{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NQYFPFEYSPPH4DX3ONPVVCLML7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d86233b64fbd083bcbbacd8db46fb63281f8c550027869ee33267282ada01dca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T17:17:23Z","title_canon_sha256":"c082ab668b4da05e87061ae1cb8cd21c00ef47a275548e7cfdfd4931208fcb68"},"schema_version":"1.0","source":{"id":"2606.29511","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29511","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29511v1","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29511","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"NQYFPFEYSPPH","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"NQYFPFEYSPPH4DX3","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"NQYFPFEY","created_at":"2026-06-30T01:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:cd7ac4aa4688be6dffef7a7fea1300e8c4c45a6dfdc4cb6a05ea2157dc1253ba","target":"graph","created_at":"2026-06-30T01:18:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.29511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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%","authors_text":"Jesse Ponnock, Lucas Ho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T17:17:23Z","title":"Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29511","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c45d5082e8237b2c951e11c29ded98675e88e0d1b4323dc674ea857f8952181a","target":"record","created_at":"2026-06-30T01:18:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d86233b64fbd083bcbbacd8db46fb63281f8c550027869ee33267282ada01dca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T17:17:23Z","title_canon_sha256":"c082ab668b4da05e87061ae1cb8cd21c00ef47a275548e7cfdfd4931208fcb68"},"schema_version":"1.0","source":{"id":"2606.29511","kind":"arxiv","version":1}},"canonical_sha256":"6c3057949893de7e0efb735f5a896c5ffb74d3199ed94148814d1954498b928f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c3057949893de7e0efb735f5a896c5ffb74d3199ed94148814d1954498b928f","first_computed_at":"2026-06-30T01:18:09.782173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:09.782173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A5eyWI3rcnaDihpwUeoDwCkdjE8VUSUlzRx4IEUzwoXK9BX94Km8BxrASkZ6oGK9Xs3KTehTOvPGp3mNQC88Bw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:09.782846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29511","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c45d5082e8237b2c951e11c29ded98675e88e0d1b4323dc674ea857f8952181a","sha256:cd7ac4aa4688be6dffef7a7fea1300e8c4c45a6dfdc4cb6a05ea2157dc1253ba"],"state_sha256":"55ed56f9d32af7c041c305b21cac29805dee415f3aa46bfdba210cb4c80f4cba"}