{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GY3U4XPXCXGATWWOYN3W3F57RZ","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":"b598d163eb536a01c7febff959d96c6df69334c824cb0907ee704c2b5e7040c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-07T09:48:39Z","title_canon_sha256":"5201cbe43505ff2c91d9145871f56ff59714d0c9114a65693c02dd94b7984741"},"schema_version":"1.0","source":{"id":"2502.04788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04788","created_at":"2026-07-05T10:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04788v1","created_at":"2026-07-05T10:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04788","created_at":"2026-07-05T10:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"GY3U4XPXCXGA","created_at":"2026-07-05T10:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"GY3U4XPXCXGATWWO","created_at":"2026-07-05T10:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"GY3U4XPX","created_at":"2026-07-05T10:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:afa6fad251e2eb8b8b3fc14394aed9fff56e0a419e30d5bac1bfb5621d005be4","target":"graph","created_at":"2026-07-05T10:10:57Z","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/2502.04788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate a competitive market involving two agents who consider both their own wealth and the wealth gap with their opponent. Both agents can invest in a financial market consisting of a risk-free asset and a risky asset, under conditions where model parameters are partially or completely unknown. This setup gives rise to a non-zero-sum differential game within the framework of reinforcement learning (RL). Each agent aims to maximize his own Choquet-regularized, time-inconsistent mean-variance objective. Adopting the dynamic programming approach, we derive a time-consisten","authors_text":"Hao Wang, Junyi Guo, Kam Chuen Yuen, Xia Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-07T09:48:39Z","title":"A non-zero-sum game with reinforcement learning under mean-variance framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04788","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:e46f84166d2063b4b53cbc83aaf46adbe089ef7771f4c7ec47891bfe11830094","target":"record","created_at":"2026-07-05T10:10:57Z","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":"b598d163eb536a01c7febff959d96c6df69334c824cb0907ee704c2b5e7040c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-07T09:48:39Z","title_canon_sha256":"5201cbe43505ff2c91d9145871f56ff59714d0c9114a65693c02dd94b7984741"},"schema_version":"1.0","source":{"id":"2502.04788","kind":"arxiv","version":1}},"canonical_sha256":"36374e5df715cc09dacec3776d97bf8e73ab6f53fb922dfbeda51988c565e44f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36374e5df715cc09dacec3776d97bf8e73ab6f53fb922dfbeda51988c565e44f","first_computed_at":"2026-07-05T10:10:57.314977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:57.314977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qSjHCQFwqDcFMaB//i+FRX5sgc8eLShKyI2G0RHSKfchlFZAn4FhhU2Fov/peyXP7jb8Gl4veOfDrz3j32HiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:57.315523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e46f84166d2063b4b53cbc83aaf46adbe089ef7771f4c7ec47891bfe11830094","sha256:afa6fad251e2eb8b8b3fc14394aed9fff56e0a419e30d5bac1bfb5621d005be4"],"state_sha256":"4b00adc06654458fab5ae7bede588d5fa4831a6d8586f78f06079ba31b38a479"}