{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OMYFGIEYC4KQWTMEKXVWZQPDE5","short_pith_number":"pith:OMYFGIEY","schema_version":"1.0","canonical_sha256":"733053209817150b4d8455eb6cc1e3274cb3ab0646f75f886bb691d584d3ca56","source":{"kind":"arxiv","id":"2103.10951","version":3},"attestation_state":"computed","paper":{"title":"Paint by Word","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Alex Andonian, Ali Jahanian, Antonio Torralba, Audrey Cui, David Bau, Sabrina Osmany, YeonHwan Park","submitted_at":"2021-03-19T17:59:08Z","abstract_excerpt":"We investigate the problem of zero-shot semantic image painting. Instead of painting modifications into an image using only concrete colors or a finite set of semantic concepts, we ask how to create semantic paint based on open full-text descriptions: our goal is to be able to point to a location in a synthesized image and apply an arbitrary new concept such as \"rustic\" or \"opulent\" or \"happy dog.\" To do this, our method combines a state-of-the art generative model of realistic images with a state-of-the-art text-image semantic similarity network. We find that, to make large changes, it is imp"},"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":"2103.10951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T17:59:08Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"4f7d1d579504ffdf0bde9cb2488aa6fd1b792d09f8af0e44c5d9bde03a460a8f","abstract_canon_sha256":"62626a48f20eb08736acbf6623e694bd64837202301db26ef72eb14a807f355a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:10.358236Z","signature_b64":"DL0WIcVGFP/+olD+0S/pTj3XnPtLfl6BLE/yPQwW2+H9NhIogSV83CEeFsYWzxU+w8EAL5doRah8+AEWnaP7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"733053209817150b4d8455eb6cc1e3274cb3ab0646f75f886bb691d584d3ca56","last_reissued_at":"2026-07-05T05:54:10.357707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:10.357707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Paint by Word","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Alex Andonian, Ali Jahanian, Antonio Torralba, Audrey Cui, David Bau, Sabrina Osmany, YeonHwan Park","submitted_at":"2021-03-19T17:59:08Z","abstract_excerpt":"We investigate the problem of zero-shot semantic image painting. Instead of painting modifications into an image using only concrete colors or a finite set of semantic concepts, we ask how to create semantic paint based on open full-text descriptions: our goal is to be able to point to a location in a synthesized image and apply an arbitrary new concept such as \"rustic\" or \"opulent\" or \"happy dog.\" To do this, our method combines a state-of-the art generative model of realistic images with a state-of-the-art text-image semantic similarity network. We find that, to make large changes, it is imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10951","kind":"arxiv","version":3},"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/2103.10951/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":"2103.10951","created_at":"2026-07-05T05:54:10.357778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10951v3","created_at":"2026-07-05T05:54:10.357778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10951","created_at":"2026-07-05T05:54:10.357778+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMYFGIEYC4KQ","created_at":"2026-07-05T05:54:10.357778+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMYFGIEYC4KQWTME","created_at":"2026-07-05T05:54:10.357778+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMYFGIEY","created_at":"2026-07-05T05:54:10.357778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26353","citing_title":"Personalized Generative Models for Contextual Debiasing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07798","citing_title":"Generative Inversion for Property-Targeted Materials Design: Application to Shape Memory Alloys","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01324","citing_title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5","json":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5.json","graph_json":"https://pith.science/api/pith-number/OMYFGIEYC4KQWTMEKXVWZQPDE5/graph.json","events_json":"https://pith.science/api/pith-number/OMYFGIEYC4KQWTMEKXVWZQPDE5/events.json","paper":"https://pith.science/paper/OMYFGIEY"},"agent_actions":{"view_html":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5","download_json":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5.json","view_paper":"https://pith.science/paper/OMYFGIEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10951&json=true","fetch_graph":"https://pith.science/api/pith-number/OMYFGIEYC4KQWTMEKXVWZQPDE5/graph.json","fetch_events":"https://pith.science/api/pith-number/OMYFGIEYC4KQWTMEKXVWZQPDE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5/action/storage_attestation","attest_author":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5/action/author_attestation","sign_citation":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5/action/citation_signature","submit_replication":"https://pith.science/pith/OMYFGIEYC4KQWTMEKXVWZQPDE5/action/replication_record"}},"created_at":"2026-07-05T05:54:10.357778+00:00","updated_at":"2026-07-05T05:54:10.357778+00:00"}