{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CCYJQLEHAJICB5QKROUSE4K32B","short_pith_number":"pith:CCYJQLEH","schema_version":"1.0","canonical_sha256":"10b0982c87025020f60a8ba922715bd068f03c8d752a78c84b39a204103ad61b","source":{"kind":"arxiv","id":"2607.06854","version":1},"attestation_state":"computed","paper":{"title":"A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Mahdi Salmani, Mohammadsaeed Haghi, Nima Kelidari","submitted_at":"2026-07-07T23:11:21Z","abstract_excerpt":"Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of themselves. So we build a strong, fixed, rule-based expert for Gin Rummy and use it only as a yardstick, never for training. It beats every agent we trained 70 to 99 percent of the time. Across more than a hundred runs, we isolate what makes a lightweight agent stronger. Trust region updates, a well-aimed reward, a curriculum of tougher opponents, warm starting,"},"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":"2607.06854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:11:21Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"69567d4251384ee8b664022d10ead78e835b2ceb5d80836aaad53bb9b6cc6880","abstract_canon_sha256":"30f4ad8fa704786ad191efdd822681ab92d02570766dee239b937ce7694a963e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:31.444419Z","signature_b64":"3pdyz+KTgHRgZqqYG+mvBbQrlUJZx9ZMsGVqnZ1CyWQKthjIQ4y2bIxfI1S+1gtwwdZ4EGHhut18gZZy7HoeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10b0982c87025020f60a8ba922715bd068f03c8d752a78c84b39a204103ad61b","last_reissued_at":"2026-07-09T00:19:31.443721Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:31.443721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Mahdi Salmani, Mohammadsaeed Haghi, Nima Kelidari","submitted_at":"2026-07-07T23:11:21Z","abstract_excerpt":"Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of themselves. So we build a strong, fixed, rule-based expert for Gin Rummy and use it only as a yardstick, never for training. It beats every agent we trained 70 to 99 percent of the time. Across more than a hundred runs, we isolate what makes a lightweight agent stronger. Trust region updates, a well-aimed reward, a curriculum of tougher opponents, warm starting,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06854","kind":"arxiv","version":1},"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/2607.06854/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":"2607.06854","created_at":"2026-07-09T00:19:31.443812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06854v1","created_at":"2026-07-09T00:19:31.443812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06854","created_at":"2026-07-09T00:19:31.443812+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCYJQLEHAJIC","created_at":"2026-07-09T00:19:31.443812+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCYJQLEHAJICB5QK","created_at":"2026-07-09T00:19:31.443812+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCYJQLEH","created_at":"2026-07-09T00:19:31.443812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B","json":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B.json","graph_json":"https://pith.science/api/pith-number/CCYJQLEHAJICB5QKROUSE4K32B/graph.json","events_json":"https://pith.science/api/pith-number/CCYJQLEHAJICB5QKROUSE4K32B/events.json","paper":"https://pith.science/paper/CCYJQLEH"},"agent_actions":{"view_html":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B","download_json":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B.json","view_paper":"https://pith.science/paper/CCYJQLEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06854&json=true","fetch_graph":"https://pith.science/api/pith-number/CCYJQLEHAJICB5QKROUSE4K32B/graph.json","fetch_events":"https://pith.science/api/pith-number/CCYJQLEHAJICB5QKROUSE4K32B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B/action/storage_attestation","attest_author":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B/action/author_attestation","sign_citation":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B/action/citation_signature","submit_replication":"https://pith.science/pith/CCYJQLEHAJICB5QKROUSE4K32B/action/replication_record"}},"created_at":"2026-07-09T00:19:31.443812+00:00","updated_at":"2026-07-09T00:19:31.443812+00:00"}