{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2O6A2VSPL7C4HYBEG42FGZU5A5","short_pith_number":"pith:2O6A2VSP","canonical_record":{"source":{"id":"1806.05780","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T01:35:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"77f7c826bb202f6f261c8273f64710410585168cb2b1e87c352e16e77deb71d0","abstract_canon_sha256":"b970cdd0b9e4c500babdf63ac948afd16c79c213b7789b3987bcca71c1744415"},"schema_version":"1.0"},"canonical_sha256":"d3bc0d564f5fc5c3e024373453669d077ab3b26cfbeb78c723cd67ff22e7bd02","source":{"kind":"arxiv","id":"1806.05780","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05780","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05780v4","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05780","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"2O6A2VSPL7C4","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"2O6A2VSPL7C4HYBE","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"2O6A2VSP","created_at":"2026-07-05T00:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2O6A2VSPL7C4HYBEG42FGZU5A5","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05780","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T01:35:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"77f7c826bb202f6f261c8273f64710410585168cb2b1e87c352e16e77deb71d0","abstract_canon_sha256":"b970cdd0b9e4c500babdf63ac948afd16c79c213b7789b3987bcca71c1744415"},"schema_version":"1.0"},"canonical_sha256":"d3bc0d564f5fc5c3e024373453669d077ab3b26cfbeb78c723cd67ff22e7bd02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:23.520999Z","signature_b64":"VxCe0oeAVH6Egy8S99J8Zt+KNLpr02h7giq6Kzqa/tyhlRf/PRKEWc+7+OfB2OjKgRB1zEn2fR22puvfAFAZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3bc0d564f5fc5c3e024373453669d077ab3b26cfbeb78c723cd67ff22e7bd02","last_reissued_at":"2026-07-05T00:02:23.520573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:23.520573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05780","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":"2026-07-05T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8VAUpBhcW5VxLkyYO6uXPHeEfsi/bZqDqe2RpnYjkS6EugRSxanwCnUYQMGYQupw9UJxwpT6PxaKq+POF1m6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:44:43.801165Z"},"content_sha256":"4157c8e458cdb3e81ebcdb0428ea9d928902fe23afd8dbdc36aabde7c90d3885","schema_version":"1.0","event_id":"sha256:4157c8e458cdb3e81ebcdb0428ea9d928902fe23afd8dbdc36aabde7c90d3885"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2O6A2VSPL7C4HYBEG42FGZU5A5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Surprising Negative Results for Generative Adversarial Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Brandon Yang, Kamyar Azizzadenesheli, Weitang Liu, Zachary C Lipton","submitted_at":"2018-06-15T01:35:03Z","abstract_excerpt":"While many recent advances in deep reinforcement learning (RL) rely on model-free methods, model-based approaches remain an alluring prospect for their potential to exploit unsupervised data to learn environment model. In this work, we provide an extensive study on the design of deep generative models for RL environments and propose a sample efficient and robust method to learn the model of Atari environments. We deploy this model and propose generative adversarial tree search (GATS) a deep RL algorithm that learns the environment model and implements Monte Carlo tree search (MCTS) on the lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05780","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/1806.05780/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":"2026-07-05T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1hCb0Tesu3oEOUMPNnUmHnzq2yv+BBsapcHALxqqloOff+ILh0zkq5TBWVVLBG7gH0xWbxsREWnOJ+sRPpjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:44:43.802935Z"},"content_sha256":"e76b9edc9cbdb228241ae589138e58204a9c03a3d570876bea95e864d3a94498","schema_version":"1.0","event_id":"sha256:e76b9edc9cbdb228241ae589138e58204a9c03a3d570876bea95e864d3a94498"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2O6A2VSPL7C4HYBEG42FGZU5A5/bundle.json","state_url":"https://pith.science/pith/2O6A2VSPL7C4HYBEG42FGZU5A5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2O6A2VSPL7C4HYBEG42FGZU5A5/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":"2026-08-13T04:44:43Z","links":{"resolver":"https://pith.science/pith/2O6A2VSPL7C4HYBEG42FGZU5A5","bundle":"https://pith.science/pith/2O6A2VSPL7C4HYBEG42FGZU5A5/bundle.json","state":"https://pith.science/pith/2O6A2VSPL7C4HYBEG42FGZU5A5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2O6A2VSPL7C4HYBEG42FGZU5A5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2O6A2VSPL7C4HYBEG42FGZU5A5","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":"b970cdd0b9e4c500babdf63ac948afd16c79c213b7789b3987bcca71c1744415","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T01:35:03Z","title_canon_sha256":"77f7c826bb202f6f261c8273f64710410585168cb2b1e87c352e16e77deb71d0"},"schema_version":"1.0","source":{"id":"1806.05780","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05780","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05780v4","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05780","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"2O6A2VSPL7C4","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"2O6A2VSPL7C4HYBE","created_at":"2026-07-05T00:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"2O6A2VSP","created_at":"2026-07-05T00:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:e76b9edc9cbdb228241ae589138e58204a9c03a3d570876bea95e864d3a94498","target":"graph","created_at":"2026-07-05T00:02:23Z","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/1806.05780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While many recent advances in deep reinforcement learning (RL) rely on model-free methods, model-based approaches remain an alluring prospect for their potential to exploit unsupervised data to learn environment model. In this work, we provide an extensive study on the design of deep generative models for RL environments and propose a sample efficient and robust method to learn the model of Atari environments. We deploy this model and propose generative adversarial tree search (GATS) a deep RL algorithm that learns the environment model and implements Monte Carlo tree search (MCTS) on the lear","authors_text":"Animashree Anandkumar, Brandon Yang, Kamyar Azizzadenesheli, Weitang Liu, Zachary C Lipton","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T01:35:03Z","title":"Surprising Negative Results for Generative Adversarial Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05780","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":"sha256:4157c8e458cdb3e81ebcdb0428ea9d928902fe23afd8dbdc36aabde7c90d3885","target":"record","created_at":"2026-07-05T00:02:23Z","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":"b970cdd0b9e4c500babdf63ac948afd16c79c213b7789b3987bcca71c1744415","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T01:35:03Z","title_canon_sha256":"77f7c826bb202f6f261c8273f64710410585168cb2b1e87c352e16e77deb71d0"},"schema_version":"1.0","source":{"id":"1806.05780","kind":"arxiv","version":4}},"canonical_sha256":"d3bc0d564f5fc5c3e024373453669d077ab3b26cfbeb78c723cd67ff22e7bd02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3bc0d564f5fc5c3e024373453669d077ab3b26cfbeb78c723cd67ff22e7bd02","first_computed_at":"2026-07-05T00:02:23.520573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:23.520573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VxCe0oeAVH6Egy8S99J8Zt+KNLpr02h7giq6Kzqa/tyhlRf/PRKEWc+7+OfB2OjKgRB1zEn2fR22puvfAFAZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:23.520999Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05780","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4157c8e458cdb3e81ebcdb0428ea9d928902fe23afd8dbdc36aabde7c90d3885","sha256:e76b9edc9cbdb228241ae589138e58204a9c03a3d570876bea95e864d3a94498"],"state_sha256":"cff8f67d48e147a8544a2972b9c1ed30bbbd5cc2a40e92c832c2aa852f41daa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1RhwJpyVnI6dIgunot9DeLlBySPqKqNyDV/JOTRwSsMRpuI1UUz+T3UjbH7U+nC551o/JnowzqDMG5ihSHmWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:44:43.830950Z","bundle_sha256":"89f0cf4f6433d1be9b1f1b6929fa13b07cdfd2eb5b17008db191e51588e0c453"}}