{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UXQH6T6SFAIAF36TXM3T6TN4ZD","short_pith_number":"pith:UXQH6T6S","schema_version":"1.0","canonical_sha256":"a5e07f4fd2281002efd3bb373f4dbcc8cb948b6f19c6422b63e8a3714a3fe4f7","source":{"kind":"arxiv","id":"2410.03097","version":2},"attestation_state":"computed","paper":{"title":"CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Long Chen, Zhen Wang, Ziqi Jiang","submitted_at":"2024-10-04T02:46:09Z","abstract_excerpt":"Precise and flexible image editing remains a fundamental challenge in computer vision. Based on the modified areas, most editing methods can be divided into two main types: global editing and local editing. In this paper, we choose the two most common editing approaches (ie text-based editing and drag-based editing) and analyze their drawbacks. Specifically, text-based methods often fail to describe the desired modifications precisely, while drag-based methods suffer from ambiguity. To address these issues, we proposed \\textbf{CLIPDrag}, a novel image editing method that is the first to combin"},"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":"2410.03097","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T02:46:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1eee42292c150633625ab00f687219777f62541ceaf9c0d0b70da36d3b61e404","abstract_canon_sha256":"9b3316846b743a8e2cb590922f24515d7de4b54a8f3fca606e40b53161bfc1f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:56.031301Z","signature_b64":"2AwPvP3dv6Sxvtm0jrZEB3xeInhllEQHeW/56Mev6HBdNpk/RwVNqxTRFh7SnJxmKWeocC3OgMjZpHA9xNQdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5e07f4fd2281002efd3bb373f4dbcc8cb948b6f19c6422b63e8a3714a3fe4f7","last_reissued_at":"2026-07-05T10:19:56.030845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:56.030845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Long Chen, Zhen Wang, Ziqi Jiang","submitted_at":"2024-10-04T02:46:09Z","abstract_excerpt":"Precise and flexible image editing remains a fundamental challenge in computer vision. Based on the modified areas, most editing methods can be divided into two main types: global editing and local editing. In this paper, we choose the two most common editing approaches (ie text-based editing and drag-based editing) and analyze their drawbacks. Specifically, text-based methods often fail to describe the desired modifications precisely, while drag-based methods suffer from ambiguity. To address these issues, we proposed \\textbf{CLIPDrag}, a novel image editing method that is the first to combin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03097","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/2410.03097/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":"2410.03097","created_at":"2026-07-05T10:19:56.030901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03097v2","created_at":"2026-07-05T10:19:56.030901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03097","created_at":"2026-07-05T10:19:56.030901+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXQH6T6SFAIA","created_at":"2026-07-05T10:19:56.030901+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXQH6T6SFAIAF36T","created_at":"2026-07-05T10:19:56.030901+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXQH6T6S","created_at":"2026-07-05T10:19:56.030901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12427","citing_title":"DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD","json":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD.json","graph_json":"https://pith.science/api/pith-number/UXQH6T6SFAIAF36TXM3T6TN4ZD/graph.json","events_json":"https://pith.science/api/pith-number/UXQH6T6SFAIAF36TXM3T6TN4ZD/events.json","paper":"https://pith.science/paper/UXQH6T6S"},"agent_actions":{"view_html":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD","download_json":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD.json","view_paper":"https://pith.science/paper/UXQH6T6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03097&json=true","fetch_graph":"https://pith.science/api/pith-number/UXQH6T6SFAIAF36TXM3T6TN4ZD/graph.json","fetch_events":"https://pith.science/api/pith-number/UXQH6T6SFAIAF36TXM3T6TN4ZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD/action/storage_attestation","attest_author":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD/action/author_attestation","sign_citation":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD/action/citation_signature","submit_replication":"https://pith.science/pith/UXQH6T6SFAIAF36TXM3T6TN4ZD/action/replication_record"}},"created_at":"2026-07-05T10:19:56.030901+00:00","updated_at":"2026-07-05T10:19:56.030901+00:00"}