{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HAIILT7SJJQH2OHTBBA6YNXQNJ","short_pith_number":"pith:HAIILT7S","canonical_record":{"source":{"id":"2010.10814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-21T08:12:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a045187f11c33acb16042e4867cdb992c7d2882819b56a0e366635cd557e3956","abstract_canon_sha256":"f4fcfe258cf957afd36e5ae891be0e96aedefb44aee714df206b5eeab28c649b"},"schema_version":"1.0"},"canonical_sha256":"381085cff24a607d38f30841ec36f06a641fc002fa3a5df1acbe77a02b16d9ea","source":{"kind":"arxiv","id":"2010.10814","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10814","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10814v1","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10814","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_12","alias_value":"HAIILT7SJJQH","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_16","alias_value":"HAIILT7SJJQH2OHT","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_8","alias_value":"HAIILT7S","created_at":"2026-07-05T01:44:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HAIILT7SJJQH2OHTBBA6YNXQNJ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.10814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-21T08:12:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a045187f11c33acb16042e4867cdb992c7d2882819b56a0e366635cd557e3956","abstract_canon_sha256":"f4fcfe258cf957afd36e5ae891be0e96aedefb44aee714df206b5eeab28c649b"},"schema_version":"1.0"},"canonical_sha256":"381085cff24a607d38f30841ec36f06a641fc002fa3a5df1acbe77a02b16d9ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:54.777340Z","signature_b64":"io2lsFZgyirO5Sw4bAA120iq9rojWf8yiBEl0LthzAVLN78cA2MavgWZrBWIcfZojaC8/mf74i49BbwyVwhVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"381085cff24a607d38f30841ec36f06a641fc002fa3a5df1acbe77a02b16d9ea","last_reissued_at":"2026-07-05T01:44:54.776916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:54.776916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.10814","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":"2026-07-05T01:44:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"avW+XJbbP7IhM93ZPnK8h9ZoCfcAYUaB5qxJmmoi+zOjWsINLslpQD98K07e0nqgEz4yEhXvQqQPPJlX0ZJrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:58:53.905455Z"},"content_sha256":"1cc2706b6fe4cb18ce72d1ea9594e0cb9e435c36bac2aaadf60d6e5b0141d62d","schema_version":"1.0","event_id":"sha256:1cc2706b6fe4cb18ce72d1ea9594e0cb9e435c36bac2aaadf60d6e5b0141d62d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HAIILT7SJJQH2OHTBBA6YNXQNJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingyi Kang, Jiashi Feng, Jie Shao, Kaixin Wang","submitted_at":"2020-10-21T08:12:03Z","abstract_excerpt":"Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their generalizability, data augmentation approaches (e.g. cutout and random convolution) are previously explored to increase the data diversity. However, we find these approaches only locally perturb the observations regardless of the training environments, showing limited effectiveness on enhancing the data diversity and the generalization performance. In this work, we introduce a simple approach, named mixreg, which tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10814","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/2010.10814/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":"2026-07-05T01:44:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGflZVWp5tH6ZXCnS05BbcCVKvU9gFpfB2WHmYf7snqwDCFnrPvgmETLOyane5FTu8DyZhnalrg3l3y/+/wMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:58:53.906681Z"},"content_sha256":"c080ad35442861720407c1be12eb17976c80a19b112e6b9af3955b6667d0cd42","schema_version":"1.0","event_id":"sha256:c080ad35442861720407c1be12eb17976c80a19b112e6b9af3955b6667d0cd42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ/bundle.json","state_url":"https://pith.science/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ/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":"2026-08-09T11:58:53Z","links":{"resolver":"https://pith.science/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ","bundle":"https://pith.science/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ/bundle.json","state":"https://pith.science/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAIILT7SJJQH2OHTBBA6YNXQNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HAIILT7SJJQH2OHTBBA6YNXQNJ","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":"f4fcfe258cf957afd36e5ae891be0e96aedefb44aee714df206b5eeab28c649b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-21T08:12:03Z","title_canon_sha256":"a045187f11c33acb16042e4867cdb992c7d2882819b56a0e366635cd557e3956"},"schema_version":"1.0","source":{"id":"2010.10814","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10814","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10814v1","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10814","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_12","alias_value":"HAIILT7SJJQH","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_16","alias_value":"HAIILT7SJJQH2OHT","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_8","alias_value":"HAIILT7S","created_at":"2026-07-05T01:44:54Z"}],"graph_snapshots":[{"event_id":"sha256:c080ad35442861720407c1be12eb17976c80a19b112e6b9af3955b6667d0cd42","target":"graph","created_at":"2026-07-05T01:44:54Z","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/2010.10814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their generalizability, data augmentation approaches (e.g. cutout and random convolution) are previously explored to increase the data diversity. However, we find these approaches only locally perturb the observations regardless of the training environments, showing limited effectiveness on enhancing the data diversity and the generalization performance. In this work, we introduce a simple approach, named mixreg, which tra","authors_text":"Bingyi Kang, Jiashi Feng, Jie Shao, Kaixin Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-21T08:12:03Z","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10814","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":"sha256:1cc2706b6fe4cb18ce72d1ea9594e0cb9e435c36bac2aaadf60d6e5b0141d62d","target":"record","created_at":"2026-07-05T01:44:54Z","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":"f4fcfe258cf957afd36e5ae891be0e96aedefb44aee714df206b5eeab28c649b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-21T08:12:03Z","title_canon_sha256":"a045187f11c33acb16042e4867cdb992c7d2882819b56a0e366635cd557e3956"},"schema_version":"1.0","source":{"id":"2010.10814","kind":"arxiv","version":1}},"canonical_sha256":"381085cff24a607d38f30841ec36f06a641fc002fa3a5df1acbe77a02b16d9ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"381085cff24a607d38f30841ec36f06a641fc002fa3a5df1acbe77a02b16d9ea","first_computed_at":"2026-07-05T01:44:54.776916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:54.776916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"io2lsFZgyirO5Sw4bAA120iq9rojWf8yiBEl0LthzAVLN78cA2MavgWZrBWIcfZojaC8/mf74i49BbwyVwhVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:54.777340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.10814","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cc2706b6fe4cb18ce72d1ea9594e0cb9e435c36bac2aaadf60d6e5b0141d62d","sha256:c080ad35442861720407c1be12eb17976c80a19b112e6b9af3955b6667d0cd42"],"state_sha256":"2c8ea4ae1eec58e46913f74e461cff752dfcd00649373221ff945479a0c4b52f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4vlwsT5BxOzHEjhOtjDNjO84oKq2+7Ex0kqX5p1QsTInBwyYZEwoq2MvWfd6ugddSw8K20NJtFKyWShFHAcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:58:53.923617Z","bundle_sha256":"58ed9e5a1f26fa800306ec55922921a57265e0c065fa31d69e87148aae417340"}}