{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5OSDD2G63JXNDXRQYVIGNYW3X6","short_pith_number":"pith:5OSDD2G6","canonical_record":{"source":{"id":"1908.04436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-12T23:27:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cf73d47bbf7841b8442e8a2828261e062d0b4047e6d036446bff4c85a2c489fd","abstract_canon_sha256":"94fb70a101d83a08644b0276f7f885c6e1f7f94594f8bf9c69f184f1ede7016c"},"schema_version":"1.0"},"canonical_sha256":"eba431e8deda6ed1de30c55066e2dbbf8f38a5d96895f1c8294062cd969a2a95","source":{"kind":"arxiv","id":"1908.04436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04436","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04436v1","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04436","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"pith_short_12","alias_value":"5OSDD2G63JXN","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"pith_short_16","alias_value":"5OSDD2G63JXNDXRQ","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"pith_short_8","alias_value":"5OSDD2G6","created_at":"2026-07-04T23:55:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5OSDD2G63JXNDXRQYVIGNYW3X6","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-12T23:27:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cf73d47bbf7841b8442e8a2828261e062d0b4047e6d036446bff4c85a2c489fd","abstract_canon_sha256":"94fb70a101d83a08644b0276f7f885c6e1f7f94594f8bf9c69f184f1ede7016c"},"schema_version":"1.0"},"canonical_sha256":"eba431e8deda6ed1de30c55066e2dbbf8f38a5d96895f1c8294062cd969a2a95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:55:13.747028Z","signature_b64":"jvRn+o6e/5mLSPsdF5D/bmOqhKy3DgNRko8c1u7YdIJDKiVj/Th4YU2o+yZdMzr2/LP1sV0rEPf/8kMtUf8gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba431e8deda6ed1de30c55066e2dbbf8f38a5d96895f1c8294062cd969a2a95","last_reissued_at":"2026-07-04T23:55:13.746697Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:55:13.746697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04436","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:55:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZkGvzovYUkN37pS+nmlV2pHL/tqNt/DVoXkbFBh4f6UbzLmYqRzG3EV/mxaF3HqczXKxMhxaffRO70+QY3h/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:09:44.484273Z"},"content_sha256":"5121b31ac5032cbeb513d8c46145f753ae77edd50016f8fee4c4bc2ff5cc041d","schema_version":"1.0","event_id":"sha256:5121b31ac5032cbeb513d8c46145f753ae77edd50016f8fee4c4bc2ff5cc041d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5OSDD2G63JXNDXRQYVIGNYW3X6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Khalifa, Christoph Salge, Damien Anderson, Julian Togelius, Matthew Stephenson, Philip Bontrager","submitted_at":"2019-08-12T23:27:26Z","abstract_excerpt":"Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to game-playing agents. These games are implemented in the General Video Game AI framework, which allows us to compare the behavior of reinforcement learning-based agents with planning agents based on tree search. We find that several of these games reliably deceive deep reinforceme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04436","kind":"arxiv","version":1},"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/1908.04436/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":"2026-07-04T23:55:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJb/oNB6yc1za97RjpAHwmyPDXhNwUNYNoAArfbVsf1kg4HW78qtxlS4oMBFIm+iyR8ZHGhaa29Rcj5YcOrNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:09:44.485289Z"},"content_sha256":"c2eb401795504ee08410830cff9b17aace9addd410b55f5ca6dc36e6211233e7","schema_version":"1.0","event_id":"sha256:c2eb401795504ee08410830cff9b17aace9addd410b55f5ca6dc36e6211233e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OSDD2G63JXNDXRQYVIGNYW3X6/bundle.json","state_url":"https://pith.science/pith/5OSDD2G63JXNDXRQYVIGNYW3X6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OSDD2G63JXNDXRQYVIGNYW3X6/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":"2026-08-16T07:09:44Z","links":{"resolver":"https://pith.science/pith/5OSDD2G63JXNDXRQYVIGNYW3X6","bundle":"https://pith.science/pith/5OSDD2G63JXNDXRQYVIGNYW3X6/bundle.json","state":"https://pith.science/pith/5OSDD2G63JXNDXRQYVIGNYW3X6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OSDD2G63JXNDXRQYVIGNYW3X6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5OSDD2G63JXNDXRQYVIGNYW3X6","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":"94fb70a101d83a08644b0276f7f885c6e1f7f94594f8bf9c69f184f1ede7016c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-12T23:27:26Z","title_canon_sha256":"cf73d47bbf7841b8442e8a2828261e062d0b4047e6d036446bff4c85a2c489fd"},"schema_version":"1.0","source":{"id":"1908.04436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04436","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04436v1","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04436","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"pith_short_12","alias_value":"5OSDD2G63JXN","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"pith_short_16","alias_value":"5OSDD2G63JXNDXRQ","created_at":"2026-07-04T23:55:13Z"},{"alias_kind":"pith_short_8","alias_value":"5OSDD2G6","created_at":"2026-07-04T23:55:13Z"}],"graph_snapshots":[{"event_id":"sha256:c2eb401795504ee08410830cff9b17aace9addd410b55f5ca6dc36e6211233e7","target":"graph","created_at":"2026-07-04T23:55:13Z","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/1908.04436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to game-playing agents. These games are implemented in the General Video Game AI framework, which allows us to compare the behavior of reinforcement learning-based agents with planning agents based on tree search. We find that several of these games reliably deceive deep reinforceme","authors_text":"Ahmed Khalifa, Christoph Salge, Damien Anderson, Julian Togelius, Matthew Stephenson, Philip Bontrager","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-12T23:27:26Z","title":"Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04436","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":"sha256:5121b31ac5032cbeb513d8c46145f753ae77edd50016f8fee4c4bc2ff5cc041d","target":"record","created_at":"2026-07-04T23:55:13Z","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":"94fb70a101d83a08644b0276f7f885c6e1f7f94594f8bf9c69f184f1ede7016c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-12T23:27:26Z","title_canon_sha256":"cf73d47bbf7841b8442e8a2828261e062d0b4047e6d036446bff4c85a2c489fd"},"schema_version":"1.0","source":{"id":"1908.04436","kind":"arxiv","version":1}},"canonical_sha256":"eba431e8deda6ed1de30c55066e2dbbf8f38a5d96895f1c8294062cd969a2a95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eba431e8deda6ed1de30c55066e2dbbf8f38a5d96895f1c8294062cd969a2a95","first_computed_at":"2026-07-04T23:55:13.746697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:55:13.746697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jvRn+o6e/5mLSPsdF5D/bmOqhKy3DgNRko8c1u7YdIJDKiVj/Th4YU2o+yZdMzr2/LP1sV0rEPf/8kMtUf8gBA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:55:13.747028Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5121b31ac5032cbeb513d8c46145f753ae77edd50016f8fee4c4bc2ff5cc041d","sha256:c2eb401795504ee08410830cff9b17aace9addd410b55f5ca6dc36e6211233e7"],"state_sha256":"9d5a89f7840b7d6e2baf0a457f72289a59f2536d36883c2288ca77a6ef41ba84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wmSG40BN917xsZ5vh5TFgDFEJUf0HTpS23UbTuJDtPJRLgl8Z+4iLbwgPCRN0BZGahAnACUS1+efZ0TsQumcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:09:44.496474Z","bundle_sha256":"ec9a940ed5781046d7375a5a1c524c6c5f0b076a8878130f661b8e63807d9c7e"}}