{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MVHWZ6DNUGI2JCHTY4JNECLNT6","short_pith_number":"pith:MVHWZ6DN","schema_version":"1.0","canonical_sha256":"654f6cf86da191a488f3c712d2096d9f814c2db59f25b6d38d48e39d0370496d","source":{"kind":"arxiv","id":"1705.08439","version":4},"attestation_state":"computed","paper":{"title":"Thinking Fast and Slow with Deep Learning and Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Barber, Thomas Anthony, Zheng Tian","submitted_at":"2017-05-23T17:48:51Z","abstract_excerpt":"Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks. Planning new policies is performed by tree search, while a deep neural network generalises those plans. Subsequently, tree search is improved by using the neural network policy to guide search, increasing the strength of new plans. In contrast, stan"},"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":"1705.08439","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T17:48:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9125d40d64252a860706aa9f8ededce01d9d9c7e2e679b6e2f3cc0f0d90f19f6","abstract_canon_sha256":"54a8cd4a2feb5ff1b9563f7467d92db4dd2c30018138994d81c6bba319ec1b2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:18.981908Z","signature_b64":"4EHJvzv2tPhKMGi5YI8dvGckRs578QMyoyCgBC++UArjfDX5RinbNyjzBmCOul23cW4KJjnvSp7BMuQVo1SDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654f6cf86da191a488f3c712d2096d9f814c2db59f25b6d38d48e39d0370496d","last_reissued_at":"2026-07-05T09:25:18.981344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:18.981344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thinking Fast and Slow with Deep Learning and Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Barber, Thomas Anthony, Zheng Tian","submitted_at":"2017-05-23T17:48:51Z","abstract_excerpt":"Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks. Planning new policies is performed by tree search, while a deep neural network generalises those plans. Subsequently, tree search is improved by using the neural network policy to guide search, increasing the strength of new plans. In contrast, stan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08439","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1705.08439/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1705.08439","created_at":"2026-07-05T09:25:18.981404+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08439v4","created_at":"2026-07-05T09:25:18.981404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08439","created_at":"2026-07-05T09:25:18.981404+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVHWZ6DNUGI2","created_at":"2026-07-05T09:25:18.981404+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVHWZ6DNUGI2JCHT","created_at":"2026-07-05T09:25:18.981404+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVHWZ6DN","created_at":"2026-07-05T09:25:18.981404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22948","citing_title":"ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":222,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6","json":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6.json","graph_json":"https://pith.science/api/pith-number/MVHWZ6DNUGI2JCHTY4JNECLNT6/graph.json","events_json":"https://pith.science/api/pith-number/MVHWZ6DNUGI2JCHTY4JNECLNT6/events.json","paper":"https://pith.science/paper/MVHWZ6DN"},"agent_actions":{"view_html":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6","download_json":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6.json","view_paper":"https://pith.science/paper/MVHWZ6DN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08439&json=true","fetch_graph":"https://pith.science/api/pith-number/MVHWZ6DNUGI2JCHTY4JNECLNT6/graph.json","fetch_events":"https://pith.science/api/pith-number/MVHWZ6DNUGI2JCHTY4JNECLNT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/action/storage_attestation","attest_author":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/action/author_attestation","sign_citation":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/action/citation_signature","submit_replication":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/action/replication_record"}},"created_at":"2026-07-05T09:25:18.981404+00:00","updated_at":"2026-07-05T09:25:18.981404+00:00"}