{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CCYJQLEHAJICB5QKROUSE4K32B","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":"30f4ad8fa704786ad191efdd822681ab92d02570766dee239b937ce7694a963e","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:11:21Z","title_canon_sha256":"69567d4251384ee8b664022d10ead78e835b2ceb5d80836aaad53bb9b6cc6880"},"schema_version":"1.0","source":{"id":"2607.06854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06854","created_at":"2026-07-09T00:19:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06854v1","created_at":"2026-07-09T00:19:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06854","created_at":"2026-07-09T00:19:31Z"},{"alias_kind":"pith_short_12","alias_value":"CCYJQLEHAJIC","created_at":"2026-07-09T00:19:31Z"},{"alias_kind":"pith_short_16","alias_value":"CCYJQLEHAJICB5QK","created_at":"2026-07-09T00:19:31Z"},{"alias_kind":"pith_short_8","alias_value":"CCYJQLEH","created_at":"2026-07-09T00:19:31Z"}],"graph_snapshots":[{"event_id":"sha256:a38b6362401a42d48fc4242d437c26185126d8f541bfd7097367d00703653cee","target":"graph","created_at":"2026-07-09T00:19:31Z","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/2607.06854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Mahdi Salmani, Mohammadsaeed Haghi, Nima Kelidari","cross_cats":["cs.AI","cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:11:21Z","title":"A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06854","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:a9c2b030cb0706d4a80aa41e39a5cac5fe7cc3b238a783b8ae4f034e700d3733","target":"record","created_at":"2026-07-09T00:19:31Z","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":"30f4ad8fa704786ad191efdd822681ab92d02570766dee239b937ce7694a963e","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:11:21Z","title_canon_sha256":"69567d4251384ee8b664022d10ead78e835b2ceb5d80836aaad53bb9b6cc6880"},"schema_version":"1.0","source":{"id":"2607.06854","kind":"arxiv","version":1}},"canonical_sha256":"10b0982c87025020f60a8ba922715bd068f03c8d752a78c84b39a204103ad61b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10b0982c87025020f60a8ba922715bd068f03c8d752a78c84b39a204103ad61b","first_computed_at":"2026-07-09T00:19:31.443721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T00:19:31.443721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3pdyz+KTgHRgZqqYG+mvBbQrlUJZx9ZMsGVqnZ1CyWQKthjIQ4y2bIxfI1S+1gtwwdZ4EGHhut18gZZy7HoeAw==","signature_status":"signed_v1","signed_at":"2026-07-09T00:19:31.444419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9c2b030cb0706d4a80aa41e39a5cac5fe7cc3b238a783b8ae4f034e700d3733","sha256:a38b6362401a42d48fc4242d437c26185126d8f541bfd7097367d00703653cee"],"state_sha256":"49b5931094069c9803a27ae5f03621613004e149dd1fdcf2eab66626f8c002e1"}