{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EE3UD2QXOUGQHR7ZLGUL7I47DA","short_pith_number":"pith:EE3UD2QX","canonical_record":{"source":{"id":"1807.01281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T16:57:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5a2234de7b429ff1d12e04bcab3c7d970485742fecabc1565db02a1890acff2f","abstract_canon_sha256":"903db0363bc9ae2ab55b96e18645efd51b66b19affb5c25219c815e3e670ae76"},"schema_version":"1.0"},"canonical_sha256":"213741ea17750d03c7f959a8bfa39f1828af1932eb89e1d9b1f09dbef304c0b1","source":{"kind":"arxiv","id":"1807.01281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01281","created_at":"2026-05-17T23:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01281v1","created_at":"2026-05-17T23:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01281","created_at":"2026-05-17T23:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"EE3UD2QXOUGQ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EE3UD2QXOUGQHR7Z","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EE3UD2QX","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EE3UD2QXOUGQHR7ZLGUL7I47DA","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T16:57:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5a2234de7b429ff1d12e04bcab3c7d970485742fecabc1565db02a1890acff2f","abstract_canon_sha256":"903db0363bc9ae2ab55b96e18645efd51b66b19affb5c25219c815e3e670ae76"},"schema_version":"1.0"},"canonical_sha256":"213741ea17750d03c7f959a8bfa39f1828af1932eb89e1d9b1f09dbef304c0b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:04.903606Z","signature_b64":"Fkklb2idiMJVrnLZvb4Ifb8mF8N8hLggnUPYstqZGGzFNA+TTCghgP+ekNMrd6wHagWFeaCeZSnMyLBBOdk8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213741ea17750d03c7f959a8bfa39f1828af1932eb89e1d9b1f09dbef304c0b1","last_reissued_at":"2026-05-17T23:43:04.903198Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:04.903198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01281","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":"2026-05-17T23:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1T9bZp+5nfuOEBRSVzuBgqK6iPOCEPnjAOt3zJpioY/o8SdcynAeDlAzzdXr0Z8DGgTQdbtIIRbNFprxX8C1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:19:20.023527Z"},"content_sha256":"a26b3f73464e55f596e88c76e24d34e219721bf995b01ae538f677c7d0c05e13","schema_version":"1.0","event_id":"sha256:a26b3f73464e55f596e88c76e24d34e219721bf995b01ae538f677c7d0c05e13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EE3UD2QXOUGQHR7ZLGUL7I47DA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Garcia Castaneda, Ari S. Morcos, Avraham Ruderman, Charles Beattie, David Silver, Demis Hassabis, Guy Lever, Iain Dunning, Joel Z. Leibo, Koray Kavukcuoglu, Louise Deason, Luke Marris, Max Jaderberg, Neil C. Rabinowitz, Nicolas Sonnerat, Thore Graepel, Tim Green, Wojciech M. Czarnecki","submitted_at":"2018-07-03T16:57:18Z","abstract_excerpt":"Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each learning and acting independently to cooperate and compete with other agents, and environments reflecting this degree of complexity remain an open challenge. In this work, we demonstrate for the first time that an agent can achieve human-level in a popular 3D multiplayer first-person video game, Quake III Arena Capture the Flag, using only pixels and game p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01281","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":""},"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":"2026-05-17T23:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WT6mTbJhPS/8eIB4uLHuIO/xlFxBR2NYvSH5Ivj+8xDHpqRMOmqR2V9KCxmzFNiGzUZ/KKpZ/QWciuQdcq/vDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:19:20.024277Z"},"content_sha256":"14403e7d9969229258f384454a953f81884b093326d8964a18388904f413fb33","schema_version":"1.0","event_id":"sha256:14403e7d9969229258f384454a953f81884b093326d8964a18388904f413fb33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA/bundle.json","state_url":"https://pith.science/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA/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":"2026-05-30T12:19:20Z","links":{"resolver":"https://pith.science/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA","bundle":"https://pith.science/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA/bundle.json","state":"https://pith.science/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EE3UD2QXOUGQHR7ZLGUL7I47DA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EE3UD2QXOUGQHR7ZLGUL7I47DA","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":"903db0363bc9ae2ab55b96e18645efd51b66b19affb5c25219c815e3e670ae76","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T16:57:18Z","title_canon_sha256":"5a2234de7b429ff1d12e04bcab3c7d970485742fecabc1565db02a1890acff2f"},"schema_version":"1.0","source":{"id":"1807.01281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01281","created_at":"2026-05-17T23:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01281v1","created_at":"2026-05-17T23:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01281","created_at":"2026-05-17T23:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"EE3UD2QXOUGQ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EE3UD2QXOUGQHR7Z","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EE3UD2QX","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:14403e7d9969229258f384454a953f81884b093326d8964a18388904f413fb33","target":"graph","created_at":"2026-05-17T23:43:04Z","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":"Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each learning and acting independently to cooperate and compete with other agents, and environments reflecting this degree of complexity remain an open challenge. In this work, we demonstrate for the first time that an agent can achieve human-level in a popular 3D multiplayer first-person video game, Quake III Arena Capture the Flag, using only pixels and game p","authors_text":"Antonio Garcia Castaneda, Ari S. Morcos, Avraham Ruderman, Charles Beattie, David Silver, Demis Hassabis, Guy Lever, Iain Dunning, Joel Z. Leibo, Koray Kavukcuoglu, Louise Deason, Luke Marris, Max Jaderberg, Neil C. Rabinowitz, Nicolas Sonnerat, Thore Graepel, Tim Green, Wojciech M. Czarnecki","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T16:57:18Z","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01281","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:a26b3f73464e55f596e88c76e24d34e219721bf995b01ae538f677c7d0c05e13","target":"record","created_at":"2026-05-17T23:43:04Z","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":"903db0363bc9ae2ab55b96e18645efd51b66b19affb5c25219c815e3e670ae76","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T16:57:18Z","title_canon_sha256":"5a2234de7b429ff1d12e04bcab3c7d970485742fecabc1565db02a1890acff2f"},"schema_version":"1.0","source":{"id":"1807.01281","kind":"arxiv","version":1}},"canonical_sha256":"213741ea17750d03c7f959a8bfa39f1828af1932eb89e1d9b1f09dbef304c0b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"213741ea17750d03c7f959a8bfa39f1828af1932eb89e1d9b1f09dbef304c0b1","first_computed_at":"2026-05-17T23:43:04.903198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:04.903198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fkklb2idiMJVrnLZvb4Ifb8mF8N8hLggnUPYstqZGGzFNA+TTCghgP+ekNMrd6wHagWFeaCeZSnMyLBBOdk8Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:04.903606Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26b3f73464e55f596e88c76e24d34e219721bf995b01ae538f677c7d0c05e13","sha256:14403e7d9969229258f384454a953f81884b093326d8964a18388904f413fb33"],"state_sha256":"045cd6d7fc5bd14c3cfb3689f4b7c6525073ad478a011d3e77da839e9b50daec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4SKBACs++9KGrYKpJhP5NbOpnC6EzdxqAN8qDJJg/G/TNIT5MYnjSc1QMHxOdJqFlZgU2uiwfzL3e6qONBsCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:19:20.027922Z","bundle_sha256":"15fdaa2c7b8b044f950f57a1786593ab09c15be04ccf35aaf243f967ee1674c3"}}