{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BXWSXS6PJOB2VPXFENBBD5CSL5","short_pith_number":"pith:BXWSXS6P","schema_version":"1.0","canonical_sha256":"0ded2bcbcf4b83aabee5234211f4525f6046743b73dce0fb535418ba0cc7f590","source":{"kind":"arxiv","id":"2303.03196","version":2},"attestation_state":"computed","paper":{"title":"Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Daniel Hennes, John Schultz, Julien Perolat, Marc Lanctot, Max Olan Smith, Neil Burch, Thomas Anthony","submitted_at":"2023-03-02T15:06:52Z","abstract_excerpt":"Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largely been restricted to few interactions against experts, with the aim to reach some desired level of performance (e.g. beating a human professional player). We propose a benchmark for multiagent learning based on repeated play of the simple game Rock, Paper, Scissors along with a population of forty-three tournament entries, some of which are intentionally sub-"},"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":"2303.03196","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2023-03-02T15:06:52Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"403d0bb4457e874c5aa9807d433dffd51a9cdc6003f1f9a7867b25045b823d90","abstract_canon_sha256":"17cad7377d35c6e64b6b098c8b67a97aa1263379cc3fce323235ef53315d5dae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:36.996446Z","signature_b64":"ipcSbJDKf6BMgVGPjFiQf4mKqw/3l2ihdF3frUUG0OKOYHx3hQNyQ3XZ9qeK5RpEqyP/N4a7G/wcRuwDXbskDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ded2bcbcf4b83aabee5234211f4525f6046743b73dce0fb535418ba0cc7f590","last_reissued_at":"2026-07-05T07:07:36.995889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:36.995889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Daniel Hennes, John Schultz, Julien Perolat, Marc Lanctot, Max Olan Smith, Neil Burch, Thomas Anthony","submitted_at":"2023-03-02T15:06:52Z","abstract_excerpt":"Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largely been restricted to few interactions against experts, with the aim to reach some desired level of performance (e.g. beating a human professional player). We propose a benchmark for multiagent learning based on repeated play of the simple game Rock, Paper, Scissors along with a population of forty-three tournament entries, some of which are intentionally sub-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03196","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/2303.03196/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":"2303.03196","created_at":"2026-07-05T07:07:36.995949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03196v2","created_at":"2026-07-05T07:07:36.995949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03196","created_at":"2026-07-05T07:07:36.995949+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXWSXS6PJOB2","created_at":"2026-07-05T07:07:36.995949+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXWSXS6PJOB2VPXF","created_at":"2026-07-05T07:07:36.995949+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXWSXS6P","created_at":"2026-07-05T07:07:36.995949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05422","citing_title":"IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5","json":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5.json","graph_json":"https://pith.science/api/pith-number/BXWSXS6PJOB2VPXFENBBD5CSL5/graph.json","events_json":"https://pith.science/api/pith-number/BXWSXS6PJOB2VPXFENBBD5CSL5/events.json","paper":"https://pith.science/paper/BXWSXS6P"},"agent_actions":{"view_html":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5","download_json":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5.json","view_paper":"https://pith.science/paper/BXWSXS6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03196&json=true","fetch_graph":"https://pith.science/api/pith-number/BXWSXS6PJOB2VPXFENBBD5CSL5/graph.json","fetch_events":"https://pith.science/api/pith-number/BXWSXS6PJOB2VPXFENBBD5CSL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5/action/storage_attestation","attest_author":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5/action/author_attestation","sign_citation":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5/action/citation_signature","submit_replication":"https://pith.science/pith/BXWSXS6PJOB2VPXFENBBD5CSL5/action/replication_record"}},"created_at":"2026-07-05T07:07:36.995949+00:00","updated_at":"2026-07-05T07:07:36.995949+00:00"}