{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VBYCNLRDFYEZVNLPWS42LP3WXT","short_pith_number":"pith:VBYCNLRD","schema_version":"1.0","canonical_sha256":"a87026ae232e099ab56fb4b9a5bf76bcd15ae01931d2e571f77f7012686f9219","source":{"kind":"arxiv","id":"2305.00768","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.MA","authors_text":"Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Joel Z. Leibo, John P. Agapiou, Karl Tuyls, Kevin R. McKee, Richard Everett, Thomas Anthony, Udari Madhushani","submitted_at":"2023-05-01T11:09:23Z","abstract_excerpt":"In social psychology, Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others. In reinforcement learning, SVO has been instantiated as an intrinsic motivation that remaps an agent's rewards based on particular target distributions of group reward. Prior studies show that groups of agents endowed with heterogeneous SVO learn diverse policies in settings that resemble the incentive structure of Prisoner's dilemma. Our work extends this body of results and demonstrates that (1) heterogeneous SVO leads to meaningfully diverse policies a"},"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":"2305.00768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-05-01T11:09:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b2355eb2ea9c07e8d2dbee32b40e26e43dcd652575b037da1908d027f5f2db4b","abstract_canon_sha256":"a173ab9b807b64d226407c4bf3d179db01882d627ef1b3a8c66cee93d3bab7eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:44.999682Z","signature_b64":"N19sZ+jDiPH6V+B3iRAbqVKwqEnKydpdjqYE8n6s8XruNhNAOs9fChI1D4HdDxmeBdQSxdmEyl0kI1Kg3rfeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a87026ae232e099ab56fb4b9a5bf76bcd15ae01931d2e571f77f7012686f9219","last_reissued_at":"2026-07-05T06:05:44.999274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:44.999274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.MA","authors_text":"Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Joel Z. Leibo, John P. Agapiou, Karl Tuyls, Kevin R. McKee, Richard Everett, Thomas Anthony, Udari Madhushani","submitted_at":"2023-05-01T11:09:23Z","abstract_excerpt":"In social psychology, Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others. In reinforcement learning, SVO has been instantiated as an intrinsic motivation that remaps an agent's rewards based on particular target distributions of group reward. Prior studies show that groups of agents endowed with heterogeneous SVO learn diverse policies in settings that resemble the incentive structure of Prisoner's dilemma. Our work extends this body of results and demonstrates that (1) heterogeneous SVO leads to meaningfully diverse policies a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00768","kind":"arxiv","version":1},"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/2305.00768/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":"2305.00768","created_at":"2026-07-05T06:05:44.999340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00768v1","created_at":"2026-07-05T06:05:44.999340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00768","created_at":"2026-07-05T06:05:44.999340+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBYCNLRDFYEZ","created_at":"2026-07-05T06:05:44.999340+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBYCNLRDFYEZVNLP","created_at":"2026-07-05T06:05:44.999340+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBYCNLRD","created_at":"2026-07-05T06:05:44.999340+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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT","json":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT.json","graph_json":"https://pith.science/api/pith-number/VBYCNLRDFYEZVNLPWS42LP3WXT/graph.json","events_json":"https://pith.science/api/pith-number/VBYCNLRDFYEZVNLPWS42LP3WXT/events.json","paper":"https://pith.science/paper/VBYCNLRD"},"agent_actions":{"view_html":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT","download_json":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT.json","view_paper":"https://pith.science/paper/VBYCNLRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00768&json=true","fetch_graph":"https://pith.science/api/pith-number/VBYCNLRDFYEZVNLPWS42LP3WXT/graph.json","fetch_events":"https://pith.science/api/pith-number/VBYCNLRDFYEZVNLPWS42LP3WXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT/action/storage_attestation","attest_author":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT/action/author_attestation","sign_citation":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT/action/citation_signature","submit_replication":"https://pith.science/pith/VBYCNLRDFYEZVNLPWS42LP3WXT/action/replication_record"}},"created_at":"2026-07-05T06:05:44.999340+00:00","updated_at":"2026-07-05T06:05:44.999340+00:00"}