{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:TVCPIQMVU2LSUDF73FABYO2BKD","short_pith_number":"pith:TVCPIQMV","schema_version":"1.0","canonical_sha256":"9d44f44195a6972a0cbfd9401c3b4150fd544839eb7f5da8e54e557d07139bcd","source":{"kind":"arxiv","id":"1604.07097","version":2},"attestation_state":"computed","paper":{"title":"Neurohex: A Deep Q-learning Hex Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gautham Vasan, Kenny Young, Ryan Hayward","submitted_at":"2016-04-24T23:56:37Z","abstract_excerpt":"DeepMind's recent spectacular success in using deep convolutional neural nets and machine learning to build superhuman level agents --- e.g. for Atari games via deep Q-learning and for the game of Go via Reinforcement Learning --- raises many questions, including to what extent these methods will succeed in other domains. In this paper we consider DQL for the game of Hex: after supervised initialization, we use selfplay to train NeuroHex, an 11-layer CNN that plays Hex on the 13x13 board. Hex is the classic two-player alternate-turn stone placement game played on a rhombus of hexagonal cells 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":"1604.07097","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-24T23:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"c1e9c68db31d48785a9dfaea7a3ac9e4412e2064428f4ee02c292083a85918a8","abstract_canon_sha256":"ff86ccd818387fb67ed63bfb3edbd7ea6f0f625096c8aad49ee0c201fe2c93a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:19.928163Z","signature_b64":"B8zY4l1jbWiKcE7oDy08EHTlNmU2WoMhHKrAPNNinoG5D/RcYwR5SK69SmBJPm+osU4JU8IT5Oy4RTusvY42Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d44f44195a6972a0cbfd9401c3b4150fd544839eb7f5da8e54e557d07139bcd","last_reissued_at":"2026-05-18T01:16:19.927518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:19.927518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neurohex: A Deep Q-learning Hex Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gautham Vasan, Kenny Young, Ryan Hayward","submitted_at":"2016-04-24T23:56:37Z","abstract_excerpt":"DeepMind's recent spectacular success in using deep convolutional neural nets and machine learning to build superhuman level agents --- e.g. for Atari games via deep Q-learning and for the game of Go via Reinforcement Learning --- raises many questions, including to what extent these methods will succeed in other domains. In this paper we consider DQL for the game of Hex: after supervised initialization, we use selfplay to train NeuroHex, an 11-layer CNN that plays Hex on the 13x13 board. Hex is the classic two-player alternate-turn stone placement game played on a rhombus of hexagonal cells i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.07097","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":"1604.07097","created_at":"2026-05-18T01:16:19.927648+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.07097v2","created_at":"2026-05-18T01:16:19.927648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.07097","created_at":"2026-05-18T01:16:19.927648+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVCPIQMVU2LS","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVCPIQMVU2LSUDF7","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVCPIQMV","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD","json":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD.json","graph_json":"https://pith.science/api/pith-number/TVCPIQMVU2LSUDF73FABYO2BKD/graph.json","events_json":"https://pith.science/api/pith-number/TVCPIQMVU2LSUDF73FABYO2BKD/events.json","paper":"https://pith.science/paper/TVCPIQMV"},"agent_actions":{"view_html":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD","download_json":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD.json","view_paper":"https://pith.science/paper/TVCPIQMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.07097&json=true","fetch_graph":"https://pith.science/api/pith-number/TVCPIQMVU2LSUDF73FABYO2BKD/graph.json","fetch_events":"https://pith.science/api/pith-number/TVCPIQMVU2LSUDF73FABYO2BKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD/action/storage_attestation","attest_author":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD/action/author_attestation","sign_citation":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD/action/citation_signature","submit_replication":"https://pith.science/pith/TVCPIQMVU2LSUDF73FABYO2BKD/action/replication_record"}},"created_at":"2026-05-18T01:16:19.927648+00:00","updated_at":"2026-05-18T01:16:19.927648+00:00"}