{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MUPCFTAWHE5PNTSXAM6OPI4VZQ","short_pith_number":"pith:MUPCFTAW","schema_version":"1.0","canonical_sha256":"651e22cc16393af6ce57033ce7a395cc04e2ea63c8129d04df344fe6c6c490ea","source":{"kind":"arxiv","id":"1812.00898","version":1},"attestation_state":"computed","paper":{"title":"Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aishwarya Agrawal, Ali Eslami, Felix Hill, Mateusz Malinowski, Oriol Vinyals, Tejas Kulkarni","submitted_at":"2018-12-03T16:51:35Z","abstract_excerpt":"Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a given symbolic instruction. Final goals are specified to our agent via images of the scenes. A symbolic instruction consistent with the goal images is used as the conditioning input for our policies. Since a single instruction corresponds to a diverse set of different but still consistent end-goal images, the agent needs to learn to generate a distribution "},"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":"1812.00898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T16:51:35Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"13e9295f367f35dd9273297bc5746e59ad3cf0bbad5b60b3f66d6f0282df3d4f","abstract_canon_sha256":"d302cd36302cfd3e23fd5e5efb662ac6ccbdd2330eadf207e7e4d01674a23a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:18.639414Z","signature_b64":"jTe5dADhQox3Mk1DrceDLEyEEPt9yOc3K2p+xUl1vYQQ9nflStVKkPJuIGXDu2Cy/ng8pYmUgGKFcX5k2JzJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"651e22cc16393af6ce57033ce7a395cc04e2ea63c8129d04df344fe6c6c490ea","last_reissued_at":"2026-05-17T23:59:18.639033Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:18.639033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aishwarya Agrawal, Ali Eslami, Felix Hill, Mateusz Malinowski, Oriol Vinyals, Tejas Kulkarni","submitted_at":"2018-12-03T16:51:35Z","abstract_excerpt":"Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a given symbolic instruction. Final goals are specified to our agent via images of the scenes. A symbolic instruction consistent with the goal images is used as the conditioning input for our policies. Since a single instruction corresponds to a diverse set of different but still consistent end-goal images, the agent needs to learn to generate a distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00898","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":"1812.00898","created_at":"2026-05-17T23:59:18.639094+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00898v1","created_at":"2026-05-17T23:59:18.639094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00898","created_at":"2026-05-17T23:59:18.639094+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUPCFTAWHE5P","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUPCFTAWHE5PNTSX","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUPCFTAW","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ","json":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ.json","graph_json":"https://pith.science/api/pith-number/MUPCFTAWHE5PNTSXAM6OPI4VZQ/graph.json","events_json":"https://pith.science/api/pith-number/MUPCFTAWHE5PNTSXAM6OPI4VZQ/events.json","paper":"https://pith.science/paper/MUPCFTAW"},"agent_actions":{"view_html":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ","download_json":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ.json","view_paper":"https://pith.science/paper/MUPCFTAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00898&json=true","fetch_graph":"https://pith.science/api/pith-number/MUPCFTAWHE5PNTSXAM6OPI4VZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MUPCFTAWHE5PNTSXAM6OPI4VZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ/action/storage_attestation","attest_author":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ/action/author_attestation","sign_citation":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ/action/citation_signature","submit_replication":"https://pith.science/pith/MUPCFTAWHE5PNTSXAM6OPI4VZQ/action/replication_record"}},"created_at":"2026-05-17T23:59:18.639094+00:00","updated_at":"2026-05-17T23:59:18.639094+00:00"}