html":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC","download_json":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC.json","view_paper":"https://pith.science/paper/RREOOFJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10058&json=true","fetch_graph":"https://pith.science/api/pith-number/RREOOFJOLZB4AMNL6VFROUAXRC/graph.json","fetch_events":"https://pith.science/api/pith-number/RREOOFJOLZB4AMNL6VFROUAXRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC/action/storage_attestation","attest_author":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC/action/author_attestation","sign_citation":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC/action/citation_signature","submit_replication":"https://pith.science/pith/RREOOFJOLZB4AMNL6VFROUAXRC/action/replication_record"}},"created_at":"2026-07-05T09:20:10.463880+00:00","updated_at":"2026-07-05T09:20:10.463880+00:00"}