{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XU2APM24WIX6XLIHWLD6A2TWY7","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":"a4849092314fe67a4b8ddf446e6c792d32fd3f65227f539343f1283dd1ddbdb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:03:53Z","title_canon_sha256":"ed206a99f1c3b8773c166031bbbd89b35684e8a59c39c3cb3c3576aeec4ed808"},"schema_version":"1.0","source":{"id":"2606.28669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28669","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28669v1","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28669","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"XU2APM24WIX6","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"XU2APM24WIX6XLIH","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"XU2APM24","created_at":"2026-06-30T01:16:46Z"}],"graph_snapshots":[{"event_id":"sha256:101ae35f2a310e37102ba937f08c6ac179f6696d9367f9a2170eb21f29ad6a8a","target":"graph","created_at":"2026-06-30T01:16:46Z","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/2606.28669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To address parameter misspecification and sudden structural environmental changes in conventional stochastic differential game (SDG) frameworks, this paper introduces a distributional control approach that characterizes optimal strategies as probability distributions over actions, conditioned on the continuous state, the discrete regime state, and parameters. This forms a reinforcement learning framework for entropy-regularized zero-sum stochastic differential games (ERRL-ZSSDGs) in a regime-switching jump-diffusion process. Using the dynamic programming principle (DPP), we derive the associat","authors_text":"Congde Hu, Danping Li, Lin Xu, Zhuo Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:03:53Z","title":"Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28669","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":"sha256:577f7c0c382a9e48ceb2f1c0e7c06d44bb53111a2bdf2dcd1b0711bdc835fbe1","target":"record","created_at":"2026-06-30T01:16:46Z","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":"a4849092314fe67a4b8ddf446e6c792d32fd3f65227f539343f1283dd1ddbdb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:03:53Z","title_canon_sha256":"ed206a99f1c3b8773c166031bbbd89b35684e8a59c39c3cb3c3576aeec4ed808"},"schema_version":"1.0","source":{"id":"2606.28669","kind":"arxiv","version":1}},"canonical_sha256":"bd3407b35cb22febad07b2c7e06a76c7cb8c5238b4cf8f93df5cb30d15880a00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd3407b35cb22febad07b2c7e06a76c7cb8c5238b4cf8f93df5cb30d15880a00","first_computed_at":"2026-06-30T01:16:46.785909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:16:46.785909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WO97PFociQnOJQvHneXEYnpy6RhSDN8LfvUnl3clrAnpaug3yWmzAkLQfmR3l2dob1wWTKJgjVds/aLSNmtfAQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:16:46.786824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:577f7c0c382a9e48ceb2f1c0e7c06d44bb53111a2bdf2dcd1b0711bdc835fbe1","sha256:101ae35f2a310e37102ba937f08c6ac179f6696d9367f9a2170eb21f29ad6a8a"],"state_sha256":"148ff329a7c25ebecc2994c43079020801fc5be3821bd8919c9985f335549a43"}