{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DRMJOBSMOPPR7JL7XMIR6O3UOR","short_pith_number":"pith:DRMJOBSM","schema_version":"1.0","canonical_sha256":"1c5897064c73df1fa57fbb111f3b747477431ef445f0f6da6241a2a98e93f574","source":{"kind":"arxiv","id":"2002.02325","version":2},"attestation_state":"computed","paper":{"title":"Social diversity and social preferences in mixed-motive reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Brian McWilliams, Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Ian Gemp, Joel Z. Leibo, Kevin R. McKee","submitted_at":"2020-02-06T16:07:02Z","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"},"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":"2002.02325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T16:07:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3d372a9863e9a73b79a43137a42088ddd86e8f39b0138ad10c3fd05183ab2a6","abstract_canon_sha256":"e6027b101a70d8c5e8325d74165d18a87e71c861bdbb1c0062d772a91ed08408"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:28.025229Z","signature_b64":"X92n/i6N6JHo31IoJwIcAeuLmHgsWJwrzOPn0Y1FkYlek8QELRGaYo6NlHv1hIxPfj/BiFcaBfeMk1uORPWBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c5897064c73df1fa57fbb111f3b747477431ef445f0f6da6241a2a98e93f574","last_reissued_at":"2026-07-05T00:40:28.024743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:28.024743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Social diversity and social preferences in mixed-motive reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Brian McWilliams, Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Ian Gemp, Joel Z. Leibo, Kevin R. McKee","submitted_at":"2020-02-06T16:07:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02325","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/2002.02325/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":"2002.02325","created_at":"2026-07-05T00:40:28.024807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02325v2","created_at":"2026-07-05T00:40:28.024807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02325","created_at":"2026-07-05T00:40:28.024807+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRMJOBSMOPPR","created_at":"2026-07-05T00:40:28.024807+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRMJOBSMOPPR7JL7","created_at":"2026-07-05T00:40:28.024807+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRMJOBSM","created_at":"2026-07-05T00:40:28.024807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03818","citing_title":"Investigating the Impact of Subgraph Social Structure Preference on the Strategic Behavior of Networked Mixed-Motive Learning Agents","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR","json":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR.json","graph_json":"https://pith.science/api/pith-number/DRMJOBSMOPPR7JL7XMIR6O3UOR/graph.json","events_json":"https://pith.science/api/pith-number/DRMJOBSMOPPR7JL7XMIR6O3UOR/events.json","paper":"https://pith.science/paper/DRMJOBSM"},"agent_actions":{"view_html":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR","download_json":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR.json","view_paper":"https://pith.science/paper/DRMJOBSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02325&json=true","fetch_graph":"https://pith.science/api/pith-number/DRMJOBSMOPPR7JL7XMIR6O3UOR/graph.json","fetch_events":"https://pith.science/api/pith-number/DRMJOBSMOPPR7JL7XMIR6O3UOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR/action/storage_attestation","attest_author":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR/action/author_attestation","sign_citation":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR/action/citation_signature","submit_replication":"https://pith.science/pith/DRMJOBSMOPPR7JL7XMIR6O3UOR/action/replication_record"}},"created_at":"2026-07-05T00:40:28.024807+00:00","updated_at":"2026-07-05T00:40:28.024807+00:00"}