{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GC36FAJXVWKWSIX3N5CYDZRUQM","short_pith_number":"pith:GC36FAJX","canonical_record":{"source":{"id":"1903.03674","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-08T21:38:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31db15f9f138ca051ae4bf58c18d150cfb8dae4d1743d6c964d656a8d711e735","abstract_canon_sha256":"8b9663365d1867daa36a42087744a5cc5011391cdf9df6d113d987e46208d5b9"},"schema_version":"1.0"},"canonical_sha256":"30b7e28137ad956922fb6f4581e634832f7cc2451be974d93def8ccca894be3c","source":{"kind":"arxiv","id":"1903.03674","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03674","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03674v2","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03674","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"GC36FAJXVWKW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GC36FAJXVWKWSIX3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GC36FAJX","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GC36FAJXVWKWSIX3N5CYDZRUQM","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03674","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-08T21:38:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31db15f9f138ca051ae4bf58c18d150cfb8dae4d1743d6c964d656a8d711e735","abstract_canon_sha256":"8b9663365d1867daa36a42087744a5cc5011391cdf9df6d113d987e46208d5b9"},"schema_version":"1.0"},"canonical_sha256":"30b7e28137ad956922fb6f4581e634832f7cc2451be974d93def8ccca894be3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:40.972399Z","signature_b64":"aVWRYdvE6NRd/eQrm2/cFrSRH4U+2cd7th80Whd4ubJNDaG+QqgARDeNYVQhrW0AiOg/CYdvXZ1qlmNZZEEEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b7e28137ad956922fb6f4581e634832f7cc2451be974d93def8ccca894be3c","last_reissued_at":"2026-05-17T23:46:40.971835Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:40.971835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03674","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":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bEKL7rt4qGRSDlPv0ckNKmNqt+S7KBTUo8jXHVGjit0+9q+23SWEi8bA0Z+Vb7uAmPII5vB/pe5kldx56Q5JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T20:29:22.570034Z"},"content_sha256":"c86e4ed6db06b98c7a02f4efc8382d26f43c59f79cba6debb5ecd6acca01e4ac","schema_version":"1.0","event_id":"sha256:c86e4ed6db06b98c7a02f4efc8382d26f43c59f79cba6debb5ecd6acca01e4ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GC36FAJXVWKWSIX3N5CYDZRUQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Self-Game-Play Agents for Combinatorial Optimization Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Karl Lieberherr, Ruiyang Xu","submitted_at":"2019-03-08T21:38:33Z","abstract_excerpt":"Recent progress in reinforcement learning (RL) using self-game-play has shown remarkable performance on several board games (e.g., Chess and Go) as well as video games (e.g., Atari games and Dota2). It is plausible to consider that RL, starting from zero knowledge, might be able to gradually approximate a winning strategy after a certain amount of training. In this paper, we explore neural Monte-Carlo-Tree-Search (neural MCTS), an RL algorithm which has been applied successfully by DeepMind to play Go and Chess at a super-human level. We try to leverage the computational power of neural MCTS t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03674","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":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yOaG6/T8ejYKKko9cG0/yhUE9t+3SpvRWGu6LVPwE43JAQ6LJLW7ZvnJx1qc2bbK+SeIJnSP5QaOGI4/MzQ1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T20:29:22.570743Z"},"content_sha256":"96fb429981d627baf2ac77b226fde6b0b949aff9f8cd45a9078683513ecba75f","schema_version":"1.0","event_id":"sha256:96fb429981d627baf2ac77b226fde6b0b949aff9f8cd45a9078683513ecba75f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GC36FAJXVWKWSIX3N5CYDZRUQM/bundle.json","state_url":"https://pith.science/pith/GC36FAJXVWKWSIX3N5CYDZRUQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GC36FAJXVWKWSIX3N5CYDZRUQM/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":"2026-06-08T20:29:22Z","links":{"resolver":"https://pith.science/pith/GC36FAJXVWKWSIX3N5CYDZRUQM","bundle":"https://pith.science/pith/GC36FAJXVWKWSIX3N5CYDZRUQM/bundle.json","state":"https://pith.science/pith/GC36FAJXVWKWSIX3N5CYDZRUQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GC36FAJXVWKWSIX3N5CYDZRUQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GC36FAJXVWKWSIX3N5CYDZRUQM","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":"8b9663365d1867daa36a42087744a5cc5011391cdf9df6d113d987e46208d5b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-08T21:38:33Z","title_canon_sha256":"31db15f9f138ca051ae4bf58c18d150cfb8dae4d1743d6c964d656a8d711e735"},"schema_version":"1.0","source":{"id":"1903.03674","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03674","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03674v2","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03674","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"GC36FAJXVWKW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GC36FAJXVWKWSIX3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GC36FAJX","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:96fb429981d627baf2ac77b226fde6b0b949aff9f8cd45a9078683513ecba75f","target":"graph","created_at":"2026-05-17T23:46:40Z","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 reinforcement learning (RL) using self-game-play has shown remarkable performance on several board games (e.g., Chess and Go) as well as video games (e.g., Atari games and Dota2). It is plausible to consider that RL, starting from zero knowledge, might be able to gradually approximate a winning strategy after a certain amount of training. In this paper, we explore neural Monte-Carlo-Tree-Search (neural MCTS), an RL algorithm which has been applied successfully by DeepMind to play Go and Chess at a super-human level. We try to leverage the computational power of neural MCTS t","authors_text":"Karl Lieberherr, Ruiyang Xu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-08T21:38:33Z","title":"Learning Self-Game-Play Agents for Combinatorial Optimization Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03674","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:c86e4ed6db06b98c7a02f4efc8382d26f43c59f79cba6debb5ecd6acca01e4ac","target":"record","created_at":"2026-05-17T23:46:40Z","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":"8b9663365d1867daa36a42087744a5cc5011391cdf9df6d113d987e46208d5b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-08T21:38:33Z","title_canon_sha256":"31db15f9f138ca051ae4bf58c18d150cfb8dae4d1743d6c964d656a8d711e735"},"schema_version":"1.0","source":{"id":"1903.03674","kind":"arxiv","version":2}},"canonical_sha256":"30b7e28137ad956922fb6f4581e634832f7cc2451be974d93def8ccca894be3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b7e28137ad956922fb6f4581e634832f7cc2451be974d93def8ccca894be3c","first_computed_at":"2026-05-17T23:46:40.971835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:40.971835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aVWRYdvE6NRd/eQrm2/cFrSRH4U+2cd7th80Whd4ubJNDaG+QqgARDeNYVQhrW0AiOg/CYdvXZ1qlmNZZEEEBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:40.972399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03674","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c86e4ed6db06b98c7a02f4efc8382d26f43c59f79cba6debb5ecd6acca01e4ac","sha256:96fb429981d627baf2ac77b226fde6b0b949aff9f8cd45a9078683513ecba75f"],"state_sha256":"dcd6c47f15aba80eb91a545487d3005189a5f204fdf61dda19f815b92b1fe7f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3LVX2PIIN5mAGw4JJY8FN60zEkdMxmbp4zQqms5DcIddaV+IjmfIP/11sOlLmX4wnHe1KvWz9Onl0Aah+NOdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T20:29:22.574411Z","bundle_sha256":"6a1c950c695ce1c29331f6e7694dcdea32bda26a2fe2483f9f82aa9d024543d3"}}