{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A2EFK6YB7S4MZTQ6NVXWFC6YMV","short_pith_number":"pith:A2EFK6YB","canonical_record":{"source":{"id":"2210.03852","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-07T23:55:51Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"34ef7763816701739cd680e8e230b9acd6c88b9eb780483e86e69d9d0ae0a0f7","abstract_canon_sha256":"a5f08ceafc179fb84f6b42c6d7d6796d924426e5c7afc9964793878c0c0465cb"},"schema_version":"1.0"},"canonical_sha256":"0688557b01fcb8ccce1e6d6f628bd86570b3b90f8123200ef4fa0b4b0fdcc543","source":{"kind":"arxiv","id":"2210.03852","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03852","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03852v4","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03852","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"A2EFK6YB7S4M","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"A2EFK6YB7S4MZTQ6","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"A2EFK6YB","created_at":"2026-07-05T08:45:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A2EFK6YB7S4MZTQ6NVXWFC6YMV","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03852","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-07T23:55:51Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"34ef7763816701739cd680e8e230b9acd6c88b9eb780483e86e69d9d0ae0a0f7","abstract_canon_sha256":"a5f08ceafc179fb84f6b42c6d7d6796d924426e5c7afc9964793878c0c0465cb"},"schema_version":"1.0"},"canonical_sha256":"0688557b01fcb8ccce1e6d6f628bd86570b3b90f8123200ef4fa0b4b0fdcc543","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:45.215782Z","signature_b64":"UZoHn2Iw97NUjiyJRJdHafsiALmAEKveRDqcJNmNfdvnqNTTKAQ1QEF+aBXVxVx1WXk10NEfMp16+mm7E9oZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0688557b01fcb8ccce1e6d6f628bd86570b3b90f8123200ef4fa0b4b0fdcc543","last_reissued_at":"2026-07-05T08:45:45.215301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:45.215301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03852","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BWUxRH8xDycODjFtWT6bn3cf5GSCMHH0JotwPTnVVwOj/Q5V8tGXUbiQSpmXfxbViQ5YGM4aO9/exYB0T74lBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:19:58.450130Z"},"content_sha256":"0a0c8208c18a71201d8a23dabd0750dbd5125c5514a6e612087899aee71b3699","schema_version":"1.0","event_id":"sha256:0a0c8208c18a71201d8a23dabd0750dbd5125c5514a6e612087899aee71b3699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A2EFK6YB7S4MZTQ6NVXWFC6YMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stackelberg POMDP: A Reinforcement Learning Approach for Economic Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.GT","authors_text":"Alon Eden, Amy Greenwald, Darshan Chakrabarti, David C. Parkes, Gianluca Brero, Matthias Gerstgrasser, Vincent Li","submitted_at":"2022-10-07T23:55:51Z","abstract_excerpt":"We introduce a reinforcement learning framework for economic design where the interaction between the environment designer and the participants is modeled as a Stackelberg game. In this game, the designer (leader) sets up the rules of the economic system, while the participants (followers) respond strategically. We integrate algorithms for determining followers' response strategies into the leader's learning environment, providing a formulation of the leader's learning problem as a POMDP that we call the Stackelberg POMDP. We prove that the optimal leader's strategy in the Stackelberg game is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03852","kind":"arxiv","version":4},"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/2210.03852/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7SHY5e9Juw8ErAwQosYp70j16+kX5JTn5ecJhgQDPcqhUbEHR9ujqzq8Fd5p08jRRSPtyMCes8NZo+8kvxKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:19:58.450692Z"},"content_sha256":"254d5175ebe5e09eae733dfc7b1198e748bba5a6dd20266bc1d52679e6d882ae","schema_version":"1.0","event_id":"sha256:254d5175ebe5e09eae733dfc7b1198e748bba5a6dd20266bc1d52679e6d882ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV/bundle.json","state_url":"https://pith.science/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T08:19:58Z","links":{"resolver":"https://pith.science/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV","bundle":"https://pith.science/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV/bundle.json","state":"https://pith.science/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2EFK6YB7S4MZTQ6NVXWFC6YMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A2EFK6YB7S4MZTQ6NVXWFC6YMV","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":"a5f08ceafc179fb84f6b42c6d7d6796d924426e5c7afc9964793878c0c0465cb","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-07T23:55:51Z","title_canon_sha256":"34ef7763816701739cd680e8e230b9acd6c88b9eb780483e86e69d9d0ae0a0f7"},"schema_version":"1.0","source":{"id":"2210.03852","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03852","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03852v4","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03852","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"A2EFK6YB7S4M","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"A2EFK6YB7S4MZTQ6","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"A2EFK6YB","created_at":"2026-07-05T08:45:45Z"}],"graph_snapshots":[{"event_id":"sha256:254d5175ebe5e09eae733dfc7b1198e748bba5a6dd20266bc1d52679e6d882ae","target":"graph","created_at":"2026-07-05T08:45:45Z","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/2210.03852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a reinforcement learning framework for economic design where the interaction between the environment designer and the participants is modeled as a Stackelberg game. In this game, the designer (leader) sets up the rules of the economic system, while the participants (followers) respond strategically. We integrate algorithms for determining followers' response strategies into the leader's learning environment, providing a formulation of the leader's learning problem as a POMDP that we call the Stackelberg POMDP. We prove that the optimal leader's strategy in the Stackelberg game is ","authors_text":"Alon Eden, Amy Greenwald, Darshan Chakrabarti, David C. Parkes, Gianluca Brero, Matthias Gerstgrasser, Vincent Li","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-07T23:55:51Z","title":"Stackelberg POMDP: A Reinforcement Learning Approach for Economic Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03852","kind":"arxiv","version":4},"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":"sha256:0a0c8208c18a71201d8a23dabd0750dbd5125c5514a6e612087899aee71b3699","target":"record","created_at":"2026-07-05T08:45:45Z","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":"a5f08ceafc179fb84f6b42c6d7d6796d924426e5c7afc9964793878c0c0465cb","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-10-07T23:55:51Z","title_canon_sha256":"34ef7763816701739cd680e8e230b9acd6c88b9eb780483e86e69d9d0ae0a0f7"},"schema_version":"1.0","source":{"id":"2210.03852","kind":"arxiv","version":4}},"canonical_sha256":"0688557b01fcb8ccce1e6d6f628bd86570b3b90f8123200ef4fa0b4b0fdcc543","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0688557b01fcb8ccce1e6d6f628bd86570b3b90f8123200ef4fa0b4b0fdcc543","first_computed_at":"2026-07-05T08:45:45.215301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:45.215301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZoHn2Iw97NUjiyJRJdHafsiALmAEKveRDqcJNmNfdvnqNTTKAQ1QEF+aBXVxVx1WXk10NEfMp16+mm7E9oZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:45.215782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03852","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a0c8208c18a71201d8a23dabd0750dbd5125c5514a6e612087899aee71b3699","sha256:254d5175ebe5e09eae733dfc7b1198e748bba5a6dd20266bc1d52679e6d882ae"],"state_sha256":"b35ec7bf4a7cc1f1af99c68ad7e0cda882d67d2ca709e43da530b0fe60c56a0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wvl3KwoRlwCRyWHFs9zARN4a+dC/DrxWIp6epETn4/QWKEoNIjNpx40UOQGlQme3UjYxIJBEJC+3Ad+WjXhTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T08:19:58.453812Z","bundle_sha256":"198b40eeff1c58ab7032135c127cecab95643c965f25d38813c73014e7c01db9"}}