{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PSPJSOUZATTXCSIHGUX7IANGZH","short_pith_number":"pith:PSPJSOUZ","schema_version":"1.0","canonical_sha256":"7c9e993a9904e7714907352ff401a6c9f7be59c5416044971ed9e667aedcb15e","source":{"kind":"arxiv","id":"1511.07401","version":2},"attestation_state":"computed","paper":{"title":"MazeBase: A Sandbox for Learning from Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Arthur Szlam, Gabriel Synnaeve, Rob Fergus, Sainbayar Sukhbaatar, Soumith Chintala","submitted_at":"2015-11-23T20:23:53Z","abstract_excerpt":"This paper introduces MazeBase: an environment for simple 2D games, designed as a sandbox for machine learning approaches to reasoning and planning. Within it, we create 10 simple games embodying a range of algorithmic tasks (e.g. if-then statements or set negation). A variety of neural models (fully connected, convolutional network, memory network) are deployed via reinforcement learning on these games, with and without a procedurally generated curriculum. Despite the tasks' simplicity, the performance of the models is far from optimal, suggesting directions for future development. We also de"},"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":"1511.07401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T20:23:53Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"9a2007eca3e6f85cf647ffdf98e3028e66b56fb9a1d69b42c7358d39d7565bd0","abstract_canon_sha256":"8b1aadde94ad28dd461612750ac537e32982bac7d09d95e621ef33704bfc0368"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:12.974053Z","signature_b64":"9hNdEBM4JYesZNmWrxwdgJ6AiYqcT5dRxXe5TjUksuN89rgf+EqqwEENcBF29l3V4amWXHDamXqR5n73W/47DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c9e993a9904e7714907352ff401a6c9f7be59c5416044971ed9e667aedcb15e","last_reissued_at":"2026-05-18T01:23:12.973308Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:12.973308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MazeBase: A Sandbox for Learning from Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Arthur Szlam, Gabriel Synnaeve, Rob Fergus, Sainbayar Sukhbaatar, Soumith Chintala","submitted_at":"2015-11-23T20:23:53Z","abstract_excerpt":"This paper introduces MazeBase: an environment for simple 2D games, designed as a sandbox for machine learning approaches to reasoning and planning. Within it, we create 10 simple games embodying a range of algorithmic tasks (e.g. if-then statements or set negation). A variety of neural models (fully connected, convolutional network, memory network) are deployed via reinforcement learning on these games, with and without a procedurally generated curriculum. Despite the tasks' simplicity, the performance of the models is far from optimal, suggesting directions for future development. We also de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07401","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":"1511.07401","created_at":"2026-05-18T01:23:12.973448+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07401v2","created_at":"2026-05-18T01:23:12.973448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07401","created_at":"2026-05-18T01:23:12.973448+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSPJSOUZATTX","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSPJSOUZATTXCSIH","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSPJSOUZ","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH","json":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH.json","graph_json":"https://pith.science/api/pith-number/PSPJSOUZATTXCSIHGUX7IANGZH/graph.json","events_json":"https://pith.science/api/pith-number/PSPJSOUZATTXCSIHGUX7IANGZH/events.json","paper":"https://pith.science/paper/PSPJSOUZ"},"agent_actions":{"view_html":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH","download_json":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH.json","view_paper":"https://pith.science/paper/PSPJSOUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07401&json=true","fetch_graph":"https://pith.science/api/pith-number/PSPJSOUZATTXCSIHGUX7IANGZH/graph.json","fetch_events":"https://pith.science/api/pith-number/PSPJSOUZATTXCSIHGUX7IANGZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH/action/storage_attestation","attest_author":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH/action/author_attestation","sign_citation":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH/action/citation_signature","submit_replication":"https://pith.science/pith/PSPJSOUZATTXCSIHGUX7IANGZH/action/replication_record"}},"created_at":"2026-05-18T01:23:12.973448+00:00","updated_at":"2026-05-18T01:23:12.973448+00:00"}