{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HP4ZWL7JKZJITTIZVTSEO2WSCS","short_pith_number":"pith:HP4ZWL7J","canonical_record":{"source":{"id":"2009.13051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T04:02:08Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"de4790285ebe62fae7593843f781eb66e7c2008ee39beb832324f4f107c349fb","abstract_canon_sha256":"d100861f2b0ff6af48f6f9545d43c0f092c0d16414fc7a93fdda404e7a00a4ee"},"schema_version":"1.0"},"canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","source":{"kind":"arxiv","id":"2009.13051","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13051","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13051v3","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13051","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"HP4ZWL7JKZJI","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"HP4ZWL7JKZJITTIZ","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"HP4ZWL7J","created_at":"2026-07-05T04:27:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HP4ZWL7JKZJITTIZVTSEO2WSCS","target":"record","payload":{"canonical_record":{"source":{"id":"2009.13051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T04:02:08Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"de4790285ebe62fae7593843f781eb66e7c2008ee39beb832324f4f107c349fb","abstract_canon_sha256":"d100861f2b0ff6af48f6f9545d43c0f092c0d16414fc7a93fdda404e7a00a4ee"},"schema_version":"1.0"},"canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:41.429654Z","signature_b64":"G4K14Afw54ED9zdf2B3CBHwT8npMgWelQBy3kN22bGHQm15kiMqB4twNFq7obOb9cl2+gmrw2wdJVdIbz1XpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","last_reissued_at":"2026-07-05T04:27:41.429272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:41.429272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.13051","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:27:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pn55LosYcg8U50PE55fnOt7LAbdZoJwxFGQX6xo74qqG3Lr5la64m5jLtja5zwJczkwKwrWhaRwW1JWX8MdWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:02:22.369600Z"},"content_sha256":"a6d30ba2d986a0d8bcd0479d6a1c74299908dfbb9307659f600789cb0924f3a3","schema_version":"1.0","event_id":"sha256:a6d30ba2d986a0d8bcd0479d6a1c74299908dfbb9307659f600789cb0924f3a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HP4ZWL7JKZJITTIZVTSEO2WSCS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agent Environment Cycle Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananth Hari, Benjamin Black, Caroline Horsch, J K Terry, Luis Santos, Nathaniel Grammel","submitted_at":"2020-09-28T04:02:08Z","abstract_excerpt":"Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL). We argue that the POSG model is conceptually ill suited to software MARL environments, and offer case studies from the literature where this mismatch has led to severely unexpected behavior. In response to this, we introduce the Agent Environment Cycle Games (AEC Games) model, which is more representative of software implementation. We then prove it's as an equivalent model to POSGs. The AEC games model is also uniquely useful in that it can elegantly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13051","kind":"arxiv","version":3},"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/2009.13051/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":"2026-07-05T04:27:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cARYPFVheOiFD/gA5UlXTV1M5tf9tJKlnhpVT4vN+THTJUC1Gp1Xt50Fsq4LCaaAxqpYPmnfcE3nmwjl8G9KAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:02:22.369978Z"},"content_sha256":"e4dd06f3e1fe30447b45fe4c219b6976ba4aa2309f7077e1da853b92f3cd3379","schema_version":"1.0","event_id":"sha256:e4dd06f3e1fe30447b45fe4c219b6976ba4aa2309f7077e1da853b92f3cd3379"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/bundle.json","state_url":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/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":"2026-07-06T10:02:22Z","links":{"resolver":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS","bundle":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/bundle.json","state":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HP4ZWL7JKZJITTIZVTSEO2WSCS","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":"d100861f2b0ff6af48f6f9545d43c0f092c0d16414fc7a93fdda404e7a00a4ee","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T04:02:08Z","title_canon_sha256":"de4790285ebe62fae7593843f781eb66e7c2008ee39beb832324f4f107c349fb"},"schema_version":"1.0","source":{"id":"2009.13051","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13051","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13051v3","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13051","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"HP4ZWL7JKZJI","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"HP4ZWL7JKZJITTIZ","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"HP4ZWL7J","created_at":"2026-07-05T04:27:41Z"}],"graph_snapshots":[{"event_id":"sha256:e4dd06f3e1fe30447b45fe4c219b6976ba4aa2309f7077e1da853b92f3cd3379","target":"graph","created_at":"2026-07-05T04:27:41Z","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/2009.13051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL). We argue that the POSG model is conceptually ill suited to software MARL environments, and offer case studies from the literature where this mismatch has led to severely unexpected behavior. In response to this, we introduce the Agent Environment Cycle Games (AEC Games) model, which is more representative of software implementation. We then prove it's as an equivalent model to POSGs. The AEC games model is also uniquely useful in that it can elegantly ","authors_text":"Ananth Hari, Benjamin Black, Caroline Horsch, J K Terry, Luis Santos, Nathaniel Grammel","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T04:02:08Z","title":"Agent Environment Cycle Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13051","kind":"arxiv","version":3},"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:a6d30ba2d986a0d8bcd0479d6a1c74299908dfbb9307659f600789cb0924f3a3","target":"record","created_at":"2026-07-05T04:27:41Z","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":"d100861f2b0ff6af48f6f9545d43c0f092c0d16414fc7a93fdda404e7a00a4ee","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T04:02:08Z","title_canon_sha256":"de4790285ebe62fae7593843f781eb66e7c2008ee39beb832324f4f107c349fb"},"schema_version":"1.0","source":{"id":"2009.13051","kind":"arxiv","version":3}},"canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","first_computed_at":"2026-07-05T04:27:41.429272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:41.429272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G4K14Afw54ED9zdf2B3CBHwT8npMgWelQBy3kN22bGHQm15kiMqB4twNFq7obOb9cl2+gmrw2wdJVdIbz1XpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:41.429654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.13051","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6d30ba2d986a0d8bcd0479d6a1c74299908dfbb9307659f600789cb0924f3a3","sha256:e4dd06f3e1fe30447b45fe4c219b6976ba4aa2309f7077e1da853b92f3cd3379"],"state_sha256":"b2c3530d9bacfdcbcedf9c7b68cdba067cb4e5c352ef2b2ba3507f384462a9b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WdE2CxgPEMCALsg17FbCYlHiJvfR/t9BxF8iqfaufShxx7L94npQiK3Cb+qgh5rvNXnzEiPm1PkMcgCND8oDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:02:22.371947Z","bundle_sha256":"98ea9dbeb00539707847c2aa6d63f173c9d83b8225e80c0184787768ea0d4315"}}