{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MAFNDXAF2UZSTY5ZLM2UIH3PXW","short_pith_number":"pith:MAFNDXAF","schema_version":"1.0","canonical_sha256":"600ad1dc05d53329e3b95b35441f6fbd98be1488f6af40ad7ecf2b690c1d1ae5","source":{"kind":"arxiv","id":"2507.06825","version":2},"attestation_state":"computed","paper":{"title":"Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Martin Schmid, Matej Straka","submitted_at":"2025-07-09T13:15:05Z","abstract_excerpt":"We introduce a real-time strategy game environment based on Generals.io, a game with thousands of weekly active players. Our environment is fully compatible with Gymnasium and PettingZoo and is capable of running thousands of frames per second on commodity hardware. We also present a reference agent, trained with supervised pre-training and self-play, which reached the top 0.003% of the 1v1 human leaderboard after only 36 hours on a single H100 GPU. To accelerate learning, we incorporate potential-based reward shaping and memory features. Our contributions of a modular RTS benchmark and a comp"},"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":"2507.06825","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T13:15:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b4b40bcb97238e7090fdbd3af6e9f11ae9b59d39aac18c8014bde725eb8d4ab","abstract_canon_sha256":"1280b12a2b14879dda742cadaeeca0ee4251930a97f89d0a807d1a5bc44834b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:54.236596Z","signature_b64":"cuMxVzoWjKIknOSyXvLIY5QZfkxPjpth+bnPd6KLK0bR+jkGEPqgxIm14ndTL4ICQY9o7rmu7jXxteMBwaagCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"600ad1dc05d53329e3b95b35441f6fbd98be1488f6af40ad7ecf2b690c1d1ae5","last_reissued_at":"2026-07-05T11:34:54.235989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:54.235989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Martin Schmid, Matej Straka","submitted_at":"2025-07-09T13:15:05Z","abstract_excerpt":"We introduce a real-time strategy game environment based on Generals.io, a game with thousands of weekly active players. Our environment is fully compatible with Gymnasium and PettingZoo and is capable of running thousands of frames per second on commodity hardware. We also present a reference agent, trained with supervised pre-training and self-play, which reached the top 0.003% of the 1v1 human leaderboard after only 36 hours on a single H100 GPU. To accelerate learning, we incorporate potential-based reward shaping and memory features. Our contributions of a modular RTS benchmark and a comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06825","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.06825/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":"2507.06825","created_at":"2026-07-05T11:34:54.236061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06825v2","created_at":"2026-07-05T11:34:54.236061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06825","created_at":"2026-07-05T11:34:54.236061+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAFNDXAF2UZS","created_at":"2026-07-05T11:34:54.236061+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAFNDXAF2UZSTY5Z","created_at":"2026-07-05T11:34:54.236061+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAFNDXAF","created_at":"2026-07-05T11:34:54.236061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23348","citing_title":"Superhuman AI for Generals.io Using Self-Play Reinforcement Learning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW","json":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW.json","graph_json":"https://pith.science/api/pith-number/MAFNDXAF2UZSTY5ZLM2UIH3PXW/graph.json","events_json":"https://pith.science/api/pith-number/MAFNDXAF2UZSTY5ZLM2UIH3PXW/events.json","paper":"https://pith.science/paper/MAFNDXAF"},"agent_actions":{"view_html":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW","download_json":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW.json","view_paper":"https://pith.science/paper/MAFNDXAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06825&json=true","fetch_graph":"https://pith.science/api/pith-number/MAFNDXAF2UZSTY5ZLM2UIH3PXW/graph.json","fetch_events":"https://pith.science/api/pith-number/MAFNDXAF2UZSTY5ZLM2UIH3PXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW/action/storage_attestation","attest_author":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW/action/author_attestation","sign_citation":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW/action/citation_signature","submit_replication":"https://pith.science/pith/MAFNDXAF2UZSTY5ZLM2UIH3PXW/action/replication_record"}},"created_at":"2026-07-05T11:34:54.236061+00:00","updated_at":"2026-07-05T11:34:54.236061+00:00"}