{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XOSOEONSJYMX3MT3KK3NCLWNP3","short_pith_number":"pith:XOSOEONS","canonical_record":{"source":{"id":"1805.07470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-18T23:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"63e2506c805daa32707aab16f64f8a521a2971142d854db12cf9b0c011136e50","abstract_canon_sha256":"6f61c2b50e4d7b39adabc5d981416db928940fc83c226944339c1982644c64d7"},"schema_version":"1.0"},"canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","source":{"kind":"arxiv","id":"1805.07470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07470","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07470v1","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07470","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"XOSOEONSJYMX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XOSOEONSJYMX3MT3","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XOSOEONS","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XOSOEONSJYMX3MT3KK3NCLWNP3","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-18T23:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"63e2506c805daa32707aab16f64f8a521a2971142d854db12cf9b0c011136e50","abstract_canon_sha256":"6f61c2b50e4d7b39adabc5d981416db928940fc83c226944339c1982644c64d7"},"schema_version":"1.0"},"canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:33.497187Z","signature_b64":"x8ndrosGChaaQCG3Qk5sqrZcRq4JJmEuEyfADwzTRWfgPOeXFMqpl4fFY1aLIk5Wem7dB91A13UgS5cLqab8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","last_reissued_at":"2026-05-18T00:15:33.496573Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:33.496573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07470","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":"2026-05-18T00:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grd7l5RG5Hcjivl9zDni0v3mCNz55q3q2a4tfCZ8JQpyzscAYVIcVLH3+F5ITjb2krRS5eXcwPahce1oVaWnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:01:25.743534Z"},"content_sha256":"1ceb8b901907aa017772f72cb057860a10130e91f80649e2b93db878c1b99ef9","schema_version":"1.0","event_id":"sha256:1ceb8b901907aa017772f72cb057860a10130e91f80649e2b93db878c1b99ef9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XOSOEONSJYMX3MT3KK3NCLWNP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solving the Rubik's Cube Without Human Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Shmakov, Forest Agostinelli, Pierre Baldi, Stephen McAleer","submitted_at":"2018-05-18T23:07:31Z","abstract_excerpt":"A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision. Recently, deep reinforcement learning algorithms combined with self-play have achieved superhuman proficiency in Go, Chess, and Shogi without human data or domain knowledge. In these environments, a reward is always received at the end of the game, however, for many combinatorial optimization environments, rewards are sparse and episodes are not guaranteed to terminate. We introduce Autodidactic Iteration: a novel reinforcement learning algorithm that is able to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07470","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":"2026-05-18T00:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u13BK/cHqVZGKnsb1Q9Hc8KOMgIt2WOZm0sMowmmnfZQHlKYUKTJHzNkcjlbA751zQjvt8hSzi09jAgsaN4DBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:01:25.744221Z"},"content_sha256":"10872c03c278d6e893f85a62f336bb213c8c0dcee62dbc861b75e91c45902507","schema_version":"1.0","event_id":"sha256:10872c03c278d6e893f85a62f336bb213c8c0dcee62dbc861b75e91c45902507"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/bundle.json","state_url":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/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":"2026-06-06T18:01:25Z","links":{"resolver":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3","bundle":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/bundle.json","state":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XOSOEONSJYMX3MT3KK3NCLWNP3","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":"6f61c2b50e4d7b39adabc5d981416db928940fc83c226944339c1982644c64d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-18T23:07:31Z","title_canon_sha256":"63e2506c805daa32707aab16f64f8a521a2971142d854db12cf9b0c011136e50"},"schema_version":"1.0","source":{"id":"1805.07470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07470","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07470v1","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07470","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"XOSOEONSJYMX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XOSOEONSJYMX3MT3","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XOSOEONS","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:10872c03c278d6e893f85a62f336bb213c8c0dcee62dbc861b75e91c45902507","target":"graph","created_at":"2026-05-18T00:15:33Z","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":"A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision. Recently, deep reinforcement learning algorithms combined with self-play have achieved superhuman proficiency in Go, Chess, and Shogi without human data or domain knowledge. In these environments, a reward is always received at the end of the game, however, for many combinatorial optimization environments, rewards are sparse and episodes are not guaranteed to terminate. We introduce Autodidactic Iteration: a novel reinforcement learning algorithm that is able to t","authors_text":"Alexander Shmakov, Forest Agostinelli, Pierre Baldi, Stephen McAleer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-18T23:07:31Z","title":"Solving the Rubik's Cube Without Human Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07470","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":"sha256:1ceb8b901907aa017772f72cb057860a10130e91f80649e2b93db878c1b99ef9","target":"record","created_at":"2026-05-18T00:15:33Z","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":"6f61c2b50e4d7b39adabc5d981416db928940fc83c226944339c1982644c64d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-18T23:07:31Z","title_canon_sha256":"63e2506c805daa32707aab16f64f8a521a2971142d854db12cf9b0c011136e50"},"schema_version":"1.0","source":{"id":"1805.07470","kind":"arxiv","version":1}},"canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","first_computed_at":"2026-05-18T00:15:33.496573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:33.496573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x8ndrosGChaaQCG3Qk5sqrZcRq4JJmEuEyfADwzTRWfgPOeXFMqpl4fFY1aLIk5Wem7dB91A13UgS5cLqab8DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:33.497187Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ceb8b901907aa017772f72cb057860a10130e91f80649e2b93db878c1b99ef9","sha256:10872c03c278d6e893f85a62f336bb213c8c0dcee62dbc861b75e91c45902507"],"state_sha256":"c633b0ae4bf60d2458c6ba8db9689b4e35e772ccc407910291e4c4574e09546e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86hcLkJl001SExZ8na5tiX7xl8MVsdx0ubGlv3tNo7e6QqA0ue4uydk3IdGsrP2RWPB/wp5ViEUAn+jd3jWjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:01:25.748099Z","bundle_sha256":"2a7c689365a890778110d158ab3f29ead36b3de5887ec9b2da325b6ca0b6d610"}}