{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AU5IKNFXWIS4PZMYUNDJHEDR2J","short_pith_number":"pith:AU5IKNFX","canonical_record":{"source":{"id":"1712.01815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-05T18:45:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a80b15bd39d80a5f99e4892ac2cda76c6d7f926b9451c8bba70545844bd9e71c","abstract_canon_sha256":"46eb0d06c1b453dfc244d1e0a7df8ab26ef0b70d52acd4c9b6c068c3fc42e3e1"},"schema_version":"1.0"},"canonical_sha256":"053a8534b7b225c7e598a346939071d24c1d6131ca1668d34530b08ecdba1ff3","source":{"kind":"arxiv","id":"1712.01815","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01815","created_at":"2026-05-18T00:28:47Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01815v1","created_at":"2026-05-18T00:28:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01815","created_at":"2026-05-18T00:28:47Z"},{"alias_kind":"pith_short_12","alias_value":"AU5IKNFXWIS4","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AU5IKNFXWIS4PZMY","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AU5IKNFX","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AU5IKNFXWIS4PZMYUNDJHEDR2J","target":"record","payload":{"canonical_record":{"source":{"id":"1712.01815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-05T18:45:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a80b15bd39d80a5f99e4892ac2cda76c6d7f926b9451c8bba70545844bd9e71c","abstract_canon_sha256":"46eb0d06c1b453dfc244d1e0a7df8ab26ef0b70d52acd4c9b6c068c3fc42e3e1"},"schema_version":"1.0"},"canonical_sha256":"053a8534b7b225c7e598a346939071d24c1d6131ca1668d34530b08ecdba1ff3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:47.429957Z","signature_b64":"Gcg53BD0AUlgJUHQFs9v+3KoctYNaGabz5W02GvseJVUJcX4jzgx0YVsR4xxzK9+NOtHqiaFfHmLdaBrWVzsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"053a8534b7b225c7e598a346939071d24c1d6131ca1668d34530b08ecdba1ff3","last_reissued_at":"2026-05-18T00:28:47.429237Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:47.429237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.01815","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":"2026-05-18T00:28:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7NBCPbIuX6mwlGwbsTeezLquTFeYofbGvvotDLP6NLGM5h1OiFeX+zlT9eP0tVxW2VcXQaoLBv3GphxyR9imAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:18:38.736637Z"},"content_sha256":"4741b82d3a4ac70dbc478580d24101b7b3ae78b801fee75183d4a7e8fad0fec4","schema_version":"1.0","event_id":"sha256:4741b82d3a4ac70dbc478580d24101b7b3ae78b801fee75183d4a7e8fad0fec4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AU5IKNFXWIS4PZMYUNDJHEDR2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Arthur Guez, David Silver, Demis Hassabis, Dharshan Kumaran, Ioannis Antonoglou, Julian Schrittwieser, Karen Simonyan, Laurent Sifre, Marc Lanctot, Matthew Lai, Thomas Hubert, Thore Graepel, Timothy Lillicrap","submitted_at":"2017-12-05T18:45:38Z","abstract_excerpt":"The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01815","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":"2026-05-18T00:28:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lq8jemBB1ChSElPftajZ5KDcVBU3c7HrCVdYjYRCfySrCSg8VBzdjdeo3whPz5ab4iCx8ES9yqr/kyZ9WA/wCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:18:38.737019Z"},"content_sha256":"6bc7d7ada7c2407b022cca53bec246db0074243ea7d3d0b3bd8b98a2b9b3a20b","schema_version":"1.0","event_id":"sha256:6bc7d7ada7c2407b022cca53bec246db0074243ea7d3d0b3bd8b98a2b9b3a20b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J/bundle.json","state_url":"https://pith.science/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J/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":"2026-05-27T05:18:38Z","links":{"resolver":"https://pith.science/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J","bundle":"https://pith.science/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J/bundle.json","state":"https://pith.science/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AU5IKNFXWIS4PZMYUNDJHEDR2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AU5IKNFXWIS4PZMYUNDJHEDR2J","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":"46eb0d06c1b453dfc244d1e0a7df8ab26ef0b70d52acd4c9b6c068c3fc42e3e1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-05T18:45:38Z","title_canon_sha256":"a80b15bd39d80a5f99e4892ac2cda76c6d7f926b9451c8bba70545844bd9e71c"},"schema_version":"1.0","source":{"id":"1712.01815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01815","created_at":"2026-05-18T00:28:47Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01815v1","created_at":"2026-05-18T00:28:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01815","created_at":"2026-05-18T00:28:47Z"},{"alias_kind":"pith_short_12","alias_value":"AU5IKNFXWIS4","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AU5IKNFXWIS4PZMY","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AU5IKNFX","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:6bc7d7ada7c2407b022cca53bec246db0074243ea7d3d0b3bd8b98a2b9b3a20b","target":"graph","created_at":"2026-05-18T00:28:47Z","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":"The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance","authors_text":"Arthur Guez, David Silver, Demis Hassabis, Dharshan Kumaran, Ioannis Antonoglou, Julian Schrittwieser, Karen Simonyan, Laurent Sifre, Marc Lanctot, Matthew Lai, Thomas Hubert, Thore Graepel, Timothy Lillicrap","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-05T18:45:38Z","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01815","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":"sha256:4741b82d3a4ac70dbc478580d24101b7b3ae78b801fee75183d4a7e8fad0fec4","target":"record","created_at":"2026-05-18T00:28:47Z","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":"46eb0d06c1b453dfc244d1e0a7df8ab26ef0b70d52acd4c9b6c068c3fc42e3e1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-05T18:45:38Z","title_canon_sha256":"a80b15bd39d80a5f99e4892ac2cda76c6d7f926b9451c8bba70545844bd9e71c"},"schema_version":"1.0","source":{"id":"1712.01815","kind":"arxiv","version":1}},"canonical_sha256":"053a8534b7b225c7e598a346939071d24c1d6131ca1668d34530b08ecdba1ff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"053a8534b7b225c7e598a346939071d24c1d6131ca1668d34530b08ecdba1ff3","first_computed_at":"2026-05-18T00:28:47.429237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:47.429237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gcg53BD0AUlgJUHQFs9v+3KoctYNaGabz5W02GvseJVUJcX4jzgx0YVsR4xxzK9+NOtHqiaFfHmLdaBrWVzsAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:47.429957Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.01815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4741b82d3a4ac70dbc478580d24101b7b3ae78b801fee75183d4a7e8fad0fec4","sha256:6bc7d7ada7c2407b022cca53bec246db0074243ea7d3d0b3bd8b98a2b9b3a20b"],"state_sha256":"304e6d66bb1ef3f1ebe21e4c5e5fde54ecedd9433f9c136fa3f8ba3b140493d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpaxO50iUx6ZXEw37spYkjkZiPquY7XRcG7+WrIe2SS5WoM8gGpZXlKLLSMhOS7gCOV/X4WxV0tMgkNsqX+ACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:18:38.739794Z","bundle_sha256":"28cd120a6a212da5146402adecce82b5ee6c39c1bb3290508c10a363e6fb0b15"}}