{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QHUZUH7LSVTO2EL7UNZHS76VYK","short_pith_number":"pith:QHUZUH7L","canonical_record":{"source":{"id":"1709.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-08T21:52:58Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"b9ca3a3d6036779ed980eb5dceddbc6321f7d2e4cfaa8ed96d8b544eb50d5a3a","abstract_canon_sha256":"0f8d18d449a2adda8e778355f60d3574f6821d9d1a81cd2bf0f4027fc0a3f7e3"},"schema_version":"1.0"},"canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","source":{"kind":"arxiv","id":"1709.02865","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02865","created_at":"2026-05-18T00:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02865v2","created_at":"2026-05-18T00:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02865","created_at":"2026-05-18T00:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"QHUZUH7LSVTO","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QHUZUH7LSVTO2EL7","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QHUZUH7L","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QHUZUH7LSVTO2EL7UNZHS76VYK","target":"record","payload":{"canonical_record":{"source":{"id":"1709.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-08T21:52:58Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"b9ca3a3d6036779ed980eb5dceddbc6321f7d2e4cfaa8ed96d8b544eb50d5a3a","abstract_canon_sha256":"0f8d18d449a2adda8e778355f60d3574f6821d9d1a81cd2bf0f4027fc0a3f7e3"},"schema_version":"1.0"},"canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:29.677909Z","signature_b64":"OiwTJpaKrfJz6/YrtgpDGrYNDG+JVlGfERNEysLww2SjzdtWmLeKH6fxyfnCTxjLTECBB0XeQ/VvDxO5Aa63AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","last_reissued_at":"2026-05-18T00:28:29.677160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:29.677160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.02865","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":"2026-05-18T00:28:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0+WtPPT6bLqr553pouh8Lb946h54wqBSZ8N8EMIIlcSFet6GmCFOEv/zTcFvwyrHWrfyoN+wwhzoy0gDPWmMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T08:04:52.969908Z"},"content_sha256":"39d21289b80a67e56df185ed8a448b81d2f54b862e50c73872535e9ce3effc6c","schema_version":"1.0","event_id":"sha256:39d21289b80a67e56df185ed8a448b81d2f54b862e50c73872535e9ce3effc6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QHUZUH7LSVTO2EL7UNZHS76VYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Alexander Peysakhovich","submitted_at":"2017-09-08T21:52:58Z","abstract_excerpt":"Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying standard RL methods while treating other agents as a part of the learner's environment. It is known that in general-sum games reactive training can lead groups of agents to converge to inefficient outcomes. We focus on one such class of environments: Stag Hunt games. Here agents either choose a risky cooperative policy (which leads to high payoffs if both choo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02865","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":""},"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":"2026-05-18T00:28:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xp6eYbIdiUdoKVDlZ8hRcIFu0Gd+yYy6401uXCV5cm8VYCPhEu4sQyIWu0ezHF3b3oL/DwzrwsnY017CSbN4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T08:04:52.970362Z"},"content_sha256":"cf58b358ae89c44f307d8c05a554e8526332d86da2b347977f0131d96bb563d2","schema_version":"1.0","event_id":"sha256:cf58b358ae89c44f307d8c05a554e8526332d86da2b347977f0131d96bb563d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/bundle.json","state_url":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/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":"2026-05-22T08:04:52Z","links":{"resolver":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK","bundle":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/bundle.json","state":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QHUZUH7LSVTO2EL7UNZHS76VYK","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":"0f8d18d449a2adda8e778355f60d3574f6821d9d1a81cd2bf0f4027fc0a3f7e3","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-08T21:52:58Z","title_canon_sha256":"b9ca3a3d6036779ed980eb5dceddbc6321f7d2e4cfaa8ed96d8b544eb50d5a3a"},"schema_version":"1.0","source":{"id":"1709.02865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02865","created_at":"2026-05-18T00:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02865v2","created_at":"2026-05-18T00:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02865","created_at":"2026-05-18T00:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"QHUZUH7LSVTO","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QHUZUH7LSVTO2EL7","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QHUZUH7L","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:cf58b358ae89c44f307d8c05a554e8526332d86da2b347977f0131d96bb563d2","target":"graph","created_at":"2026-05-18T00:28:29Z","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"},"paper":{"abstract_excerpt":"Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying standard RL methods while treating other agents as a part of the learner's environment. It is known that in general-sum games reactive training can lead groups of agents to converge to inefficient outcomes. We focus on one such class of environments: Stag Hunt games. Here agents either choose a risky cooperative policy (which leads to high payoffs if both choo","authors_text":"Adam Lerer, Alexander Peysakhovich","cross_cats":["cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-08T21:52:58Z","title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02865","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":"sha256:39d21289b80a67e56df185ed8a448b81d2f54b862e50c73872535e9ce3effc6c","target":"record","created_at":"2026-05-18T00:28:29Z","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":"0f8d18d449a2adda8e778355f60d3574f6821d9d1a81cd2bf0f4027fc0a3f7e3","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-08T21:52:58Z","title_canon_sha256":"b9ca3a3d6036779ed980eb5dceddbc6321f7d2e4cfaa8ed96d8b544eb50d5a3a"},"schema_version":"1.0","source":{"id":"1709.02865","kind":"arxiv","version":2}},"canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","first_computed_at":"2026-05-18T00:28:29.677160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:29.677160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OiwTJpaKrfJz6/YrtgpDGrYNDG+JVlGfERNEysLww2SjzdtWmLeKH6fxyfnCTxjLTECBB0XeQ/VvDxO5Aa63AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:29.677909Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.02865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39d21289b80a67e56df185ed8a448b81d2f54b862e50c73872535e9ce3effc6c","sha256:cf58b358ae89c44f307d8c05a554e8526332d86da2b347977f0131d96bb563d2"],"state_sha256":"533b09f303a8cea5aa614ce5997e54ae309a013af7c25ae09875d6cfef676e02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUFwM6yR+CrCPk3pNUqU60SYVNNSRwhyvn4SZ97tXO8qP4tIL3igP9gxTWE2c7sHVOefbkczEjGppK2GkWp+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T08:04:52.973751Z","bundle_sha256":"a9e4a780318fcfdec4eb8e343bca4c70b3a891c2def2341ac3b0187ead35cb73"}}