{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DRMJOBSMOPPR7JL7XMIR6O3UOR","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":"e6027b101a70d8c5e8325d74165d18a87e71c861bdbb1c0062d772a91ed08408","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T16:07:02Z","title_canon_sha256":"e3d372a9863e9a73b79a43137a42088ddd86e8f39b0138ad10c3fd05183ab2a6"},"schema_version":"1.0","source":{"id":"2002.02325","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.02325","created_at":"2026-07-05T00:40:28Z"},{"alias_kind":"arxiv_version","alias_value":"2002.02325v2","created_at":"2026-07-05T00:40:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02325","created_at":"2026-07-05T00:40:28Z"},{"alias_kind":"pith_short_12","alias_value":"DRMJOBSMOPPR","created_at":"2026-07-05T00:40:28Z"},{"alias_kind":"pith_short_16","alias_value":"DRMJOBSMOPPR7JL7","created_at":"2026-07-05T00:40:28Z"},{"alias_kind":"pith_short_8","alias_value":"DRMJOBSM","created_at":"2026-07-05T00:40:28Z"}],"graph_snapshots":[{"event_id":"sha256:faf6f4c04b1d2fb5c37c6a4b36c181ea10a117e285d4d0c5f31dd8881405e5db","target":"graph","created_at":"2026-07-05T00:40:28Z","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/2002.02325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research on reinforcement learning in pure-conflict and pure-common interest games has emphasized the importance of population heterogeneity. In contrast, studies of reinforcement learning in mixed-motive games have primarily leveraged homogeneous approaches. Given the defining characteristic of mixed-motive games--the imperfect correlation of incentives between group members--we study the effect of population heterogeneity on mixed-motive reinforcement learning. We draw on interdependence theory from social psychology and imbue reinforcement learning agents with Social Value Orientatio","authors_text":"Brian McWilliams, Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Ian Gemp, Joel Z. Leibo, Kevin R. McKee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T16:07:02Z","title":"Social diversity and social preferences in mixed-motive reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02325","kind":"arxiv","version":2},"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":"sha256:39e0c2791fd1ee23ed029ef74a8a581702be35e0ef34351f60fd5a6c46ccd3c2","target":"record","created_at":"2026-07-05T00:40:28Z","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":"e6027b101a70d8c5e8325d74165d18a87e71c861bdbb1c0062d772a91ed08408","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T16:07:02Z","title_canon_sha256":"e3d372a9863e9a73b79a43137a42088ddd86e8f39b0138ad10c3fd05183ab2a6"},"schema_version":"1.0","source":{"id":"2002.02325","kind":"arxiv","version":2}},"canonical_sha256":"1c5897064c73df1fa57fbb111f3b747477431ef445f0f6da6241a2a98e93f574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c5897064c73df1fa57fbb111f3b747477431ef445f0f6da6241a2a98e93f574","first_computed_at":"2026-07-05T00:40:28.024743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:28.024743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X92n/i6N6JHo31IoJwIcAeuLmHgsWJwrzOPn0Y1FkYlek8QELRGaYo6NlHv1hIxPfj/BiFcaBfeMk1uORPWBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:28.025229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.02325","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39e0c2791fd1ee23ed029ef74a8a581702be35e0ef34351f60fd5a6c46ccd3c2","sha256:faf6f4c04b1d2fb5c37c6a4b36c181ea10a117e285d4d0c5f31dd8881405e5db"],"state_sha256":"a377fe000cbc973685c34b0b17fac75d9eb8d47e93a51f7ec16472edacde2cd4"}