{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PR6E4J5G26G5DC22RHFDI4SB5X","short_pith_number":"pith:PR6E4J5G","schema_version":"1.0","canonical_sha256":"7c7c4e27a6d78dd18b5a89ca347241ededc86cf9554087e682572586817fc478","source":{"kind":"arxiv","id":"2204.12371","version":3},"attestation_state":"computed","paper":{"title":"Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SI"],"primary_cat":"cs.LG","authors_text":"Hawoong Jeong, Seungwoong Ha","submitted_at":"2022-04-26T15:10:27Z","abstract_excerpt":"How have individuals of social animals in nature evolved to learn from each other, and what would be the optimal strategy for such learning in a specific environment? Here, we address both problems by employing a deep reinforcement learning model to optimize the social learning strategies (SLSs) of agents in a cooperative game in a multi-dimensional landscape. Throughout the training for maximizing the overall payoff, we find that the agent spontaneously learns various concepts of social learning, such as copying, focusing on frequent and well-performing neighbors, self-comparison, and the imp"},"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":"2204.12371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T15:10:27Z","cross_cats_sorted":["cs.NE","cs.SI"],"title_canon_sha256":"9aa8ce044603a0c90053509daff30515a58d06101f8921e3b207c87598839a41","abstract_canon_sha256":"9b8d61cca4a929e6d8104c79ca02d1808ed867dc053396ee462e0d54d977807f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:25.038869Z","signature_b64":"EqNxxgki5jJuKD8rE7r29FxBmVvIxOs7FcMGmeDjhnGbwxqlj/kl+Xla394HTuN2zXC9pdVqowM5il2JLSDvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c7c4e27a6d78dd18b5a89ca347241ededc86cf9554087e682572586817fc478","last_reissued_at":"2026-07-05T05:42:25.038459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:25.038459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SI"],"primary_cat":"cs.LG","authors_text":"Hawoong Jeong, Seungwoong Ha","submitted_at":"2022-04-26T15:10:27Z","abstract_excerpt":"How have individuals of social animals in nature evolved to learn from each other, and what would be the optimal strategy for such learning in a specific environment? Here, we address both problems by employing a deep reinforcement learning model to optimize the social learning strategies (SLSs) of agents in a cooperative game in a multi-dimensional landscape. Throughout the training for maximizing the overall payoff, we find that the agent spontaneously learns various concepts of social learning, such as copying, focusing on frequent and well-performing neighbors, self-comparison, and the imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12371","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/2204.12371/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":"2204.12371","created_at":"2026-07-05T05:42:25.038513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.12371v3","created_at":"2026-07-05T05:42:25.038513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12371","created_at":"2026-07-05T05:42:25.038513+00:00"},{"alias_kind":"pith_short_12","alias_value":"PR6E4J5G26G5","created_at":"2026-07-05T05:42:25.038513+00:00"},{"alias_kind":"pith_short_16","alias_value":"PR6E4J5G26G5DC22","created_at":"2026-07-05T05:42:25.038513+00:00"},{"alias_kind":"pith_short_8","alias_value":"PR6E4J5G","created_at":"2026-07-05T05:42:25.038513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X","json":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X.json","graph_json":"https://pith.science/api/pith-number/PR6E4J5G26G5DC22RHFDI4SB5X/graph.json","events_json":"https://pith.science/api/pith-number/PR6E4J5G26G5DC22RHFDI4SB5X/events.json","paper":"https://pith.science/paper/PR6E4J5G"},"agent_actions":{"view_html":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X","download_json":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X.json","view_paper":"https://pith.science/paper/PR6E4J5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.12371&json=true","fetch_graph":"https://pith.science/api/pith-number/PR6E4J5G26G5DC22RHFDI4SB5X/graph.json","fetch_events":"https://pith.science/api/pith-number/PR6E4J5G26G5DC22RHFDI4SB5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X/action/storage_attestation","attest_author":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X/action/author_attestation","sign_citation":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X/action/citation_signature","submit_replication":"https://pith.science/pith/PR6E4J5G26G5DC22RHFDI4SB5X/action/replication_record"}},"created_at":"2026-07-05T05:42:25.038513+00:00","updated_at":"2026-07-05T05:42:25.038513+00:00"}