{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KHVLWZ7X56XLH2IWI4WBAU6MMX","short_pith_number":"pith:KHVLWZ7X","canonical_record":{"source":{"id":"1805.10755","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5","abstract_canon_sha256":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734"},"schema_version":"1.0"},"canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","source":{"kind":"arxiv","id":"1805.10755","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10755","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10755v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10755","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"KHVLWZ7X56XL","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KHVLWZ7X56XLH2IW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KHVLWZ7X","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KHVLWZ7X56XLH2IWI4WBAU6MMX","target":"record","payload":{"canonical_record":{"source":{"id":"1805.10755","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5","abstract_canon_sha256":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734"},"schema_version":"1.0"},"canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.631793Z","signature_b64":"EJlSKHvP6+rSXEIOI6jGtYFaPSju1Rjb+QM+FHGsU+xWooyegzGWThl++ZsF7LnA3WZaGB+F/hyc9PQc1DVKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","last_reissued_at":"2026-05-17T23:49:17.631285Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.631285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.10755","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":"2026-05-17T23:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qarxWXICpaVrqiAralnb53gvJdBlT1+WGamjDHwcMNwqo/qUqS5Hhh7hGF7iKpgSF09SIM+A949P6+JxmRoJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T03:45:46.224715Z"},"content_sha256":"87c2924e197c15032be8b0b02587fdd45af338e1a77bbdd85aa0668522687791","schema_version":"1.0","event_id":"sha256:87c2924e197c15032be8b0b02587fdd45af338e1a77bbdd85aa0668522687791"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KHVLWZ7X56XLH2IWI4WBAU6MMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual Policy Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","submitted_at":"2018-05-28T03:41:56Z","abstract_excerpt":"Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e.g., ExIt from [2], AlphaGo-Zero from [27]). This new family of algorithms maintains, and alternately optimizes, two policies: a fast, reactive policy (e.g., a deep neural network) deployed at test time, and a slow, non-reactive policy (e.g., Tree Search), that can plan multiple steps ahead. The reactive policy is updated under supervision from the non-reactive policy, while the non-reactive policy is improved with guidance from the reactive policy. In this work we stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10755","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":"2026-05-17T23:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XDJAt4rDxlNxMQsEAxzthNfJ6iixt0SVf//D0skBOgbMUgnO+hct9NexLdC00pFhU3uWEa1xk2lVQC+48DJrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T03:45:46.225397Z"},"content_sha256":"5fdd50c2ed33315e428470a116e64daa93650e9d69910d9956625fee371fb5dc","schema_version":"1.0","event_id":"sha256:5fdd50c2ed33315e428470a116e64daa93650e9d69910d9956625fee371fb5dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/bundle.json","state_url":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/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":"2026-05-24T03:45:46Z","links":{"resolver":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX","bundle":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/bundle.json","state":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KHVLWZ7X56XLH2IWI4WBAU6MMX","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":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5"},"schema_version":"1.0","source":{"id":"1805.10755","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10755","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10755v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10755","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"KHVLWZ7X56XL","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KHVLWZ7X56XLH2IW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KHVLWZ7X","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:5fdd50c2ed33315e428470a116e64daa93650e9d69910d9956625fee371fb5dc","target":"graph","created_at":"2026-05-17T23:49:17Z","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":"Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e.g., ExIt from [2], AlphaGo-Zero from [27]). This new family of algorithms maintains, and alternately optimizes, two policies: a fast, reactive policy (e.g., a deep neural network) deployed at test time, and a slow, non-reactive policy (e.g., Tree Search), that can plan multiple steps ahead. The reactive policy is updated under supervision from the non-reactive policy, while the non-reactive policy is improved with guidance from the reactive policy. In this work we stud","authors_text":"Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","title":"Dual Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10755","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":"sha256:87c2924e197c15032be8b0b02587fdd45af338e1a77bbdd85aa0668522687791","target":"record","created_at":"2026-05-17T23:49:17Z","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":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5"},"schema_version":"1.0","source":{"id":"1805.10755","kind":"arxiv","version":2}},"canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","first_computed_at":"2026-05-17T23:49:17.631285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:17.631285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EJlSKHvP6+rSXEIOI6jGtYFaPSju1Rjb+QM+FHGsU+xWooyegzGWThl++ZsF7LnA3WZaGB+F/hyc9PQc1DVKCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:17.631793Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10755","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87c2924e197c15032be8b0b02587fdd45af338e1a77bbdd85aa0668522687791","sha256:5fdd50c2ed33315e428470a116e64daa93650e9d69910d9956625fee371fb5dc"],"state_sha256":"6a31724d89daa1adad4d2a76bd96a0256c8cdef7ad749af6c798906b48af3bf5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSNJpdxjyjTBkjQbt0TRmIRtwmUvekqUB85nlgFhwjYVssD0HI3mlTjigexcEwQao5ZH7dTsqXCIawKfRVQiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T03:45:46.229014Z","bundle_sha256":"f8301400ed11b397611aba5cf8eb02f63803fadf1626e2cc8b71a682bd66e912"}}