{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6DBXPFMWPQIMJPHHJFFRAODBDC","short_pith_number":"pith:6DBXPFMW","schema_version":"1.0","canonical_sha256":"f0c37795967c10c4bce7494b10386118a5194164723e695501d30781b94dccb7","source":{"kind":"arxiv","id":"1804.01118","version":1},"attestation_state":"computed","paper":{"title":"Synthesizing Programs for Images using Reinforced Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Igor Babuschkin, Oriol Vinyals, S.M. Ali Eslami, Tejas Kulkarni, Yaroslav Ganin","submitted_at":"2018-04-03T18:25:42Z","abstract_excerpt":"Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets."},"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":"1804.01118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-03T18:25:42Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"023c8546ca155f3ef15a75e81057e8997e8e294dc379b1c6746a589a20e037ee","abstract_canon_sha256":"e30f1745a5f233ec8c56b240cc2aa83bad03094ed61b7f7ca56bbc53269fec0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:16.070799Z","signature_b64":"FM1ti7JH4LZQQ5nviboDj0+X77deT7HgPv7ejB/KnWWm/DIxWLpHoghVYnXOUEDxwsoHIs7GkIj9sB/n5AjQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0c37795967c10c4bce7494b10386118a5194164723e695501d30781b94dccb7","last_reissued_at":"2026-05-18T00:19:16.070189Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:16.070189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesizing Programs for Images using Reinforced Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Igor Babuschkin, Oriol Vinyals, S.M. Ali Eslami, Tejas Kulkarni, Yaroslav Ganin","submitted_at":"2018-04-03T18:25:42Z","abstract_excerpt":"Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01118","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":""},"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":"1804.01118","created_at":"2026-05-18T00:19:16.070277+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.01118v1","created_at":"2026-05-18T00:19:16.070277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01118","created_at":"2026-05-18T00:19:16.070277+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DBXPFMWPQIM","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DBXPFMWPQIMJPHH","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DBXPFMW","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17673","citing_title":"SketchAgent: Language-Driven Sequential Sketch Generation","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC","json":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC.json","graph_json":"https://pith.science/api/pith-number/6DBXPFMWPQIMJPHHJFFRAODBDC/graph.json","events_json":"https://pith.science/api/pith-number/6DBXPFMWPQIMJPHHJFFRAODBDC/events.json","paper":"https://pith.science/paper/6DBXPFMW"},"agent_actions":{"view_html":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC","download_json":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC.json","view_paper":"https://pith.science/paper/6DBXPFMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.01118&json=true","fetch_graph":"https://pith.science/api/pith-number/6DBXPFMWPQIMJPHHJFFRAODBDC/graph.json","fetch_events":"https://pith.science/api/pith-number/6DBXPFMWPQIMJPHHJFFRAODBDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC/action/storage_attestation","attest_author":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC/action/author_attestation","sign_citation":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC/action/citation_signature","submit_replication":"https://pith.science/pith/6DBXPFMWPQIMJPHHJFFRAODBDC/action/replication_record"}},"created_at":"2026-05-18T00:19:16.070277+00:00","updated_at":"2026-05-18T00:19:16.070277+00:00"}