{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ERACTWVARQP7IOVB6RYS77V72T","short_pith_number":"pith:ERACTWVA","schema_version":"1.0","canonical_sha256":"244029daa08c1ff43aa1f4712ffebfd4e25a8718ed2de28d3165253da4d92ed8","source":{"kind":"arxiv","id":"1707.01068","version":4},"attestation_state":"computed","paper":{"title":"Maintaining cooperation in complex social dilemmas using deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Alexander Peysakhovich","submitted_at":"2017-07-04T17:02:05Z","abstract_excerpt":"Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare. Building artificially intelligent agents that achieve good outcomes in these situations is important because many real world interactions include a tension between selfish interests and the welfare of others. We show how to modify modern reinforcement learning methods to construct agents that act in ways that are simple to understand, nice (begin by cooperating), provokable (try to avoid being exploited), and forgiving (try to return to mutual cooperation). We show both theo"},"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":"1707.01068","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-04T17:02:05Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"e923c772f74bd93cbf27ba1fb8167a6beef6e85b9fddafa402e783abbce866cc","abstract_canon_sha256":"4bc73ee51a24f80af8037c561faeec4850c9a12b9c2c6e02ba915e118832d58a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:10.887540Z","signature_b64":"Xz2l12Q7F3UXi9e+9XmubUaC+rR9eE5rc7hAv6V1aCD61dKh7tObhUrktfZFeynQJOXV67gj3GFe3AzYKeMEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244029daa08c1ff43aa1f4712ffebfd4e25a8718ed2de28d3165253da4d92ed8","last_reissued_at":"2026-05-18T00:22:10.886930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:10.886930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maintaining cooperation in complex social dilemmas using deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Alexander Peysakhovich","submitted_at":"2017-07-04T17:02:05Z","abstract_excerpt":"Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare. Building artificially intelligent agents that achieve good outcomes in these situations is important because many real world interactions include a tension between selfish interests and the welfare of others. We show how to modify modern reinforcement learning methods to construct agents that act in ways that are simple to understand, nice (begin by cooperating), provokable (try to avoid being exploited), and forgiving (try to return to mutual cooperation). We show both theo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01068","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":""},"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":"1707.01068","created_at":"2026-05-18T00:22:10.887017+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.01068v4","created_at":"2026-05-18T00:22:10.887017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01068","created_at":"2026-05-18T00:22:10.887017+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERACTWVARQP7","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERACTWVARQP7IOVB","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERACTWVA","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T","json":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T.json","graph_json":"https://pith.science/api/pith-number/ERACTWVARQP7IOVB6RYS77V72T/graph.json","events_json":"https://pith.science/api/pith-number/ERACTWVARQP7IOVB6RYS77V72T/events.json","paper":"https://pith.science/paper/ERACTWVA"},"agent_actions":{"view_html":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T","download_json":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T.json","view_paper":"https://pith.science/paper/ERACTWVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.01068&json=true","fetch_graph":"https://pith.science/api/pith-number/ERACTWVARQP7IOVB6RYS77V72T/graph.json","fetch_events":"https://pith.science/api/pith-number/ERACTWVARQP7IOVB6RYS77V72T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T/action/storage_attestation","attest_author":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T/action/author_attestation","sign_citation":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T/action/citation_signature","submit_replication":"https://pith.science/pith/ERACTWVARQP7IOVB6RYS77V72T/action/replication_record"}},"created_at":"2026-05-18T00:22:10.887017+00:00","updated_at":"2026-05-18T00:22:10.887017+00:00"}