{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SARCLDAEPKV37H4MUNNY6XADDM","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":"a951f4f62f91a0f58344967b75270585b1b4433c2a45518d07c808e1cd4773d3","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T14:22:42Z","title_canon_sha256":"244ea45acee77e7964c77a8521e73558056bb6f8f23e6880a7db04f6a75739d8"},"schema_version":"1.0","source":{"id":"2607.18296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18296","created_at":"2026-07-22T00:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18296v1","created_at":"2026-07-22T00:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18296","created_at":"2026-07-22T00:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"SARCLDAEPKV3","created_at":"2026-07-22T00:22:40Z"},{"alias_kind":"pith_short_16","alias_value":"SARCLDAEPKV37H4M","created_at":"2026-07-22T00:22:40Z"},{"alias_kind":"pith_short_8","alias_value":"SARCLDAE","created_at":"2026-07-22T00:22:40Z"}],"graph_snapshots":[{"event_id":"sha256:dc2794313bf79a87073aa62a55c2a93a3039fefd4c8926f6e6ac7b7921162e36","target":"graph","created_at":"2026-07-22T00:22:40Z","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/2607.18296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Baghchal is a two-player asymmetric board game with Nepali origins where four tigers are to capture goats and twenty goats desire to keep tigers in immobility. Although Baghchal has a complex structure which is strategic, has perfect information structure, and has cultural meaning, it has not been adequately covered in deep reinforcement learning (RL) literature. This paper gives a systematic exploration of four deep RL solutions Deep Q-Network (DQN), REINFORCE, Proximal Policy Optimization (PPO) and MuZero that are trained on one side of the asymmetric gameplay of Baghchal and then evaluated ","authors_text":"Aarav Subedi, Aaryan Shakya, Manoj Shakya, Ranjit Raut, Sagun Rai","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T14:22:42Z","title":"Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18296","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:c7cc6525cccb6f130c1e69c63d2f873676ff4e80179c888bbe9b532c25587fa5","target":"record","created_at":"2026-07-22T00:22:40Z","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":"a951f4f62f91a0f58344967b75270585b1b4433c2a45518d07c808e1cd4773d3","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T14:22:42Z","title_canon_sha256":"244ea45acee77e7964c77a8521e73558056bb6f8f23e6880a7db04f6a75739d8"},"schema_version":"1.0","source":{"id":"2607.18296","kind":"arxiv","version":1}},"canonical_sha256":"9022258c047aabbf9f8ca35b8f5c031b024ad9b9eff5a01709da39501d48f901","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9022258c047aabbf9f8ca35b8f5c031b024ad9b9eff5a01709da39501d48f901","first_computed_at":"2026-07-22T00:22:40.537986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:40.537986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"st405md1t3wYoQPoCZU5k8uR8+h30IMArda8NarWCIrbzcnHVzFl1l7hXCCP2xgaa+FIyWtxcflB0aE9ZeDrDg==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:40.538801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7cc6525cccb6f130c1e69c63d2f873676ff4e80179c888bbe9b532c25587fa5","sha256:dc2794313bf79a87073aa62a55c2a93a3039fefd4c8926f6e6ac7b7921162e36"],"state_sha256":"8d27620929104b4ef5c0d9f7b4fcb53efbb58b65c4b1733b166e62485f86a582"}