{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UMCPILPIV7C6YGIPLOMT4J6KNJ","short_pith_number":"pith:UMCPILPI","canonical_record":{"source":{"id":"1812.02341","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T04:29:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd17f2b71ba90f9eff42b9b643a6a215a34e84a6f7b80b92f2baed0dc2696c30","abstract_canon_sha256":"f311d30e970d86ad6dbb9288ee7b2eb00743a73d5ee35835a8b6e5d80a4393a9"},"schema_version":"1.0"},"canonical_sha256":"a304f42de8afc5ec190f5b993e27ca6a70e911828199f3e947f869b41bc49a2d","source":{"kind":"arxiv","id":"1812.02341","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02341","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02341v3","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02341","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"UMCPILPIV7C6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UMCPILPIV7C6YGIP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UMCPILPI","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UMCPILPIV7C6YGIPLOMT4J6KNJ","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02341","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T04:29:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd17f2b71ba90f9eff42b9b643a6a215a34e84a6f7b80b92f2baed0dc2696c30","abstract_canon_sha256":"f311d30e970d86ad6dbb9288ee7b2eb00743a73d5ee35835a8b6e5d80a4393a9"},"schema_version":"1.0"},"canonical_sha256":"a304f42de8afc5ec190f5b993e27ca6a70e911828199f3e947f869b41bc49a2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:41.391072Z","signature_b64":"6+N7/MdmTH3sCYn6W6uXuLa0tMatOoAlfX/ALg4hRIGkfLjoteFibmhPrSTDQAGdvjs7PnrxkL8CU51LdInCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a304f42de8afc5ec190f5b993e27ca6a70e911828199f3e947f869b41bc49a2d","last_reissued_at":"2026-05-17T23:40:41.390444Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:41.390444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02341","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":"2026-05-17T23:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLO881LBWA/9GCxu5yM4pG9wztjDotQ/se0bKzitOdnnHOP6ELl0pzgPpfkE5yfA9FMEW9DNL4+4G/d7zRhzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:29:33.867738Z"},"content_sha256":"a369daaa20aa89bbe84e8444a021cd94d8f0802a806b937bb064681adcbe13a0","schema_version":"1.0","event_id":"sha256:a369daaa20aa89bbe84e8444a021cd94d8f0802a806b937bb064681adcbe13a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UMCPILPIV7C6YGIPLOMT4J6KNJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Generalization in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris Hesse, John Schulman, Karl Cobbe, Oleg Klimov, Taehoon Kim","submitted_at":"2018-12-06T04:29:29Z","abstract_excerpt":"In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02341","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":""},"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":"2026-05-17T23:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRHLgDkATtyj4uhlj6zHnQM9B4lx25y1/NBsNxrnN4tQKibocjcCVqFb351Gzy2XUZ4to7FQhtTNzdZQoEsfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:29:33.868365Z"},"content_sha256":"c50d268c621f782dfde5fd789b3663924abf5723feb657b09a98ea87cf5b7720","schema_version":"1.0","event_id":"sha256:c50d268c621f782dfde5fd789b3663924abf5723feb657b09a98ea87cf5b7720"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ/bundle.json","state_url":"https://pith.science/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ/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":"2026-05-21T17:29:33Z","links":{"resolver":"https://pith.science/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ","bundle":"https://pith.science/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ/bundle.json","state":"https://pith.science/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UMCPILPIV7C6YGIPLOMT4J6KNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UMCPILPIV7C6YGIPLOMT4J6KNJ","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":"f311d30e970d86ad6dbb9288ee7b2eb00743a73d5ee35835a8b6e5d80a4393a9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T04:29:29Z","title_canon_sha256":"bd17f2b71ba90f9eff42b9b643a6a215a34e84a6f7b80b92f2baed0dc2696c30"},"schema_version":"1.0","source":{"id":"1812.02341","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02341","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02341v3","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02341","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"UMCPILPIV7C6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UMCPILPIV7C6YGIP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UMCPILPI","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:c50d268c621f782dfde5fd789b3663924abf5723feb657b09a98ea87cf5b7720","target":"graph","created_at":"2026-05-17T23:40:41Z","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":"In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We th","authors_text":"Chris Hesse, John Schulman, Karl Cobbe, Oleg Klimov, Taehoon Kim","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T04:29:29Z","title":"Quantifying Generalization in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02341","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:a369daaa20aa89bbe84e8444a021cd94d8f0802a806b937bb064681adcbe13a0","target":"record","created_at":"2026-05-17T23:40:41Z","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":"f311d30e970d86ad6dbb9288ee7b2eb00743a73d5ee35835a8b6e5d80a4393a9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T04:29:29Z","title_canon_sha256":"bd17f2b71ba90f9eff42b9b643a6a215a34e84a6f7b80b92f2baed0dc2696c30"},"schema_version":"1.0","source":{"id":"1812.02341","kind":"arxiv","version":3}},"canonical_sha256":"a304f42de8afc5ec190f5b993e27ca6a70e911828199f3e947f869b41bc49a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a304f42de8afc5ec190f5b993e27ca6a70e911828199f3e947f869b41bc49a2d","first_computed_at":"2026-05-17T23:40:41.390444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:41.390444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6+N7/MdmTH3sCYn6W6uXuLa0tMatOoAlfX/ALg4hRIGkfLjoteFibmhPrSTDQAGdvjs7PnrxkL8CU51LdInCBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:41.391072Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02341","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a369daaa20aa89bbe84e8444a021cd94d8f0802a806b937bb064681adcbe13a0","sha256:c50d268c621f782dfde5fd789b3663924abf5723feb657b09a98ea87cf5b7720"],"state_sha256":"4317b9b9756094c5d74c2694d0265db7592e2753305462b7153e8c896e4df162"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4yfyv9nouJwHx/hXoMxpEYZImmOMZH7WFjE49XiTDdj3kJ40aFt1wAW8NYfqfMdWzvuCauTo3XRdCHh1PBhGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T17:29:33.870960Z","bundle_sha256":"e691d7bc27ea9d618d91bf14341d8a023b5b2affc52d4c10148401e8e3041d77"}}