{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NQYFPFEYSPPH4DX3ONPVVCLML7","short_pith_number":"pith:NQYFPFEY","schema_version":"1.0","canonical_sha256":"6c3057949893de7e0efb735f5a896c5ffb74d3199ed94148814d1954498b928f","source":{"kind":"arxiv","id":"2606.29511","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jesse Ponnock, Lucas Ho","submitted_at":"2026-06-28T17:17:23Z","abstract_excerpt":"World 1-1 of Super Mario Bros is widely celebrated as a masterclass in game design: its progressive structure is credited with teaching players core mechanics through the level itself. We ask whether that structure is empirically measurable using reinforcement learning. We implement World 1-1 from scratch as a fully discrete environment and compare four algorithms -- Q-Learning, SARSA, Monte Carlo, and Deep Q-Network (DQN) -- across three progressively complex versions of the same level. Monte Carlo emerges as the strongest agent (94.9% $\\pm$ 1.5% win rate), outperforming DQN (76.4% $\\pm$ 3.4%"},"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":"2606.29511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T17:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"c082ab668b4da05e87061ae1cb8cd21c00ef47a275548e7cfdfd4931208fcb68","abstract_canon_sha256":"d86233b64fbd083bcbbacd8db46fb63281f8c550027869ee33267282ada01dca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:09.782846Z","signature_b64":"A5eyWI3rcnaDihpwUeoDwCkdjE8VUSUlzRx4IEUzwoXK9BX94Km8BxrASkZ6oGK9Xs3KTehTOvPGp3mNQC88Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c3057949893de7e0efb735f5a896c5ffb74d3199ed94148814d1954498b928f","last_reissued_at":"2026-06-30T01:18:09.782173Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:09.782173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jesse Ponnock, Lucas Ho","submitted_at":"2026-06-28T17:17:23Z","abstract_excerpt":"World 1-1 of Super Mario Bros is widely celebrated as a masterclass in game design: its progressive structure is credited with teaching players core mechanics through the level itself. We ask whether that structure is empirically measurable using reinforcement learning. We implement World 1-1 from scratch as a fully discrete environment and compare four algorithms -- Q-Learning, SARSA, Monte Carlo, and Deep Q-Network (DQN) -- across three progressively complex versions of the same level. Monte Carlo emerges as the strongest agent (94.9% $\\pm$ 1.5% win rate), outperforming DQN (76.4% $\\pm$ 3.4%"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29511","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/2606.29511/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":"2606.29511","created_at":"2026-06-30T01:18:09.782267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29511v1","created_at":"2026-06-30T01:18:09.782267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29511","created_at":"2026-06-30T01:18:09.782267+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQYFPFEYSPPH","created_at":"2026-06-30T01:18:09.782267+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQYFPFEYSPPH4DX3","created_at":"2026-06-30T01:18:09.782267+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQYFPFEY","created_at":"2026-06-30T01:18:09.782267+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/NQYFPFEYSPPH4DX3ONPVVCLML7","json":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7.json","graph_json":"https://pith.science/api/pith-number/NQYFPFEYSPPH4DX3ONPVVCLML7/graph.json","events_json":"https://pith.science/api/pith-number/NQYFPFEYSPPH4DX3ONPVVCLML7/events.json","paper":"https://pith.science/paper/NQYFPFEY"},"agent_actions":{"view_html":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7","download_json":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7.json","view_paper":"https://pith.science/paper/NQYFPFEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29511&json=true","fetch_graph":"https://pith.science/api/pith-number/NQYFPFEYSPPH4DX3ONPVVCLML7/graph.json","fetch_events":"https://pith.science/api/pith-number/NQYFPFEYSPPH4DX3ONPVVCLML7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7/action/storage_attestation","attest_author":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7/action/author_attestation","sign_citation":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7/action/citation_signature","submit_replication":"https://pith.science/pith/NQYFPFEYSPPH4DX3ONPVVCLML7/action/replication_record"}},"created_at":"2026-06-30T01:18:09.782267+00:00","updated_at":"2026-06-30T01:18:09.782267+00:00"}