{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_6fa2e2b189d1a7f4c2aef5273c8c82879bac265903ba78032f01c763e6ce4a9a","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_6fa2e2b189d1a7f4c2aef5273c8c82879bac265903ba78032f01c763e6ce4a9a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fd020e1e46041c4e0e473aacea985a9c41fc100e2745ac865d262af55f666cae","published":"Thu, 09 Jul 2026 00:00:00 -0400","receipt_hash":"fd020e1e46041c4e0e473aacea985a9c41fc100e2745ac865d262af55f666cae","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"fd020e1e46041c4e0e473aacea985a9c41fc100e2745ac865d262af55f666cae","observed_at":"2026-07-09T04:43:38.345231Z","parent_run_hash":"3e22c7c40abc4d94232acf1766a43492b8b8d51d10a58f1109535988a16554e6","published":"Thu, 09 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2607.06854v1 Announce Type: cross \nAbstract: 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, and keeping the best checkpoint all help, and stacking them lifts a self-play champion from about 30 to 36 percent against the expert. Several ideas did not pay off. Short-term and longer-term reward shaping, learned state embeddings, imitation and DAgger, and a live large language model opponent were each unhelpful, too slow, or too heavy to tra","title":"A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong","url":"https://arxiv.org/abs/2607.06854","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.06854v1 Announce Type: cross \nAbstract: 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, and keeping the best checkpoint all help, and stacking them lifts a self-play champion from about 30 to 36 percent against the expert. Several ideas did not pay off. Short-term and longer-term reward shaping, learned state embeddings, imitation and DAgger, and a live large language model opponent were each unhelpful, too slow, or too heavy to tra","title":"A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-09T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.06854"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:c83f98368ef84a99ba2717fd055d38f874195044a7501a5c34d4cd5c7d40bfc36667ed82acec0a84862a09a159e9cdb7f896c859217f900c849c568c25b34e0e","signer":"crovia.substrate","subject":{"observed_at":"2026-07-09T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.06854"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"7eb5f4e7ce73694b9a635d4bfdbeae4353105f05d0584857d80ad05aa7fd83c7","leaf_index":296082,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"09a0469ca22e3dc0d7e66f5d9e2b13ce7b9a02bea318f5e75fd214306400aa0c","side":"right"},{"sibling":"68f882eeb04338f319b0dc7ffcb239c506f572cf75581893b04ecdf0c06f6423","side":"left"},{"sibling":"02f3a564e9f20f6d512cd0a0f2842bcef73da22a26a2caf82f5aa6754b6e598f","side":"right"},{"sibling":"096c54968c1103407321d012749a38b83d9e29be3e1e004941701ee610f49a72","side":"right"},{"sibling":"b0a450bec5bab300b0fbe592d4258400f10372db0492ed3f7090f5cd4515424e","side":"left"},{"sibling":"283005c20026acb13d616599e4790a32f791d2cb73de3d6b876c68697f7d72dd","side":"right"},{"sibling":"6c45b7ac79d3163d45e1d56cd7db0b01778b873ed657ef89d1d09b6352b1b91e","side":"right"},{"sibling":"6e8f2e16cb75beb661e7f7b63be19804b6f6474dfbf899f8e417b19695f2fba4","side":"left"},{"sibling":"47a94dfb6e50a020e68582e6af2e6a8cf5a4c7efe9fed3deaedbc51f53d75367","side":"right"},{"sibling":"92bb57de69c78fd32ac7108b10d81676c184265a5a53de3c4b22d8cf3b54b499","side":"right"},{"sibling":"85a226efd14acc17835b04bc26706fa44595edbd531f194faf59f60ab72d4bb8","side":"left"},{"sibling":"da38b05536b12aee196b6ac988739211c257d32da790faccf5ac4b0cbc1bb15c","side":"right"},{"sibling":"d438dc3eddb0b14dc8b97cd021a4f44545ce5a8e827f3ea4044fd32b1877475e","side":"right"},{"sibling":"f73ad10346837ae47f59f0647f79b9416e1d499bf2b90af44448e7f09372200a","side":"right"},{"sibling":"bdc09902fcd434c0f7d3e680bf550e560777228c0b085ce80c637ce97fc4104c","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"ba603dffe985ef518e3a72793a3eaca83a7f1a79e5491fd0f62f421339f2d137","side":"right"},{"sibling":"be20b90931f0a14e3558ea4387537200fcbd14e019b3c5ed07a2ae4c62fc7c42","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":296360,"merkle_root":"64af62f723a5bc02adfa98b77e2006fc634de4ebf68626694f052342a200bea2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260709T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-09T05:38:18Z","sig_algorithm":"ed25519","signature":"92ece7411e0d82898aac164e7d6573a6d0f7a595aad0780d710d873e548a061d2a8678cef4d237d3bf0eabe0a5f766b41cbc0b4bada2801e7532026291b4a309","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_6fa2e2b189d1a7f4c2aef5273c8c82879bac265903ba78032f01c763e6ce4a9a"}}