{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OQI3OV7C75B47JMJ2GNBQB6RJX","short_pith_number":"pith:OQI3OV7C","schema_version":"1.0","canonical_sha256":"7411b757e2ff43cfa589d19a1807d14dc2c59826e5d5d6a0eb66baa3614ec184","source":{"kind":"arxiv","id":"2404.18020","version":1},"attestation_state":"computed","paper":{"title":"DM-Align: Leveraging the Power of Natural Language Instructions to Make Changes to Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Maria Mihaela Trusca, Marie-Francine Moens, Tinne Tuytelaars","submitted_at":"2024-04-27T22:45:47Z","abstract_excerpt":"Text-based semantic image editing assumes the manipulation of an image using a natural language instruction. Although recent works are capable of generating creative and qualitative images, the problem is still mostly approached as a black box sensitive to generating unexpected outputs. Therefore, we propose a novel model to enhance the text-based control of an image editor by explicitly reasoning about which parts of the image to alter or preserve. It relies on word alignments between a description of the original source image and the instruction that reflects the needed updates, and the inpu"},"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":"2404.18020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T22:45:47Z","cross_cats_sorted":[],"title_canon_sha256":"3c2b97c74041dd11eaee63201fbb9e4474abdb034e843aaa01f71948865d6722","abstract_canon_sha256":"ae43134cab87d02b810e0ab30779fe1dd08edf5d853d13c1837c18ea744b2a2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:56.872715Z","signature_b64":"NQdY64F4fLrKQGd5faqmFmLQbbCXLo9ecWHTiRyWSgdNip8qddsvJ9HuTF6u/ThBGk7tddWvy/QC+xKQJ3v3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7411b757e2ff43cfa589d19a1807d14dc2c59826e5d5d6a0eb66baa3614ec184","last_reissued_at":"2026-07-05T08:12:56.872329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:56.872329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DM-Align: Leveraging the Power of Natural Language Instructions to Make Changes to Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Maria Mihaela Trusca, Marie-Francine Moens, Tinne Tuytelaars","submitted_at":"2024-04-27T22:45:47Z","abstract_excerpt":"Text-based semantic image editing assumes the manipulation of an image using a natural language instruction. Although recent works are capable of generating creative and qualitative images, the problem is still mostly approached as a black box sensitive to generating unexpected outputs. Therefore, we propose a novel model to enhance the text-based control of an image editor by explicitly reasoning about which parts of the image to alter or preserve. It relies on word alignments between a description of the original source image and the instruction that reflects the needed updates, and the inpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18020","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/2404.18020/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":"2404.18020","created_at":"2026-07-05T08:12:56.872390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18020v1","created_at":"2026-07-05T08:12:56.872390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18020","created_at":"2026-07-05T08:12:56.872390+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQI3OV7C75B4","created_at":"2026-07-05T08:12:56.872390+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQI3OV7C75B47JMJ","created_at":"2026-07-05T08:12:56.872390+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQI3OV7C","created_at":"2026-07-05T08:12:56.872390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04558","citing_title":"Action-based image editing guided by human instructions","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX","json":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX.json","graph_json":"https://pith.science/api/pith-number/OQI3OV7C75B47JMJ2GNBQB6RJX/graph.json","events_json":"https://pith.science/api/pith-number/OQI3OV7C75B47JMJ2GNBQB6RJX/events.json","paper":"https://pith.science/paper/OQI3OV7C"},"agent_actions":{"view_html":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX","download_json":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX.json","view_paper":"https://pith.science/paper/OQI3OV7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18020&json=true","fetch_graph":"https://pith.science/api/pith-number/OQI3OV7C75B47JMJ2GNBQB6RJX/graph.json","fetch_events":"https://pith.science/api/pith-number/OQI3OV7C75B47JMJ2GNBQB6RJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX/action/storage_attestation","attest_author":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX/action/author_attestation","sign_citation":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX/action/citation_signature","submit_replication":"https://pith.science/pith/OQI3OV7C75B47JMJ2GNBQB6RJX/action/replication_record"}},"created_at":"2026-07-05T08:12:56.872390+00:00","updated_at":"2026-07-05T08:12:56.872390+00:00"}