{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:52X6ZBSJDURIPOE5RGCVZ4J5VL","short_pith_number":"pith:52X6ZBSJ","schema_version":"1.0","canonical_sha256":"eeafec86491d2287b89d89855cf13daaf167a49717bcba635872dcc6d3c4f366","source":{"kind":"arxiv","id":"2509.16296","version":2},"attestation_state":"computed","paper":{"title":"Learning in Stackelberg Markov Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GT","cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrew L. Liu, Jun He, Yihsu Chen","submitted_at":"2025-09-19T16:12:53Z","abstract_excerpt":"Designing socially optimal policies in multi-agent environments is a fundamental challenge in both economics and artificial intelligence. This paper studies a general framework for learning Stackelberg equilibria in dynamic and uncertain environments, where a single leader interacts with a population of adaptive followers. Motivated by pressing real-world challenges such as equitable electricity tariff design for consumers with distributed energy resources (such as rooftop solar and energy storage), we formalize a class of Stackelberg Markov games and establish the existence and uniqueness of "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.16296","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.SY","submitted_at":"2025-09-19T16:12:53Z","cross_cats_sorted":["cs.GT","cs.SY"],"title_canon_sha256":"6ea8a8869f8924b1ca9f2147e2d81c9c5d9a20232f3aabe3100f933fb7d69806","abstract_canon_sha256":"e74379ae9b55076f95def287db22dbc1e169be2494ce097c6636703b3d540d7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:08.834238Z","signature_b64":"U2tiJ2aUVbVPrz02ovtX3RclQJNQf/IBkKPac2cOzCUDV+pv5N3vEwazMMYc8XkzxpwAgAKVVqgwD161FJc7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeafec86491d2287b89d89855cf13daaf167a49717bcba635872dcc6d3c4f366","last_reissued_at":"2026-06-02T02:04:08.833660Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:08.833660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in Stackelberg Markov Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GT","cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrew L. Liu, Jun He, Yihsu Chen","submitted_at":"2025-09-19T16:12:53Z","abstract_excerpt":"Designing socially optimal policies in multi-agent environments is a fundamental challenge in both economics and artificial intelligence. This paper studies a general framework for learning Stackelberg equilibria in dynamic and uncertain environments, where a single leader interacts with a population of adaptive followers. Motivated by pressing real-world challenges such as equitable electricity tariff design for consumers with distributed energy resources (such as rooftop solar and energy storage), we formalize a class of Stackelberg Markov games and establish the existence and uniqueness of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.16296","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.16296/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.16296","created_at":"2026-06-02T02:04:08.833755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.16296v2","created_at":"2026-06-02T02:04:08.833755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.16296","created_at":"2026-06-02T02:04:08.833755+00:00"},{"alias_kind":"pith_short_12","alias_value":"52X6ZBSJDURI","created_at":"2026-06-02T02:04:08.833755+00:00"},{"alias_kind":"pith_short_16","alias_value":"52X6ZBSJDURIPOE5","created_at":"2026-06-02T02:04:08.833755+00:00"},{"alias_kind":"pith_short_8","alias_value":"52X6ZBSJ","created_at":"2026-06-02T02:04:08.833755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.04394","citing_title":"Finite-Time Analysis of Q-Value Iteration for General-Sum Stackelberg Games","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL","json":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL.json","graph_json":"https://pith.science/api/pith-number/52X6ZBSJDURIPOE5RGCVZ4J5VL/graph.json","events_json":"https://pith.science/api/pith-number/52X6ZBSJDURIPOE5RGCVZ4J5VL/events.json","paper":"https://pith.science/paper/52X6ZBSJ"},"agent_actions":{"view_html":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL","download_json":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL.json","view_paper":"https://pith.science/paper/52X6ZBSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.16296&json=true","fetch_graph":"https://pith.science/api/pith-number/52X6ZBSJDURIPOE5RGCVZ4J5VL/graph.json","fetch_events":"https://pith.science/api/pith-number/52X6ZBSJDURIPOE5RGCVZ4J5VL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL/action/storage_attestation","attest_author":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL/action/author_attestation","sign_citation":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL/action/citation_signature","submit_replication":"https://pith.science/pith/52X6ZBSJDURIPOE5RGCVZ4J5VL/action/replication_record"}},"created_at":"2026-06-02T02:04:08.833755+00:00","updated_at":"2026-06-02T02:04:08.833755+00:00"}