{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7X5ZBTZ4JDZZ54AQHX23VF5K5I","short_pith_number":"pith:7X5ZBTZ4","canonical_record":{"source":{"id":"2208.10469","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-08-22T17:42:03Z","cross_cats_sorted":["cs.GT","cs.MA","econ.TH"],"title_canon_sha256":"ba6a8d5523287c2fb00028f937e304ac6b5f470d5532a99a7928aeb4619e7f57","abstract_canon_sha256":"9afc3c285f5ccc033ff1cdd9d91b3369fb3d27e94b4c7b25e2272cf47854adec"},"schema_version":"1.0"},"canonical_sha256":"fdfb90cf3c48f39ef0103df5ba97aaea19c6663847c27d3dab61e9020fded2da","source":{"kind":"arxiv","id":"2208.10469","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10469","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10469v4","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10469","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"7X5ZBTZ4JDZZ","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"7X5ZBTZ4JDZZ54AQ","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"7X5ZBTZ4","created_at":"2026-07-05T07:38:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7X5ZBTZ4JDZZ54AQHX23VF5K5I","target":"record","payload":{"canonical_record":{"source":{"id":"2208.10469","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-08-22T17:42:03Z","cross_cats_sorted":["cs.GT","cs.MA","econ.TH"],"title_canon_sha256":"ba6a8d5523287c2fb00028f937e304ac6b5f470d5532a99a7928aeb4619e7f57","abstract_canon_sha256":"9afc3c285f5ccc033ff1cdd9d91b3369fb3d27e94b4c7b25e2272cf47854adec"},"schema_version":"1.0"},"canonical_sha256":"fdfb90cf3c48f39ef0103df5ba97aaea19c6663847c27d3dab61e9020fded2da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:24.698707Z","signature_b64":"FT36+xltJSl9gX7llSqql+9+13fWmiLKj9kKOY1dfAVD7PmxpTrM22/IeQ15j/1GudTQmQ80RZ7iJVbmN7wVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdfb90cf3c48f39ef0103df5ba97aaea19c6663847c27d3dab61e9020fded2da","last_reissued_at":"2026-07-05T07:38:24.698269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:24.698269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.10469","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":"2026-07-05T07:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Y0iULhRxVR/XtZiiKJpAukam7xMH2vwp0C12UPYvAbJDVQgRvCgHyJhCh0e/sNyZwxmWkXkQ8aJmd/F4HLRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:14:01.728285Z"},"content_sha256":"5b8f81403767e5f418b40f1b5129d997b3e83785707cbe5a1954a3426988a8a6","schema_version":"1.0","event_id":"sha256:5b8f81403767e5f418b40f1b5129d997b3e83785707cbe5a1954a3426988a8a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7X5ZBTZ4JDZZ54AQHX23VF5K5I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.MA","econ.TH"],"primary_cat":"cs.AI","authors_text":"Andreas A. Haupt, Dylan Hadfield-Menell, Mehul Damani, Phillip J.K. Christoffersen","submitted_at":"2022-08-22T17:42:03Z","abstract_excerpt":"Multi-agent Reinforcement Learning (MARL) is a powerful tool for training autonomous agents acting independently in a common environment. However, it can lead to sub-optimal behavior when individual incentives and group incentives diverge. Humans are remarkably capable at solving these social dilemmas. It is an open problem in MARL to replicate such cooperative behaviors in selfish agents. In this work, we draw upon the idea of formal contracting from economics to overcome diverging incentives between agents in MARL. We propose an augmentation to a Markov game where agents voluntarily agree to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10469","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/2208.10469/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":"2026-07-05T07:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVwXOaOxdSlAX12KLFL+APfJ5dJgWRXi14isgeGmqfQtyXhrk6Ji6mhW5CiCd8IPHgPcT4TC4KHjgqHR5eIdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:14:01.729318Z"},"content_sha256":"e73bf5c9f4270f075b483715a1e71a401593727de4cc827585b2cc2f048810f5","schema_version":"1.0","event_id":"sha256:e73bf5c9f4270f075b483715a1e71a401593727de4cc827585b2cc2f048810f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I/bundle.json","state_url":"https://pith.science/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I/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":"2026-08-16T23:14:01Z","links":{"resolver":"https://pith.science/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I","bundle":"https://pith.science/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I/bundle.json","state":"https://pith.science/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7X5ZBTZ4JDZZ54AQHX23VF5K5I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7X5ZBTZ4JDZZ54AQHX23VF5K5I","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":"9afc3c285f5ccc033ff1cdd9d91b3369fb3d27e94b4c7b25e2272cf47854adec","cross_cats_sorted":["cs.GT","cs.MA","econ.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-08-22T17:42:03Z","title_canon_sha256":"ba6a8d5523287c2fb00028f937e304ac6b5f470d5532a99a7928aeb4619e7f57"},"schema_version":"1.0","source":{"id":"2208.10469","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10469","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10469v4","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10469","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"7X5ZBTZ4JDZZ","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"7X5ZBTZ4JDZZ54AQ","created_at":"2026-07-05T07:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"7X5ZBTZ4","created_at":"2026-07-05T07:38:24Z"}],"graph_snapshots":[{"event_id":"sha256:e73bf5c9f4270f075b483715a1e71a401593727de4cc827585b2cc2f048810f5","target":"graph","created_at":"2026-07-05T07:38:24Z","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/2208.10469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent Reinforcement Learning (MARL) is a powerful tool for training autonomous agents acting independently in a common environment. However, it can lead to sub-optimal behavior when individual incentives and group incentives diverge. Humans are remarkably capable at solving these social dilemmas. It is an open problem in MARL to replicate such cooperative behaviors in selfish agents. In this work, we draw upon the idea of formal contracting from economics to overcome diverging incentives between agents in MARL. We propose an augmentation to a Markov game where agents voluntarily agree to","authors_text":"Andreas A. Haupt, Dylan Hadfield-Menell, Mehul Damani, Phillip J.K. Christoffersen","cross_cats":["cs.GT","cs.MA","econ.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-08-22T17:42:03Z","title":"Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10469","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":"sha256:5b8f81403767e5f418b40f1b5129d997b3e83785707cbe5a1954a3426988a8a6","target":"record","created_at":"2026-07-05T07:38:24Z","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":"9afc3c285f5ccc033ff1cdd9d91b3369fb3d27e94b4c7b25e2272cf47854adec","cross_cats_sorted":["cs.GT","cs.MA","econ.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-08-22T17:42:03Z","title_canon_sha256":"ba6a8d5523287c2fb00028f937e304ac6b5f470d5532a99a7928aeb4619e7f57"},"schema_version":"1.0","source":{"id":"2208.10469","kind":"arxiv","version":4}},"canonical_sha256":"fdfb90cf3c48f39ef0103df5ba97aaea19c6663847c27d3dab61e9020fded2da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdfb90cf3c48f39ef0103df5ba97aaea19c6663847c27d3dab61e9020fded2da","first_computed_at":"2026-07-05T07:38:24.698269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:24.698269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FT36+xltJSl9gX7llSqql+9+13fWmiLKj9kKOY1dfAVD7PmxpTrM22/IeQ15j/1GudTQmQ80RZ7iJVbmN7wVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:24.698707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10469","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b8f81403767e5f418b40f1b5129d997b3e83785707cbe5a1954a3426988a8a6","sha256:e73bf5c9f4270f075b483715a1e71a401593727de4cc827585b2cc2f048810f5"],"state_sha256":"2a3f91cf102117629cb9e864f4280269590433addf20a212a175387db7bf994f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNYUr8jxfDS2hyo6xW/fT6Mu1uSjsGP0keuSZYMBl8QvnwvvIFBp5EsbaggoBuF2ZfmLKuEMEPvcoP/T8TmIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:14:01.739535Z","bundle_sha256":"a16de4fb75582538e9267bb8171d8fa4db4d920b7b25aeb5e3c46fdda5c05d37"}}