{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:I3JPEUVXUBCASCJDQGRSAVYQC5","short_pith_number":"pith:I3JPEUVX","canonical_record":{"source":{"id":"1810.06078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-14T18:49:33Z","cross_cats_sorted":[],"title_canon_sha256":"cb610496ac500327ff9840318fc9fc2d972070499fb8d380afe4200050d2fec6","abstract_canon_sha256":"ae4d078bbc7aa2a79c13221169dad1336c9b13cbf648816aa98b4c32f9cde8ce"},"schema_version":"1.0"},"canonical_sha256":"46d2f252b7a04409092381a320571017610b1a826322b81bcdf6f352bab20587","source":{"kind":"arxiv","id":"1810.06078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06078","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06078v1","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06078","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"I3JPEUVXUBCA","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I3JPEUVXUBCASCJD","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I3JPEUVX","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:I3JPEUVXUBCASCJDQGRSAVYQC5","target":"record","payload":{"canonical_record":{"source":{"id":"1810.06078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-14T18:49:33Z","cross_cats_sorted":[],"title_canon_sha256":"cb610496ac500327ff9840318fc9fc2d972070499fb8d380afe4200050d2fec6","abstract_canon_sha256":"ae4d078bbc7aa2a79c13221169dad1336c9b13cbf648816aa98b4c32f9cde8ce"},"schema_version":"1.0"},"canonical_sha256":"46d2f252b7a04409092381a320571017610b1a826322b81bcdf6f352bab20587","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:14.354477Z","signature_b64":"pH1MJ8eq375cbAR6j4RIY6ow2SmVKWXkOkA7ro5jCCgAOMxIpWPJzEAYghFDSItHxQnf3hmqVsflzikTHu63Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d2f252b7a04409092381a320571017610b1a826322b81bcdf6f352bab20587","last_reissued_at":"2026-05-18T00:03:14.353914Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:14.353914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.06078","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":"2026-05-18T00:03:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaZWs/ALxdJm06JIXzfc0Thi7lfAC4yD3jcPHBlNJ3JrIhZYO//rUu1e26Bxfo8pT0Ng7UDpWyQxukAJtsg7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:48:16.667971Z"},"content_sha256":"dc7cb9da5ef00b01259538b78c3f265bf172ef01e20ab0684d1692b54f117270","schema_version":"1.0","event_id":"sha256:dc7cb9da5ef00b01259538b78c3f265bf172ef01e20ab0684d1692b54f117270"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:I3JPEUVXUBCASCJDQGRSAVYQC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing the Potential of Classical Q-learning in General Game Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aske Plaat, Hui Wang, Michael Emmerich","submitted_at":"2018-10-14T18:49:33Z","abstract_excerpt":"After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed. For small games, simple classical table-based Q-learning might still be the algorithm of choice. General Game Playing (GGP) provides a good testbed for reinforcement learning to research AGI. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee $\\&$ Stone, IJCAI 2007) in GGP. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06078","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":"2026-05-18T00:03:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aZXsXoP7YAdX+ovYwdRt7BKUsm5erpphRAQk5iZrNVpsiTsw8pBlPv+vZON+HNl9+ep7/WBFZqA3FfRuNoCKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:48:16.668339Z"},"content_sha256":"24b84e185a6013530e2be7e855763884a83bb69f05799c51de6c849550127fde","schema_version":"1.0","event_id":"sha256:24b84e185a6013530e2be7e855763884a83bb69f05799c51de6c849550127fde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3JPEUVXUBCASCJDQGRSAVYQC5/bundle.json","state_url":"https://pith.science/pith/I3JPEUVXUBCASCJDQGRSAVYQC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3JPEUVXUBCASCJDQGRSAVYQC5/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":"2026-06-05T20:48:16Z","links":{"resolver":"https://pith.science/pith/I3JPEUVXUBCASCJDQGRSAVYQC5","bundle":"https://pith.science/pith/I3JPEUVXUBCASCJDQGRSAVYQC5/bundle.json","state":"https://pith.science/pith/I3JPEUVXUBCASCJDQGRSAVYQC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3JPEUVXUBCASCJDQGRSAVYQC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I3JPEUVXUBCASCJDQGRSAVYQC5","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":"ae4d078bbc7aa2a79c13221169dad1336c9b13cbf648816aa98b4c32f9cde8ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-14T18:49:33Z","title_canon_sha256":"cb610496ac500327ff9840318fc9fc2d972070499fb8d380afe4200050d2fec6"},"schema_version":"1.0","source":{"id":"1810.06078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06078","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06078v1","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06078","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"I3JPEUVXUBCA","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I3JPEUVXUBCASCJD","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I3JPEUVX","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:24b84e185a6013530e2be7e855763884a83bb69f05799c51de6c849550127fde","target":"graph","created_at":"2026-05-18T00:03:14Z","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":"After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed. For small games, simple classical table-based Q-learning might still be the algorithm of choice. General Game Playing (GGP) provides a good testbed for reinforcement learning to research AGI. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee $\\&$ Stone, IJCAI 2007) in GGP. In th","authors_text":"Aske Plaat, Hui Wang, Michael Emmerich","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-14T18:49:33Z","title":"Assessing the Potential of Classical Q-learning in General Game Playing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06078","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:dc7cb9da5ef00b01259538b78c3f265bf172ef01e20ab0684d1692b54f117270","target":"record","created_at":"2026-05-18T00:03:14Z","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":"ae4d078bbc7aa2a79c13221169dad1336c9b13cbf648816aa98b4c32f9cde8ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-14T18:49:33Z","title_canon_sha256":"cb610496ac500327ff9840318fc9fc2d972070499fb8d380afe4200050d2fec6"},"schema_version":"1.0","source":{"id":"1810.06078","kind":"arxiv","version":1}},"canonical_sha256":"46d2f252b7a04409092381a320571017610b1a826322b81bcdf6f352bab20587","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46d2f252b7a04409092381a320571017610b1a826322b81bcdf6f352bab20587","first_computed_at":"2026-05-18T00:03:14.353914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:14.353914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pH1MJ8eq375cbAR6j4RIY6ow2SmVKWXkOkA7ro5jCCgAOMxIpWPJzEAYghFDSItHxQnf3hmqVsflzikTHu63Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:14.354477Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc7cb9da5ef00b01259538b78c3f265bf172ef01e20ab0684d1692b54f117270","sha256:24b84e185a6013530e2be7e855763884a83bb69f05799c51de6c849550127fde"],"state_sha256":"7da1bce24665990241bfd6c931524494c76ebc328415f4add651a3c7da55e4dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hi7XAxy4BiZov9MX2Uap+DPd1MrBDskB7RKPvIW5Gf7T91ceXTb9gV/E5r27XemCPjaVFxyIt8A6pQeFR63eDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T20:48:16.670279Z","bundle_sha256":"9d483e300272688e40327462c38cab55f4d77c119b6d6a5553bece8f834a9543"}}