{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WZ3NKOTOQ4DI4D6DYERCO5P5TC","short_pith_number":"pith:WZ3NKOTO","schema_version":"1.0","canonical_sha256":"b676d53a6e87068e0fc3c1222775fd98a7b70e0d7e3ba9167ef1a5a64307f591","source":{"kind":"arxiv","id":"2106.14843","version":1},"attestation_state":"computed","paper":{"title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Frans, L.B. Soros, Olaf Witkowski","submitted_at":"2021-06-28T16:43:26Z","abstract_excerpt":"This work presents CLIPDraw, an algorithm that synthesizes novel drawings based on natural language input. CLIPDraw does not require any training; rather a pre-trained CLIP language-image encoder is used as a metric for maximizing similarity between the given description and a generated drawing. Crucially, CLIPDraw operates over vector strokes rather than pixel images, a constraint that biases drawings towards simpler human-recognizable shapes. Results compare between CLIPDraw and other synthesis-through-optimization methods, as well as highlight various interesting behaviors of CLIPDraw, such"},"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":"2106.14843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-28T16:43:26Z","cross_cats_sorted":[],"title_canon_sha256":"c6c7bedfa4be64fba609540cfbe1b8eedc94d197925d2002d5c81c9efafd2015","abstract_canon_sha256":"dda0420650e73a9a4f795f8badb9bae829bea6ac1f01b821dd64fcb9507d5ca6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:54.405617Z","signature_b64":"smGb4YE6OdjgePxvkwCW8TSzOQcKTpPfXb0qlsJIMPejpCfIqKJLnJB+hXzCJ8NqBesxSZBmrARPLhUJ3gdiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b676d53a6e87068e0fc3c1222775fd98a7b70e0d7e3ba9167ef1a5a64307f591","last_reissued_at":"2026-07-05T02:52:54.405240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:54.405240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Frans, L.B. Soros, Olaf Witkowski","submitted_at":"2021-06-28T16:43:26Z","abstract_excerpt":"This work presents CLIPDraw, an algorithm that synthesizes novel drawings based on natural language input. CLIPDraw does not require any training; rather a pre-trained CLIP language-image encoder is used as a metric for maximizing similarity between the given description and a generated drawing. Crucially, CLIPDraw operates over vector strokes rather than pixel images, a constraint that biases drawings towards simpler human-recognizable shapes. Results compare between CLIPDraw and other synthesis-through-optimization methods, as well as highlight various interesting behaviors of CLIPDraw, such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14843","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/2106.14843/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":"2106.14843","created_at":"2026-07-05T02:52:54.405295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14843v1","created_at":"2026-07-05T02:52:54.405295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14843","created_at":"2026-07-05T02:52:54.405295+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZ3NKOTOQ4DI","created_at":"2026-07-05T02:52:54.405295+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZ3NKOTOQ4DI4D6D","created_at":"2026-07-05T02:52:54.405295+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZ3NKOTO","created_at":"2026-07-05T02:52:54.405295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC","json":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC.json","graph_json":"https://pith.science/api/pith-number/WZ3NKOTOQ4DI4D6DYERCO5P5TC/graph.json","events_json":"https://pith.science/api/pith-number/WZ3NKOTOQ4DI4D6DYERCO5P5TC/events.json","paper":"https://pith.science/paper/WZ3NKOTO"},"agent_actions":{"view_html":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC","download_json":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC.json","view_paper":"https://pith.science/paper/WZ3NKOTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14843&json=true","fetch_graph":"https://pith.science/api/pith-number/WZ3NKOTOQ4DI4D6DYERCO5P5TC/graph.json","fetch_events":"https://pith.science/api/pith-number/WZ3NKOTOQ4DI4D6DYERCO5P5TC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC/action/storage_attestation","attest_author":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC/action/author_attestation","sign_citation":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC/action/citation_signature","submit_replication":"https://pith.science/pith/WZ3NKOTOQ4DI4D6DYERCO5P5TC/action/replication_record"}},"created_at":"2026-07-05T02:52:54.405295+00:00","updated_at":"2026-07-05T02:52:54.405295+00:00"}