{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EAUP5AH3ZTCTH3YXDG5VK57NFU","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":"4f63dc9b83121444bbcdb527abb288045dacd1bea54dd972970fcf772f9bdab6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-22T09:00:00Z","title_canon_sha256":"96f60c48d1d9f949534b34eeb9b3ab6169e8467a5c06deb73b8d9b3236fa619b"},"schema_version":"1.0","source":{"id":"2607.19928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19928","created_at":"2026-07-23T01:24:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19928v1","created_at":"2026-07-23T01:24:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19928","created_at":"2026-07-23T01:24:44Z"},{"alias_kind":"pith_short_12","alias_value":"EAUP5AH3ZTCT","created_at":"2026-07-23T01:24:44Z"},{"alias_kind":"pith_short_16","alias_value":"EAUP5AH3ZTCTH3YX","created_at":"2026-07-23T01:24:44Z"},{"alias_kind":"pith_short_8","alias_value":"EAUP5AH3","created_at":"2026-07-23T01:24:44Z"}],"graph_snapshots":[{"event_id":"sha256:3de91b8f779d873b0c78ec2a662cf2ca5a906c6678a18a6a76b06aa24b14aac0","target":"graph","created_at":"2026-07-23T01:24:44Z","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/2607.19928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study continuous-time reinforcement learning for $N$-player noncooperative stochastic differential games. Each player adopts an entropy-regularized exploratory policy; given the others' actions, the optimal response is a Gibbs distribution, and a Nash equilibrium requires these $N$ conditional distributions to be jointly compatible. We prove that the natural equilibrium concept -- simultaneous Hamiltonian maximization -- is equivalent to this compatibility, and establish a necessary and sufficient condition expressed as a computable cross-partial criterion on the optimal $q$-functions. Nash","authors_text":"Jing Zhang, Jisheng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-22T09:00:00Z","title":"Continuous-Time Reinforcement Learning for $N$-Player Stochastic Differential Games with Exploratory Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19928","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":"sha256:554582c80dca297f26aa888623c6508842070e9e03bbfaed3e72450e970bbd7e","target":"record","created_at":"2026-07-23T01:24:44Z","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":"4f63dc9b83121444bbcdb527abb288045dacd1bea54dd972970fcf772f9bdab6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-22T09:00:00Z","title_canon_sha256":"96f60c48d1d9f949534b34eeb9b3ab6169e8467a5c06deb73b8d9b3236fa619b"},"schema_version":"1.0","source":{"id":"2607.19928","kind":"arxiv","version":1}},"canonical_sha256":"2028fe80fbccc533ef1719bb5577ed2d093260fe407e2e038d169fca4c05c2f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2028fe80fbccc533ef1719bb5577ed2d093260fe407e2e038d169fca4c05c2f8","first_computed_at":"2026-07-23T01:24:44.302728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:44.302728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZjhUekRhwc4zbMIQIlUL9idAzq8oDFJKY0AcpsDC5QvTOoWBUmJfG1buGmQpNQJh1s3twEF9uSefO+8oo3oICg==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:44.305760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:554582c80dca297f26aa888623c6508842070e9e03bbfaed3e72450e970bbd7e","sha256:3de91b8f779d873b0c78ec2a662cf2ca5a906c6678a18a6a76b06aa24b14aac0"],"state_sha256":"9d51e8d9b0987daba63be34f96c8d9866e37c0d2411c86e0678a059b9b04af49"}