{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZVBMYROB2TA3SIXAMLJDGJ6BXI","short_pith_number":"pith:ZVBMYROB","canonical_record":{"source":{"id":"1810.00123","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T00:52:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e722447df5599d1c0340059f478306113b029bd51559a8bf28472e5d11b9fef6","abstract_canon_sha256":"447ea4407ec498944a9267428fe0ede408923e43ebf09840ec079c6f6ef3a175"},"schema_version":"1.0"},"canonical_sha256":"cd42cc45c1d4c1b922e062d23327c1ba2ff286ecc747b629e784c7240cd98b1d","source":{"kind":"arxiv","id":"1810.00123","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00123","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00123v3","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00123","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZVBMYROB2TA3","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZVBMYROB2TA3SIXA","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZVBMYROB","created_at":"2026-07-05T00:34:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZVBMYROB2TA3SIXAMLJDGJ6BXI","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00123","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T00:52:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e722447df5599d1c0340059f478306113b029bd51559a8bf28472e5d11b9fef6","abstract_canon_sha256":"447ea4407ec498944a9267428fe0ede408923e43ebf09840ec079c6f6ef3a175"},"schema_version":"1.0"},"canonical_sha256":"cd42cc45c1d4c1b922e062d23327c1ba2ff286ecc747b629e784c7240cd98b1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:34:13.390600Z","signature_b64":"LCC5Xkjy6SIj9hqmfYeLESPO7YxkJIyoE1Oqzkmo6KCzbRuCbI7QGrgrYdyeYxmJUTTIpEouhNq9fVygRhOrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd42cc45c1d4c1b922e062d23327c1ba2ff286ecc747b629e784c7240cd98b1d","last_reissued_at":"2026-07-05T00:34:13.390096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:34:13.390096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00123","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UyG/Vv2qfmv2ad4E0GHeAqDCjXbfjsl5pbXuKvIw7KNpSN7IackRlUtEbb2nW0x8rX1xzOi9Sm2IZhomplZaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:49:39.146382Z"},"content_sha256":"8e295134c8a2cb2c4239151d43b7c9d64cc11782e391a313147c83db3a2a4e93","schema_version":"1.0","event_id":"sha256:8e295134c8a2cb2c4239151d43b7c9d64cc11782e391a313147c83db3a2a4e93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZVBMYROB2TA3SIXAMLJDGJ6BXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization and Regularization in DQN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jesse Farebrother, Marlos C. Machado, Michael Bowling","submitted_at":"2018-09-29T00:52:34Z","abstract_excerpt":"Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep reinforcement learning algorithms can struggle to generalize when evaluated in remarkably similar environments. In this paper we propose a protocol to evaluate generalization in reinforcement learning through different modes of Atari 2600 games. With that protocol we assess the generalization capabilities of DQN, one of the most traditional deep reinforcement learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00123","kind":"arxiv","version":3},"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/1810.00123/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":"2026-07-05T00:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mL7KrrYwd3a2/4K4WFspKZKI50ZKrBGAtaT7TG6mNIMHl9VzdQcZB5jUR0AVP4y/ljNBLnvxnMwozbJ5HoMzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:49:39.147323Z"},"content_sha256":"fe745a43e01e26bf5212c3a5f73f5bb063c51ce0784337cac6be7758a0d6e8c1","schema_version":"1.0","event_id":"sha256:fe745a43e01e26bf5212c3a5f73f5bb063c51ce0784337cac6be7758a0d6e8c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI/bundle.json","state_url":"https://pith.science/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI/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":"2026-08-10T11:49:39Z","links":{"resolver":"https://pith.science/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI","bundle":"https://pith.science/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI/bundle.json","state":"https://pith.science/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVBMYROB2TA3SIXAMLJDGJ6BXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZVBMYROB2TA3SIXAMLJDGJ6BXI","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":"447ea4407ec498944a9267428fe0ede408923e43ebf09840ec079c6f6ef3a175","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T00:52:34Z","title_canon_sha256":"e722447df5599d1c0340059f478306113b029bd51559a8bf28472e5d11b9fef6"},"schema_version":"1.0","source":{"id":"1810.00123","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00123","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00123v3","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00123","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZVBMYROB2TA3","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZVBMYROB2TA3SIXA","created_at":"2026-07-05T00:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZVBMYROB","created_at":"2026-07-05T00:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:fe745a43e01e26bf5212c3a5f73f5bb063c51ce0784337cac6be7758a0d6e8c1","target":"graph","created_at":"2026-07-05T00:34:13Z","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/1810.00123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep reinforcement learning algorithms can struggle to generalize when evaluated in remarkably similar environments. In this paper we propose a protocol to evaluate generalization in reinforcement learning through different modes of Atari 2600 games. With that protocol we assess the generalization capabilities of DQN, one of the most traditional deep reinforcement learning","authors_text":"Jesse Farebrother, Marlos C. Machado, Michael Bowling","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T00:52:34Z","title":"Generalization and Regularization in DQN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00123","kind":"arxiv","version":3},"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":"sha256:8e295134c8a2cb2c4239151d43b7c9d64cc11782e391a313147c83db3a2a4e93","target":"record","created_at":"2026-07-05T00:34:13Z","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":"447ea4407ec498944a9267428fe0ede408923e43ebf09840ec079c6f6ef3a175","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T00:52:34Z","title_canon_sha256":"e722447df5599d1c0340059f478306113b029bd51559a8bf28472e5d11b9fef6"},"schema_version":"1.0","source":{"id":"1810.00123","kind":"arxiv","version":3}},"canonical_sha256":"cd42cc45c1d4c1b922e062d23327c1ba2ff286ecc747b629e784c7240cd98b1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd42cc45c1d4c1b922e062d23327c1ba2ff286ecc747b629e784c7240cd98b1d","first_computed_at":"2026-07-05T00:34:13.390096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:34:13.390096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LCC5Xkjy6SIj9hqmfYeLESPO7YxkJIyoE1Oqzkmo6KCzbRuCbI7QGrgrYdyeYxmJUTTIpEouhNq9fVygRhOrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:34:13.390600Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00123","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e295134c8a2cb2c4239151d43b7c9d64cc11782e391a313147c83db3a2a4e93","sha256:fe745a43e01e26bf5212c3a5f73f5bb063c51ce0784337cac6be7758a0d6e8c1"],"state_sha256":"ab42e19e112da146b9922f1db2b6160fae8c58a41221bce7bbfc2f6cdce348ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dd4W90n26AdbhYQ53iq4CuNkPxNnjsrtYTdD5LWlaO0iULH7hBF4AMZ1tihXe1I6FXkfp+OKdvDGTICOUWCBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:49:39.154981Z","bundle_sha256":"90e4e43818998cf6f54b39ac9e950e0ea630bab8dd22342adadaac49a3cde693"}}