{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FR72GR2AMV67FTXMCCXFP2R3XB","short_pith_number":"pith:FR72GR2A","schema_version":"1.0","canonical_sha256":"2c7fa34740657df2ceec10ae57ea3bb856395f88cb19872ebb5946daf91d772b","source":{"kind":"arxiv","id":"1904.08410","version":2},"attestation_state":"computed","paper":{"title":"Neural Painters: A learned differentiable constraint for generating brushstroke paintings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Reiichiro Nakano","submitted_at":"2019-04-17T03:03:49Z","abstract_excerpt":"We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to \"paint\" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encouraging this agent to follow human-like strokes when reconstructing digits. We also explore the use of a neural painter as a differentiable image parameterization. By directly optimizing brushstrokes to activate neurons in a pre-trained convolutional network, we can directly visuali"},"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":"1904.08410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-17T03:03:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9fed42c381d3a1eeb505cf009e9aa2dc4a3cd79d78bc9a60472ee529b3a6443e","abstract_canon_sha256":"1f3798037bc849b1583ec4f3c43958b1bcbc5d9a654644ffff142eca808808dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:04.322902Z","signature_b64":"3+hlX51p811KZzL4zQgSkFneFIvtIO/2k7a0BkVgjSc/i1E2nFa6WCW1Yf/HG2O3KB+oU415fIOc4sq04ctgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c7fa34740657df2ceec10ae57ea3bb856395f88cb19872ebb5946daf91d772b","last_reissued_at":"2026-05-17T23:48:04.322399Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:04.322399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Painters: A learned differentiable constraint for generating brushstroke paintings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Reiichiro Nakano","submitted_at":"2019-04-17T03:03:49Z","abstract_excerpt":"We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to \"paint\" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encouraging this agent to follow human-like strokes when reconstructing digits. We also explore the use of a neural painter as a differentiable image parameterization. By directly optimizing brushstrokes to activate neurons in a pre-trained convolutional network, we can directly visuali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08410","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":""},"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":"1904.08410","created_at":"2026-05-17T23:48:04.322480+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.08410v2","created_at":"2026-05-17T23:48:04.322480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08410","created_at":"2026-05-17T23:48:04.322480+00:00"},{"alias_kind":"pith_short_12","alias_value":"FR72GR2AMV67","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FR72GR2AMV67FTXM","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FR72GR2A","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01572","citing_title":"MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB","json":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB.json","graph_json":"https://pith.science/api/pith-number/FR72GR2AMV67FTXMCCXFP2R3XB/graph.json","events_json":"https://pith.science/api/pith-number/FR72GR2AMV67FTXMCCXFP2R3XB/events.json","paper":"https://pith.science/paper/FR72GR2A"},"agent_actions":{"view_html":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB","download_json":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB.json","view_paper":"https://pith.science/paper/FR72GR2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.08410&json=true","fetch_graph":"https://pith.science/api/pith-number/FR72GR2AMV67FTXMCCXFP2R3XB/graph.json","fetch_events":"https://pith.science/api/pith-number/FR72GR2AMV67FTXMCCXFP2R3XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB/action/storage_attestation","attest_author":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB/action/author_attestation","sign_citation":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB/action/citation_signature","submit_replication":"https://pith.science/pith/FR72GR2AMV67FTXMCCXFP2R3XB/action/replication_record"}},"created_at":"2026-05-17T23:48:04.322480+00:00","updated_at":"2026-05-17T23:48:04.322480+00:00"}