{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OQI3OV7C75B47JMJ2GNBQB6RJX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ae43134cab87d02b810e0ab30779fe1dd08edf5d853d13c1837c18ea744b2a2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T22:45:47Z","title_canon_sha256":"3c2b97c74041dd11eaee63201fbb9e4474abdb034e843aaa01f71948865d6722"},"schema_version":"1.0","source":{"id":"2404.18020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18020","created_at":"2026-07-05T08:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18020v1","created_at":"2026-07-05T08:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18020","created_at":"2026-07-05T08:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"OQI3OV7C75B4","created_at":"2026-07-05T08:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"OQI3OV7C75B47JMJ","created_at":"2026-07-05T08:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"OQI3OV7C","created_at":"2026-07-05T08:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:bfdfb8591e966f7b599cc2c3b2a70629ae61d9447b162a3cb0e8a88d44368875","target":"graph","created_at":"2026-07-05T08:12:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.18020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Maria Mihaela Trusca, Marie-Francine Moens, Tinne Tuytelaars","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T22:45:47Z","title":"DM-Align: Leveraging the Power of Natural Language Instructions to Make Changes to Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18020","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78097b137c85e8de0ee7860bbaf669a20453b5dd3d22e809fd30d05ff5c5eda8","target":"record","created_at":"2026-07-05T08:12:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ae43134cab87d02b810e0ab30779fe1dd08edf5d853d13c1837c18ea744b2a2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T22:45:47Z","title_canon_sha256":"3c2b97c74041dd11eaee63201fbb9e4474abdb034e843aaa01f71948865d6722"},"schema_version":"1.0","source":{"id":"2404.18020","kind":"arxiv","version":1}},"canonical_sha256":"7411b757e2ff43cfa589d19a1807d14dc2c59826e5d5d6a0eb66baa3614ec184","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7411b757e2ff43cfa589d19a1807d14dc2c59826e5d5d6a0eb66baa3614ec184","first_computed_at":"2026-07-05T08:12:56.872329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:56.872329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NQdY64F4fLrKQGd5faqmFmLQbbCXLo9ecWHTiRyWSgdNip8qddsvJ9HuTF6u/ThBGk7tddWvy/QC+xKQJ3v3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:56.872715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78097b137c85e8de0ee7860bbaf669a20453b5dd3d22e809fd30d05ff5c5eda8","sha256:bfdfb8591e966f7b599cc2c3b2a70629ae61d9447b162a3cb0e8a88d44368875"],"state_sha256":"e0818ff5167708705e7144178a5339f8d4306104ad90fc635a264e367f69b703"}