{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:P6YZSD2AZSD6RRAZXMGYNVSUPT","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":"99bd9ce67d0dde0f5da29eb7e97d04fb433e3b31c7e18bb87cace2b1d0efe3cc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-23T18:08:58Z","title_canon_sha256":"34dd85e2eb282b59eccb806f7b5e59dd0b9148abbb815684ce44d8aeb4f870df"},"schema_version":"1.0","source":{"id":"2004.11410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.11410","created_at":"2026-07-05T00:57:53Z"},{"alias_kind":"arxiv_version","alias_value":"2004.11410v1","created_at":"2026-07-05T00:57:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11410","created_at":"2026-07-05T00:57:53Z"},{"alias_kind":"pith_short_12","alias_value":"P6YZSD2AZSD6","created_at":"2026-07-05T00:57:53Z"},{"alias_kind":"pith_short_16","alias_value":"P6YZSD2AZSD6RRAZ","created_at":"2026-07-05T00:57:53Z"},{"alias_kind":"pith_short_8","alias_value":"P6YZSD2A","created_at":"2026-07-05T00:57:53Z"}],"graph_snapshots":[{"event_id":"sha256:f71ff126bbd60d785749d147c1116aa16ff9218a1037dfb9972f0edea056b6f0","target":"graph","created_at":"2026-07-05T00:57:53Z","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/2004.11410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed. We consider alternatives to this assumption for the class of goal-directed Reinforcement Learning (RL) problems. Instead of an environment transition model, we assume an imperfect, goal-directed policy. This low-level policy can be improved by a plan, consisting of an appropriate sequence of sub-goals that guide it from the start to th","authors_text":"Alexander Neitz, Giambattista Parascandolo, Jessica B. Hamrick, John Aslanides, Josh Merel, Lars Buesing, Leonard Hasenclever, Nicolas Heess, Theophane Weber","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-23T18:08:58Z","title":"Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11410","kind":"arxiv","version":1},"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":"sha256:9c8aad7721896deeb7a55fea6d18bf79e9d9115818a3c62aba17baa5a2554377","target":"record","created_at":"2026-07-05T00:57:53Z","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":"99bd9ce67d0dde0f5da29eb7e97d04fb433e3b31c7e18bb87cace2b1d0efe3cc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-23T18:08:58Z","title_canon_sha256":"34dd85e2eb282b59eccb806f7b5e59dd0b9148abbb815684ce44d8aeb4f870df"},"schema_version":"1.0","source":{"id":"2004.11410","kind":"arxiv","version":1}},"canonical_sha256":"7fb1990f40cc87e8c419bb0d86d6547cd4eaf16ea325b8b1af3353502da7f443","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fb1990f40cc87e8c419bb0d86d6547cd4eaf16ea325b8b1af3353502da7f443","first_computed_at":"2026-07-05T00:57:53.826705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:57:53.826705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bEaPS42S2EbqXb2nfE/6gQiVh6EaPAx97Jvpwap84ZxyT4PaDajdnr736o343TrcUGQiKXfoS1UrdOmp9eHFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:57:53.827136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.11410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c8aad7721896deeb7a55fea6d18bf79e9d9115818a3c62aba17baa5a2554377","sha256:f71ff126bbd60d785749d147c1116aa16ff9218a1037dfb9972f0edea056b6f0"],"state_sha256":"0534be57c6206739ef115581b4163078308d919af6eed9b5a22884a876f94945"}