{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZTODZLGHLIMPAR55D5K3F6SMOV","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":"bbe4d6935c73d304a36fe1ff6b1c6f0995ad96aec09009aefe4b8501a48062c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:17:22Z","title_canon_sha256":"bbe73485037b1ed405ed5677938e19136eb0562f799fa417b48d69d88ec63a6f"},"schema_version":"1.0","source":{"id":"2606.28671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28671","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28671v1","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28671","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZTODZLGHLIMP","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"ZTODZLGHLIMPAR55","created_at":"2026-06-30T01:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"ZTODZLGH","created_at":"2026-06-30T01:16:46Z"}],"graph_snapshots":[{"event_id":"sha256:955dd4763032caaba9e6bacbf2e3ddaf05ea463c87b875ba9bdb48fd872bede2","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/2606.28671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stackelberg differential games (SDGs) provide a powerful framework for hierarchical decision-making in stochastic and continuous-time environments, yet their solution remains computationally challenging due to the complexity of traditional dynamic programming and Hamilton-Jacobi-Bellman-Isaacs (HJBI) methods, especially in high-dimensional systems. This paper proposes an entropy-regularized reinforcement learning (ERRL) approach for linear-quadratic SDGs (LQ-SDGs) within a continuous-time diffusion framework governed by Markovian regime switching. The key innovation lies in deriving explorator","authors_text":"Congde Hu, Danping Li, Lin Xu, Wenying Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:17:22Z","title":"Entropy-Regularized Reinforcement Learning for Linear-Quadratic Stackelberg Differential Games in Regime-Switching Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28671","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:f2b6e6329aefc665d58e1601011a70968974d0e976e8dda1c1549ddb123abba9","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":"bbe4d6935c73d304a36fe1ff6b1c6f0995ad96aec09009aefe4b8501a48062c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:17:22Z","title_canon_sha256":"bbe73485037b1ed405ed5677938e19136eb0562f799fa417b48d69d88ec63a6f"},"schema_version":"1.0","source":{"id":"2606.28671","kind":"arxiv","version":1}},"canonical_sha256":"ccdc3cacc75a18f047bd1f55b2fa4c755861c02a06cbc84b032eb361949bda59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccdc3cacc75a18f047bd1f55b2fa4c755861c02a06cbc84b032eb361949bda59","first_computed_at":"2026-06-30T01:16:46.893561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:16:46.893561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z4t2nVL2dBiOY5zwnY23ScV64dXGqBt59laBssKOt8bhlBMMuyyOfPxjJa2+sC5NSakEa/5jHNI0sWCbk0rxBA==","signature_status":"signed_v1","signed_at":"2026-06-30T01:16:46.894543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2b6e6329aefc665d58e1601011a70968974d0e976e8dda1c1549ddb123abba9","sha256:955dd4763032caaba9e6bacbf2e3ddaf05ea463c87b875ba9bdb48fd872bede2"],"state_sha256":"a3f6400d88d6ba9c6e8355722bad67d4b074ab71ad3a77e1d334e49d1fc11af0"}