{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CWHN5XFOF7LCNPAA7QMR5O5ISP","short_pith_number":"pith:CWHN5XFO","canonical_record":{"source":{"id":"2401.16073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.PE","submitted_at":"2024-01-29T11:30:35Z","cross_cats_sorted":["cond-mat.dis-nn","nlin.AO","physics.soc-ph"],"title_canon_sha256":"79a6f8562ccae4d12f13d208bb0344a4fe339b6b3b1bea314fbea7078d46f81f","abstract_canon_sha256":"7d339087733e783a6dd1fd9f95a0ba5b25337b7b23efeeebd57181f9c14fe06d"},"schema_version":"1.0"},"canonical_sha256":"158ededcae2fd626bc00fc191ebba893dc532360de69cdcff248eea0ce0d3a30","source":{"kind":"arxiv","id":"2401.16073","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16073","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16073v1","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16073","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"pith_short_12","alias_value":"CWHN5XFOF7LC","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"pith_short_16","alias_value":"CWHN5XFOF7LCNPAA","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"pith_short_8","alias_value":"CWHN5XFO","created_at":"2026-07-05T09:51:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CWHN5XFOF7LCNPAA7QMR5O5ISP","target":"record","payload":{"canonical_record":{"source":{"id":"2401.16073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.PE","submitted_at":"2024-01-29T11:30:35Z","cross_cats_sorted":["cond-mat.dis-nn","nlin.AO","physics.soc-ph"],"title_canon_sha256":"79a6f8562ccae4d12f13d208bb0344a4fe339b6b3b1bea314fbea7078d46f81f","abstract_canon_sha256":"7d339087733e783a6dd1fd9f95a0ba5b25337b7b23efeeebd57181f9c14fe06d"},"schema_version":"1.0"},"canonical_sha256":"158ededcae2fd626bc00fc191ebba893dc532360de69cdcff248eea0ce0d3a30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:30.548517Z","signature_b64":"+aJ8qyWGKzfpWGkpot6k0/tQ009xUoVays9KfVj6V22kAGbBdjnnTpi8Oak6CS8qJ8YAoZCD3fzkOdTGBTP9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158ededcae2fd626bc00fc191ebba893dc532360de69cdcff248eea0ce0d3a30","last_reissued_at":"2026-07-05T09:51:30.547988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:30.547988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.16073","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:51:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kyil4xMPUIfxbWui0ReIJjHKZdgZIhbM9+jpEG+iP/bC5Y38hFEYr+sHxcBfVjYFTIZIhUkP9g7iRS64BiU0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:01:00.361995Z"},"content_sha256":"e1a3cff3865fcc48fb3d03e1e8ff179707a3eb91e34ebac479a942496e6de7e1","schema_version":"1.0","event_id":"sha256:e1a3cff3865fcc48fb3d03e1e8ff179707a3eb91e34ebac479a942496e6de7e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CWHN5XFOF7LCNPAA7QMR5O5ISP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emergence of cooperation under punishment: A reinforcement learning perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","nlin.AO","physics.soc-ph"],"primary_cat":"q-bio.PE","authors_text":"Chenyang Zhao, Chun Zhang, Guozhong Zheng, Jiqiang Zhang, Li Chen","submitted_at":"2024-01-29T11:30:35Z","abstract_excerpt":"Punishment is a common tactic to sustain cooperation and has been extensively studied for a long time. While most of previous game-theoretic work adopt the imitation learning where players imitate the strategies who are better off, the learning logic in the real world is often much more complex. In this work, we turn to the reinforcement learning paradigm, where individuals make their decisions based upon their past experience and long-term returns. Specifically, we investigate the Prisoners' dilemma game with Q-learning algorithm, and cooperators probabilistically pose punishment on defectors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16073","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/2401.16073/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:51:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIdR6udtKKU9OrxT7hHEChBWlgBoKT+L1oRKS8K/hcuTYyDdpYVxlWRXDTI34jvz+adsKVSaHhhSN6eJdCi5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:01:00.362375Z"},"content_sha256":"24d0dc31df5299103436c6b810c8eec2a435ae4779d08c04b7f317c6e5e1a83d","schema_version":"1.0","event_id":"sha256:24d0dc31df5299103436c6b810c8eec2a435ae4779d08c04b7f317c6e5e1a83d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP/bundle.json","state_url":"https://pith.science/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-17T02:01:00Z","links":{"resolver":"https://pith.science/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP","bundle":"https://pith.science/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP/bundle.json","state":"https://pith.science/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWHN5XFOF7LCNPAA7QMR5O5ISP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CWHN5XFOF7LCNPAA7QMR5O5ISP","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":"7d339087733e783a6dd1fd9f95a0ba5b25337b7b23efeeebd57181f9c14fe06d","cross_cats_sorted":["cond-mat.dis-nn","nlin.AO","physics.soc-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.PE","submitted_at":"2024-01-29T11:30:35Z","title_canon_sha256":"79a6f8562ccae4d12f13d208bb0344a4fe339b6b3b1bea314fbea7078d46f81f"},"schema_version":"1.0","source":{"id":"2401.16073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16073","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16073v1","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16073","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"pith_short_12","alias_value":"CWHN5XFOF7LC","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"pith_short_16","alias_value":"CWHN5XFOF7LCNPAA","created_at":"2026-07-05T09:51:30Z"},{"alias_kind":"pith_short_8","alias_value":"CWHN5XFO","created_at":"2026-07-05T09:51:30Z"}],"graph_snapshots":[{"event_id":"sha256:24d0dc31df5299103436c6b810c8eec2a435ae4779d08c04b7f317c6e5e1a83d","target":"graph","created_at":"2026-07-05T09:51:30Z","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/2401.16073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Punishment is a common tactic to sustain cooperation and has been extensively studied for a long time. While most of previous game-theoretic work adopt the imitation learning where players imitate the strategies who are better off, the learning logic in the real world is often much more complex. In this work, we turn to the reinforcement learning paradigm, where individuals make their decisions based upon their past experience and long-term returns. Specifically, we investigate the Prisoners' dilemma game with Q-learning algorithm, and cooperators probabilistically pose punishment on defectors","authors_text":"Chenyang Zhao, Chun Zhang, Guozhong Zheng, Jiqiang Zhang, Li Chen","cross_cats":["cond-mat.dis-nn","nlin.AO","physics.soc-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.PE","submitted_at":"2024-01-29T11:30:35Z","title":"Emergence of cooperation under punishment: A reinforcement learning perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16073","kind":"arxiv","version":1},"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:e1a3cff3865fcc48fb3d03e1e8ff179707a3eb91e34ebac479a942496e6de7e1","target":"record","created_at":"2026-07-05T09:51:30Z","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":"7d339087733e783a6dd1fd9f95a0ba5b25337b7b23efeeebd57181f9c14fe06d","cross_cats_sorted":["cond-mat.dis-nn","nlin.AO","physics.soc-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.PE","submitted_at":"2024-01-29T11:30:35Z","title_canon_sha256":"79a6f8562ccae4d12f13d208bb0344a4fe339b6b3b1bea314fbea7078d46f81f"},"schema_version":"1.0","source":{"id":"2401.16073","kind":"arxiv","version":1}},"canonical_sha256":"158ededcae2fd626bc00fc191ebba893dc532360de69cdcff248eea0ce0d3a30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"158ededcae2fd626bc00fc191ebba893dc532360de69cdcff248eea0ce0d3a30","first_computed_at":"2026-07-05T09:51:30.547988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:30.547988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+aJ8qyWGKzfpWGkpot6k0/tQ009xUoVays9KfVj6V22kAGbBdjnnTpi8Oak6CS8qJ8YAoZCD3fzkOdTGBTP9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:30.548517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1a3cff3865fcc48fb3d03e1e8ff179707a3eb91e34ebac479a942496e6de7e1","sha256:24d0dc31df5299103436c6b810c8eec2a435ae4779d08c04b7f317c6e5e1a83d"],"state_sha256":"7e2fd108742b332841ea52378df5d185f307b8ba9e45985821a4217854af783c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsXDp3f3tJ+lQ2A6F21ibFSR4Bjujssz3t7y/up90MaScnYwgabPR2685dYLGrW/2EGzn18C58wkvdQPXqNBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T02:01:00.364435Z","bundle_sha256":"69a1382a1763082ce3f61ae89e528fad2b5f80534098c67c92fd2dff97fd1ce8"}}