{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KLEHK2IRF74OO7L4ID7SUH2BIV","short_pith_number":"pith:KLEHK2IR","schema_version":"1.0","canonical_sha256":"52c87569112ff8e77d7c40ff2a1f414578c7d0c08c6304aa8c76b0b43b4ba82d","source":{"kind":"arxiv","id":"1901.08106","version":2},"attestation_state":"computed","paper":{"title":"Open-ended Learning in Symmetric Zero-sum Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Balduzzi, Julien Perolat, Marta Garnelo, Max Jaderberg, Thore Graepel, Wojciech M. Czarnecki, Yoram Bachrach","submitted_at":"2019-01-23T19:56:17Z","abstract_excerpt":"Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences of agents of increasing strength. However, nontransitive games, such as rock-paper-scissors, can exhibit strategic cycles, and there is no longer a clear objective -- we want agents to increase in strength, but against whom is unclear. In this paper, we introduce a geometric framework for formulating agent objectives in zero-sum games, in order to construct adaptive sequences "},"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":"1901.08106","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T19:56:17Z","cross_cats_sorted":["cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"6425c1df082adcd62651eb62cc104ad7f265a3a8de4bee19f839eb8ceecb6121","abstract_canon_sha256":"0dcc5b410920dd4da7e1dbae54486c0b1b782fdec894dff22ee843d72accf3ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:29.110503Z","signature_b64":"LUYhavygkUNWZQLEexehiUsuyFQHbLVW7xzdEVtl1eux4sw+giJDlbrUFnJE5WCr9gMF6vlgCouFHX7S38q3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c87569112ff8e77d7c40ff2a1f414578c7d0c08c6304aa8c76b0b43b4ba82d","last_reissued_at":"2026-05-17T23:46:29.109925Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:29.109925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-ended Learning in Symmetric Zero-sum Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Balduzzi, Julien Perolat, Marta Garnelo, Max Jaderberg, Thore Graepel, Wojciech M. Czarnecki, Yoram Bachrach","submitted_at":"2019-01-23T19:56:17Z","abstract_excerpt":"Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences of agents of increasing strength. However, nontransitive games, such as rock-paper-scissors, can exhibit strategic cycles, and there is no longer a clear objective -- we want agents to increase in strength, but against whom is unclear. In this paper, we introduce a geometric framework for formulating agent objectives in zero-sum games, in order to construct adaptive sequences "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08106","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":"1901.08106","created_at":"2026-05-17T23:46:29.110002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08106v2","created_at":"2026-05-17T23:46:29.110002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08106","created_at":"2026-05-17T23:46:29.110002+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLEHK2IRF74O","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLEHK2IRF74OO7L4","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLEHK2IR","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1912.06680","citing_title":"Dota 2 with Large Scale Deep Reinforcement Learning","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV","json":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV.json","graph_json":"https://pith.science/api/pith-number/KLEHK2IRF74OO7L4ID7SUH2BIV/graph.json","events_json":"https://pith.science/api/pith-number/KLEHK2IRF74OO7L4ID7SUH2BIV/events.json","paper":"https://pith.science/paper/KLEHK2IR"},"agent_actions":{"view_html":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV","download_json":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV.json","view_paper":"https://pith.science/paper/KLEHK2IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08106&json=true","fetch_graph":"https://pith.science/api/pith-number/KLEHK2IRF74OO7L4ID7SUH2BIV/graph.json","fetch_events":"https://pith.science/api/pith-number/KLEHK2IRF74OO7L4ID7SUH2BIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV/action/storage_attestation","attest_author":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV/action/author_attestation","sign_citation":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV/action/citation_signature","submit_replication":"https://pith.science/pith/KLEHK2IRF74OO7L4ID7SUH2BIV/action/replication_record"}},"created_at":"2026-05-17T23:46:29.110002+00:00","updated_at":"2026-05-17T23:46:29.110002+00:00"}