{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GC6KI4PNDPY3TCUNHNEMBPU3T2","short_pith_number":"pith:GC6KI4PN","schema_version":"1.0","canonical_sha256":"30bca471ed1bf1b98a8d3b48c0be9b9e9c73faa9e67fb568eba8a5ae3b405853","source":{"kind":"arxiv","id":"2403.10701","version":1},"attestation_state":"computed","paper":{"title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Price, Daniel Aliaga, He Zhang, Jianming Zhang, Scott Cohen, Soo Ye Kim, Wei Xiong, Yizhi Song, Zhe Lin, Zhifei Zhang","submitted_at":"2024-03-15T21:37:04Z","abstract_excerpt":"Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both"},"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":"2403.10701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T21:37:04Z","cross_cats_sorted":[],"title_canon_sha256":"5db83654667941b104f81c07e8c8611e018cc7827febbaf70aaf5af5a36f95be","abstract_canon_sha256":"78dae0028994893482a34809f6d70a7de30c093f8c1846c129e36f230d55e62f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:05.304367Z","signature_b64":"i8W2PIjmHrXwnFeHfY/5EWgbOwQ7TGwPIgGu3fvdVMolENiIaHK8RMUYgOzeA290XlhOgraL5OHObgfItik9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30bca471ed1bf1b98a8d3b48c0be9b9e9c73faa9e67fb568eba8a5ae3b405853","last_reissued_at":"2026-07-05T07:57:05.303784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:05.303784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Price, Daniel Aliaga, He Zhang, Jianming Zhang, Scott Cohen, Soo Ye Kim, Wei Xiong, Yizhi Song, Zhe Lin, Zhifei Zhang","submitted_at":"2024-03-15T21:37:04Z","abstract_excerpt":"Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10701","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/2403.10701/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":"2403.10701","created_at":"2026-07-05T07:57:05.303855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10701v1","created_at":"2026-07-05T07:57:05.303855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10701","created_at":"2026-07-05T07:57:05.303855+00:00"},{"alias_kind":"pith_short_12","alias_value":"GC6KI4PNDPY3","created_at":"2026-07-05T07:57:05.303855+00:00"},{"alias_kind":"pith_short_16","alias_value":"GC6KI4PNDPY3TCUN","created_at":"2026-07-05T07:57:05.303855+00:00"},{"alias_kind":"pith_short_8","alias_value":"GC6KI4PN","created_at":"2026-07-05T07:57:05.303855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19575","citing_title":"Interact-Custom: Customized Human Object Interaction Image Generation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2","json":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2.json","graph_json":"https://pith.science/api/pith-number/GC6KI4PNDPY3TCUNHNEMBPU3T2/graph.json","events_json":"https://pith.science/api/pith-number/GC6KI4PNDPY3TCUNHNEMBPU3T2/events.json","paper":"https://pith.science/paper/GC6KI4PN"},"agent_actions":{"view_html":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2","download_json":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2.json","view_paper":"https://pith.science/paper/GC6KI4PN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10701&json=true","fetch_graph":"https://pith.science/api/pith-number/GC6KI4PNDPY3TCUNHNEMBPU3T2/graph.json","fetch_events":"https://pith.science/api/pith-number/GC6KI4PNDPY3TCUNHNEMBPU3T2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2/action/storage_attestation","attest_author":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2/action/author_attestation","sign_citation":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2/action/citation_signature","submit_replication":"https://pith.science/pith/GC6KI4PNDPY3TCUNHNEMBPU3T2/action/replication_record"}},"created_at":"2026-07-05T07:57:05.303855+00:00","updated_at":"2026-07-05T07:57:05.303855+00:00"}