{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F44OOBPTYEZTVSLIKOQ7TODGUE","short_pith_number":"pith:F44OOBPT","schema_version":"1.0","canonical_sha256":"2f38e705f3c1333ac96853a1f9b866a1267f95e900d135670b0f08b526deb6b7","source":{"kind":"arxiv","id":"2411.07232","version":2},"attestation_state":"computed","paper":{"title":"Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dvir Samuel, Gal Chechik, Lior Wolf, Rinon Gal, Yoad Tewel, Yuval Atzmon","submitted_at":"2024-11-11T18:50:09Z","abstract_excerpt":"Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself"},"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":"2411.07232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T18:50:09Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"15c77192dc53bc5bdf9449d274858547eb2b6a35a43a639aa1ba4f93ad694873","abstract_canon_sha256":"cc97e2756e0c4fd0afe81dc0907da4ed887fdc65e76a6b681bf41a56f28c47de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:23.054823Z","signature_b64":"T11op0H7rYPsAdpRxU84BqRYE7piy3oMMr/F9d0/QdKa8Sr+h4h/p7iZcg2b4jTW00tnFGpwB+C0pX6PZrf+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f38e705f3c1333ac96853a1f9b866a1267f95e900d135670b0f08b526deb6b7","last_reissued_at":"2026-07-05T09:34:23.054349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:23.054349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dvir Samuel, Gal Chechik, Lior Wolf, Rinon Gal, Yoad Tewel, Yuval Atzmon","submitted_at":"2024-11-11T18:50:09Z","abstract_excerpt":"Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07232","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/2411.07232/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":"2411.07232","created_at":"2026-07-05T09:34:23.054411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07232v2","created_at":"2026-07-05T09:34:23.054411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07232","created_at":"2026-07-05T09:34:23.054411+00:00"},{"alias_kind":"pith_short_12","alias_value":"F44OOBPTYEZT","created_at":"2026-07-05T09:34:23.054411+00:00"},{"alias_kind":"pith_short_16","alias_value":"F44OOBPTYEZTVSLI","created_at":"2026-07-05T09:34:23.054411+00:00"},{"alias_kind":"pith_short_8","alias_value":"F44OOBPT","created_at":"2026-07-05T09:34:23.054411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14842","citing_title":"Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00931","citing_title":"CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15921","citing_title":"AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24407","citing_title":"AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priors","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE","json":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE.json","graph_json":"https://pith.science/api/pith-number/F44OOBPTYEZTVSLIKOQ7TODGUE/graph.json","events_json":"https://pith.science/api/pith-number/F44OOBPTYEZTVSLIKOQ7TODGUE/events.json","paper":"https://pith.science/paper/F44OOBPT"},"agent_actions":{"view_html":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE","download_json":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE.json","view_paper":"https://pith.science/paper/F44OOBPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07232&json=true","fetch_graph":"https://pith.science/api/pith-number/F44OOBPTYEZTVSLIKOQ7TODGUE/graph.json","fetch_events":"https://pith.science/api/pith-number/F44OOBPTYEZTVSLIKOQ7TODGUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE/action/storage_attestation","attest_author":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE/action/author_attestation","sign_citation":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE/action/citation_signature","submit_replication":"https://pith.science/pith/F44OOBPTYEZTVSLIKOQ7TODGUE/action/replication_record"}},"created_at":"2026-07-05T09:34:23.054411+00:00","updated_at":"2026-07-05T09:34:23.054411+00:00"}