{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2I25J5SWYLFGNU4ZVRSNOSH2WH","short_pith_number":"pith:2I25J5SW","schema_version":"1.0","canonical_sha256":"d235d4f656c2ca66d399ac64d748fab1e74d7f95117bfb0dfed2abf7f7995dfa","source":{"kind":"arxiv","id":"2307.12493","version":4},"attestation_state":"computed","paper":{"title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adams Wai-Kin Kong, Shilin Lu, Yanzhu Liu","submitted_at":"2023-07-24T02:50:44Z","abstract_excerpt":"Text-driven diffusion models have exhibited impressive generative capabilities, enabling various image editing tasks. In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of text-driven diffusion models for cross-domain image-guided composition. This task aims to seamlessly integrate user-provided objects into a specific visual context. Current diffusion-based methods often involve costly instance-based optimization or finetuning of pretrained models on customized datasets, which can potentially undermine their rich prior. In contrast, 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":"2307.12493","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T02:50:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"185eb31aa695db6edf26b36533d80496ec68065dcc8072d274ff09cda5d14133","abstract_canon_sha256":"1d192faf0d7c924c310c887d085191142da84a5238874a59749e873a09dc8c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:58.409008Z","signature_b64":"lc+d7Loq7FKNF+drpnxxFVE7O+1l+JR//O2F+y//iahB3ymVmC/Lp+pIptM+iWbfjRwwEYcI80VzmSxLL6ByDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d235d4f656c2ca66d399ac64d748fab1e74d7f95117bfb0dfed2abf7f7995dfa","last_reissued_at":"2026-07-05T06:58:58.408513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:58.408513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adams Wai-Kin Kong, Shilin Lu, Yanzhu Liu","submitted_at":"2023-07-24T02:50:44Z","abstract_excerpt":"Text-driven diffusion models have exhibited impressive generative capabilities, enabling various image editing tasks. In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of text-driven diffusion models for cross-domain image-guided composition. This task aims to seamlessly integrate user-provided objects into a specific visual context. Current diffusion-based methods often involve costly instance-based optimization or finetuning of pretrained models on customized datasets, which can potentially undermine their rich prior. In contrast, T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12493","kind":"arxiv","version":4},"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/2307.12493/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":"2307.12493","created_at":"2026-07-05T06:58:58.408575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12493v4","created_at":"2026-07-05T06:58:58.408575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12493","created_at":"2026-07-05T06:58:58.408575+00:00"},{"alias_kind":"pith_short_12","alias_value":"2I25J5SWYLFG","created_at":"2026-07-05T06:58:58.408575+00:00"},{"alias_kind":"pith_short_16","alias_value":"2I25J5SWYLFGNU4Z","created_at":"2026-07-05T06:58:58.408575+00:00"},{"alias_kind":"pith_short_8","alias_value":"2I25J5SW","created_at":"2026-07-05T06:58:58.408575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH","json":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH.json","graph_json":"https://pith.science/api/pith-number/2I25J5SWYLFGNU4ZVRSNOSH2WH/graph.json","events_json":"https://pith.science/api/pith-number/2I25J5SWYLFGNU4ZVRSNOSH2WH/events.json","paper":"https://pith.science/paper/2I25J5SW"},"agent_actions":{"view_html":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH","download_json":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH.json","view_paper":"https://pith.science/paper/2I25J5SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12493&json=true","fetch_graph":"https://pith.science/api/pith-number/2I25J5SWYLFGNU4ZVRSNOSH2WH/graph.json","fetch_events":"https://pith.science/api/pith-number/2I25J5SWYLFGNU4ZVRSNOSH2WH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH/action/storage_attestation","attest_author":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH/action/author_attestation","sign_citation":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH/action/citation_signature","submit_replication":"https://pith.science/pith/2I25J5SWYLFGNU4ZVRSNOSH2WH/action/replication_record"}},"created_at":"2026-07-05T06:58:58.408575+00:00","updated_at":"2026-07-05T06:58:58.408575+00:00"}