{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:BRVJ4DGWOC4WGSDRHZI7SUXOGJ","short_pith_number":"pith:BRVJ4DGW","schema_version":"1.0","canonical_sha256":"0c6a9e0cd670b96348713e51f952ee32404da171c9d63181172bc6404918d34f","source":{"kind":"arxiv","id":"1412.6564","version":2},"attestation_state":"computed","paper":{"title":"Move Evaluation in Go Using Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Aja Huang, Chris J. Maddison, David Silver, Ilya Sutskever","submitted_at":"2014-12-20T00:31:30Z","abstract_excerpt":"The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1412.6564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T00:31:30Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8110504b5bcb2d7d3bd70e7e3798c93b4ef6826aaa90b2369af923b423cdda7b","abstract_canon_sha256":"25ea07e54df5a835d29d1293123c5092077eb31d04928c2122635affa45b83ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:07.966822Z","signature_b64":"UcyPRFfUa/DvKWiRuahwgpLgSyLUOSIS5R+KZX+/JwE6EufSUOZq+QBY8b1lFZhiavn/VoF/1NBEt4zK7vhYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c6a9e0cd670b96348713e51f952ee32404da171c9d63181172bc6404918d34f","last_reissued_at":"2026-05-18T02:19:07.966142Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:07.966142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Move Evaluation in Go Using Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Aja Huang, Chris J. Maddison, David Silver, Ilya Sutskever","submitted_at":"2014-12-20T00:31:30Z","abstract_excerpt":"The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6564","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1412.6564","created_at":"2026-05-18T02:19:07.966267+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6564v2","created_at":"2026-05-18T02:19:07.966267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6564","created_at":"2026-05-18T02:19:07.966267+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRVJ4DGWOC4W","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRVJ4DGWOC4WGSDR","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRVJ4DGW","created_at":"2026-05-18T12:28:22.404517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.04658","citing_title":"Playing Go without Game Tree Search Using Convolutional Neural Networks","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":281,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ","json":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ.json","graph_json":"https://pith.science/api/pith-number/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/graph.json","events_json":"https://pith.science/api/pith-number/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/events.json","paper":"https://pith.science/paper/BRVJ4DGW"},"agent_actions":{"view_html":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ","download_json":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ.json","view_paper":"https://pith.science/paper/BRVJ4DGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6564&json=true","fetch_graph":"https://pith.science/api/pith-number/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/action/storage_attestation","attest_author":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/action/author_attestation","sign_citation":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/action/citation_signature","submit_replication":"https://pith.science/pith/BRVJ4DGWOC4WGSDRHZI7SUXOGJ/action/replication_record"}},"created_at":"2026-05-18T02:19:07.966267+00:00","updated_at":"2026-05-18T02:19:07.966267+00:00"}