{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CAV5OUSECDAEINY7VUYQF3AG2Q","short_pith_number":"pith:CAV5OUSE","canonical_record":{"source":{"id":"2209.01013","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T09:14:47Z","cross_cats_sorted":["econ.GN","nlin.AO","physics.soc-ph","q-fin.EC"],"title_canon_sha256":"b5ff300ce681c5ee6e9ad5a49010d759bdc8e198bef3c96de5b462ba671b917e","abstract_canon_sha256":"945aa135d1354d927977f3ac1e97aa6e8574794347e238758a50c7e5055e1fc5"},"schema_version":"1.0"},"canonical_sha256":"102bd7524410c044371fad3102ec06d4043b4ad4f44f0799af7b033d97a56ace","source":{"kind":"arxiv","id":"2209.01013","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.01013","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2209.01013v2","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01013","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"CAV5OUSECDAE","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"CAV5OUSECDAEINY7","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"CAV5OUSE","created_at":"2026-07-05T05:43:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CAV5OUSECDAEINY7VUYQF3AG2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2209.01013","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T09:14:47Z","cross_cats_sorted":["econ.GN","nlin.AO","physics.soc-ph","q-fin.EC"],"title_canon_sha256":"b5ff300ce681c5ee6e9ad5a49010d759bdc8e198bef3c96de5b462ba671b917e","abstract_canon_sha256":"945aa135d1354d927977f3ac1e97aa6e8574794347e238758a50c7e5055e1fc5"},"schema_version":"1.0"},"canonical_sha256":"102bd7524410c044371fad3102ec06d4043b4ad4f44f0799af7b033d97a56ace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:54.739190Z","signature_b64":"toP2fiVEZ50/D9kntUZ/6iYv4OqtQ3SIwOlF8eNKAkvVtGvVJCydKbSN66Mmo5c3ywd7m8NNHY0cXJxqaPBFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"102bd7524410c044371fad3102ec06d4043b4ad4f44f0799af7b033d97a56ace","last_reissued_at":"2026-07-05T05:43:54.738760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:54.738760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.01013","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vsEC//qWwaadqrwJ5UQMhAvgPaYnovD/YzulE6nAPERTGzy/HJ7hPEaGu7aBInM7vuBlMpLbgNPQd02WX+g2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:22:45.957105Z"},"content_sha256":"0da1e7ec8c32fc148dd0d0ffbd449cef5a3433aae263eb993618a0d981c2eb6d","schema_version":"1.0","event_id":"sha256:0da1e7ec8c32fc148dd0d0ffbd449cef5a3433aae263eb993618a0d981c2eb6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CAV5OUSECDAEINY7VUYQF3AG2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intrinsic fluctuations of reinforcement learning promote cooperation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["econ.GN","nlin.AO","physics.soc-ph","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Janusz Meylahn, Wolfram Barfuss","submitted_at":"2022-09-01T09:14:47Z","abstract_excerpt":"In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While evolutionary theory revealed a range of mechanisms promoting cooperation, the conditions under which agents learn to cooperate are contested. Here, we demonstrate which and how individual elements of the multi-agent learning setting lead to cooperation. We use the iterated Prisoner's dilemma with one-period memory as a testbed. Each of the two learning agents lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01013","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/2209.01013/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":"2026-07-05T05:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+v+zL+RP9o+x5pWePNa1EP5OldLF/ZjWRMEAHrkKrG9GwK0uYsHkCs52IefUNXj6B/Mkb3qf8zh5glegv/qSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:22:45.957786Z"},"content_sha256":"1fd82b338b0d64b2b0b78fa508e5b2fb18f948485227d416ad68e18635576906","schema_version":"1.0","event_id":"sha256:1fd82b338b0d64b2b0b78fa508e5b2fb18f948485227d416ad68e18635576906"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CAV5OUSECDAEINY7VUYQF3AG2Q/bundle.json","state_url":"https://pith.science/pith/CAV5OUSECDAEINY7VUYQF3AG2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CAV5OUSECDAEINY7VUYQF3AG2Q/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":"2026-07-07T07:22:45Z","links":{"resolver":"https://pith.science/pith/CAV5OUSECDAEINY7VUYQF3AG2Q","bundle":"https://pith.science/pith/CAV5OUSECDAEINY7VUYQF3AG2Q/bundle.json","state":"https://pith.science/pith/CAV5OUSECDAEINY7VUYQF3AG2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CAV5OUSECDAEINY7VUYQF3AG2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CAV5OUSECDAEINY7VUYQF3AG2Q","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":"945aa135d1354d927977f3ac1e97aa6e8574794347e238758a50c7e5055e1fc5","cross_cats_sorted":["econ.GN","nlin.AO","physics.soc-ph","q-fin.EC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T09:14:47Z","title_canon_sha256":"b5ff300ce681c5ee6e9ad5a49010d759bdc8e198bef3c96de5b462ba671b917e"},"schema_version":"1.0","source":{"id":"2209.01013","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.01013","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2209.01013v2","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01013","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"CAV5OUSECDAE","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"CAV5OUSECDAEINY7","created_at":"2026-07-05T05:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"CAV5OUSE","created_at":"2026-07-05T05:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:1fd82b338b0d64b2b0b78fa508e5b2fb18f948485227d416ad68e18635576906","target":"graph","created_at":"2026-07-05T05:43:54Z","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/2209.01013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While evolutionary theory revealed a range of mechanisms promoting cooperation, the conditions under which agents learn to cooperate are contested. Here, we demonstrate which and how individual elements of the multi-agent learning setting lead to cooperation. We use the iterated Prisoner's dilemma with one-period memory as a testbed. Each of the two learning agents lea","authors_text":"Janusz Meylahn, Wolfram Barfuss","cross_cats":["econ.GN","nlin.AO","physics.soc-ph","q-fin.EC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T09:14:47Z","title":"Intrinsic fluctuations of reinforcement learning promote cooperation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01013","kind":"arxiv","version":2},"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":"sha256:0da1e7ec8c32fc148dd0d0ffbd449cef5a3433aae263eb993618a0d981c2eb6d","target":"record","created_at":"2026-07-05T05:43:54Z","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":"945aa135d1354d927977f3ac1e97aa6e8574794347e238758a50c7e5055e1fc5","cross_cats_sorted":["econ.GN","nlin.AO","physics.soc-ph","q-fin.EC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T09:14:47Z","title_canon_sha256":"b5ff300ce681c5ee6e9ad5a49010d759bdc8e198bef3c96de5b462ba671b917e"},"schema_version":"1.0","source":{"id":"2209.01013","kind":"arxiv","version":2}},"canonical_sha256":"102bd7524410c044371fad3102ec06d4043b4ad4f44f0799af7b033d97a56ace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"102bd7524410c044371fad3102ec06d4043b4ad4f44f0799af7b033d97a56ace","first_computed_at":"2026-07-05T05:43:54.738760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:54.738760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toP2fiVEZ50/D9kntUZ/6iYv4OqtQ3SIwOlF8eNKAkvVtGvVJCydKbSN66Mmo5c3ywd7m8NNHY0cXJxqaPBFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:54.739190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.01013","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0da1e7ec8c32fc148dd0d0ffbd449cef5a3433aae263eb993618a0d981c2eb6d","sha256:1fd82b338b0d64b2b0b78fa508e5b2fb18f948485227d416ad68e18635576906"],"state_sha256":"9976d0089b55229e47d923834306bea622b5c52864b138a635e93b2c907c8246"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzmQpEm6ctKDogX3CtBty1n9VoIw9IucWEpP15zsNeTRB+1QuL+qbt/fDQO32LX3aViCeNgxQ9R4e1h5dUCoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:22:45.961756Z","bundle_sha256":"d1a59747eb9440e65c355fbae583293d02acd00309467a738125b795831078f8"}}