{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MVHWZ6DNUGI2JCHTY4JNECLNT6","short_pith_number":"pith:MVHWZ6DN","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"},"canonical_sha256":"654f6cf86da191a488f3c712d2096d9f814c2db59f25b6d38d48e39d0370496d","source":{"kind":"arxiv","id":"1705.08439","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08439","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08439v4","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08439","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"MVHWZ6DNUGI2","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"MVHWZ6DNUGI2JCHT","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"MVHWZ6DN","created_at":"2026-07-05T09:25:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MVHWZ6DNUGI2JCHTY4JNECLNT6","target":"record","payload":{"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"},"canonical_sha256":"654f6cf86da191a488f3c712d2096d9f814c2db59f25b6d38d48e39d0370496d","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"},"source_kind":"arxiv","source_id":"1705.08439","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:25:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fw7tyow/1F7PYiUftZLTbck+VOYx44s0QBAsHmKfcMIiHAfJfWWLFFBKp5Y7XnMA478AecAuP71TDx+QKMNEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:01:55.433672Z"},"content_sha256":"45d84b0b795d4330809f1051db73b721afbe8e338be4abc0acc94f3432283daa","schema_version":"1.0","event_id":"sha256:45d84b0b795d4330809f1051db73b721afbe8e338be4abc0acc94f3432283daa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MVHWZ6DNUGI2JCHTY4JNECLNT6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:25:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0OG3SkrxXyhM1SLIHpaywoPa8fnmKsxUsquPb8o/a7tc+Pryl6WKZIdfAkkYhPSmveyAvpo29FTkY64wNhykBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:01:55.434743Z"},"content_sha256":"272d757f19d6749aa8c5ae32e5daee20b8dc4299b4b6e79c643e78c8455809e5","schema_version":"1.0","event_id":"sha256:272d757f19d6749aa8c5ae32e5daee20b8dc4299b4b6e79c643e78c8455809e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/bundle.json","state_url":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/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":"2026-08-08T22:01:55Z","links":{"resolver":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6","bundle":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/bundle.json","state":"https://pith.science/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVHWZ6DNUGI2JCHTY4JNECLNT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MVHWZ6DNUGI2JCHTY4JNECLNT6","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":"54a8cd4a2feb5ff1b9563f7467d92db4dd2c30018138994d81c6bba319ec1b2e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T17:48:51Z","title_canon_sha256":"9125d40d64252a860706aa9f8ededce01d9d9c7e2e679b6e2f3cc0f0d90f19f6"},"schema_version":"1.0","source":{"id":"1705.08439","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08439","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08439v4","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08439","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"MVHWZ6DNUGI2","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"MVHWZ6DNUGI2JCHT","created_at":"2026-07-05T09:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"MVHWZ6DN","created_at":"2026-07-05T09:25:18Z"}],"graph_snapshots":[{"event_id":"sha256:272d757f19d6749aa8c5ae32e5daee20b8dc4299b4b6e79c643e78c8455809e5","target":"graph","created_at":"2026-07-05T09:25:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1705.08439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Barber, Thomas Anthony, Zheng Tian","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T17:48:51Z","title":"Thinking Fast and Slow with Deep Learning and Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08439","kind":"arxiv","version":4},"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":"sha256:45d84b0b795d4330809f1051db73b721afbe8e338be4abc0acc94f3432283daa","target":"record","created_at":"2026-07-05T09:25:18Z","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":"54a8cd4a2feb5ff1b9563f7467d92db4dd2c30018138994d81c6bba319ec1b2e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-23T17:48:51Z","title_canon_sha256":"9125d40d64252a860706aa9f8ededce01d9d9c7e2e679b6e2f3cc0f0d90f19f6"},"schema_version":"1.0","source":{"id":"1705.08439","kind":"arxiv","version":4}},"canonical_sha256":"654f6cf86da191a488f3c712d2096d9f814c2db59f25b6d38d48e39d0370496d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"654f6cf86da191a488f3c712d2096d9f814c2db59f25b6d38d48e39d0370496d","first_computed_at":"2026-07-05T09:25:18.981344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:18.981344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4EHJvzv2tPhKMGi5YI8dvGckRs578QMyoyCgBC++UArjfDX5RinbNyjzBmCOul23cW4KJjnvSp7BMuQVo1SDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:18.981908Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08439","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45d84b0b795d4330809f1051db73b721afbe8e338be4abc0acc94f3432283daa","sha256:272d757f19d6749aa8c5ae32e5daee20b8dc4299b4b6e79c643e78c8455809e5"],"state_sha256":"5e1e752394285f96d2caa6d5cbe12db8d730d87c9e8d62f0fafa6285df5434a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CTfAvx5FdxKCtdq8VQyyqwMBwN9LbVt27Qd1WhWy9IzQrzB0tK26yrC7HomsDqhqwajlgQHS6sWv3pSJ2E+iCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:01:55.440089Z","bundle_sha256":"5a7451bcb85b246eae6bd8e3c61b8e40488e749c35977d511930947e574ca6c2"}}