{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M27TLR2Z2ZD5PRKEHFCE4KEJVS","short_pith_number":"pith:M27TLR2Z","schema_version":"1.0","canonical_sha256":"66bf35c759d647d7c54439444e2889acb696fd480470100d079f85d4f8cbe1f9","source":{"kind":"arxiv","id":"2305.05947","version":1},"attestation_state":"computed","paper":{"title":"iEdit: Localised Text-guided Image Editing with Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binod Bhattarai, Erhan Gundogdu, Loris Bazzani, Michael Donoser, Rumeysa Bodur, Tae-Kyun Kim","submitted_at":"2023-05-10T07:39:14Z","abstract_excerpt":"Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for text-guided image editing, namely \\texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving the fidelity of t"},"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":"2305.05947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T07:39:14Z","cross_cats_sorted":[],"title_canon_sha256":"2728bafee9f17e0e5edb7ff839920f74ddd1c796cf8ae24e3d32ff1e97f6af25","abstract_canon_sha256":"180ae4fd0c02d6b1e5f50cac7620bea07946025d0e1fb789b59053e6498a3e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:58.016742Z","signature_b64":"DuovFPqe51a5DgBWFJw5JEUxT7aAEc9fLEjlWFlP0FSlbkGaifs61/RB2KGMExXaXqsUqc4qQOl5LiwXSvR9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66bf35c759d647d7c54439444e2889acb696fd480470100d079f85d4f8cbe1f9","last_reissued_at":"2026-07-05T06:08:58.016398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:58.016398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iEdit: Localised Text-guided Image Editing with Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binod Bhattarai, Erhan Gundogdu, Loris Bazzani, Michael Donoser, Rumeysa Bodur, Tae-Kyun Kim","submitted_at":"2023-05-10T07:39:14Z","abstract_excerpt":"Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for text-guided image editing, namely \\texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving the fidelity of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05947","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/2305.05947/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":"2305.05947","created_at":"2026-07-05T06:08:58.016460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05947v1","created_at":"2026-07-05T06:08:58.016460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05947","created_at":"2026-07-05T06:08:58.016460+00:00"},{"alias_kind":"pith_short_12","alias_value":"M27TLR2Z2ZD5","created_at":"2026-07-05T06:08:58.016460+00:00"},{"alias_kind":"pith_short_16","alias_value":"M27TLR2Z2ZD5PRKE","created_at":"2026-07-05T06:08:58.016460+00:00"},{"alias_kind":"pith_short_8","alias_value":"M27TLR2Z","created_at":"2026-07-05T06:08:58.016460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00356","citing_title":"Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS","json":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS.json","graph_json":"https://pith.science/api/pith-number/M27TLR2Z2ZD5PRKEHFCE4KEJVS/graph.json","events_json":"https://pith.science/api/pith-number/M27TLR2Z2ZD5PRKEHFCE4KEJVS/events.json","paper":"https://pith.science/paper/M27TLR2Z"},"agent_actions":{"view_html":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS","download_json":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS.json","view_paper":"https://pith.science/paper/M27TLR2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05947&json=true","fetch_graph":"https://pith.science/api/pith-number/M27TLR2Z2ZD5PRKEHFCE4KEJVS/graph.json","fetch_events":"https://pith.science/api/pith-number/M27TLR2Z2ZD5PRKEHFCE4KEJVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS/action/storage_attestation","attest_author":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS/action/author_attestation","sign_citation":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS/action/citation_signature","submit_replication":"https://pith.science/pith/M27TLR2Z2ZD5PRKEHFCE4KEJVS/action/replication_record"}},"created_at":"2026-07-05T06:08:58.016460+00:00","updated_at":"2026-07-05T06:08:58.016460+00:00"}