{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TM7UVXL3JLDMNTUDFB6OAS2EQ6","short_pith_number":"pith:TM7UVXL3","canonical_record":{"source":{"id":"2208.02376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T22:52:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2cc9f927ec2e51c3cfdc58d622e1a517a69d93c4e4883e3f3e93aba8f1fce8e","abstract_canon_sha256":"64a8226c1359f04be175ec6186ee568d7977dde0a4ea06e41786e7baf89f96fb"},"schema_version":"1.0"},"canonical_sha256":"9b3f4add7b4ac6c6ce83287ce04b4487a4137571e86359199848d14cf14308ca","source":{"kind":"arxiv","id":"2208.02376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.02376","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"2208.02376v1","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.02376","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"TM7UVXL3JLDM","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"pith_short_16","alias_value":"TM7UVXL3JLDMNTUD","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"pith_short_8","alias_value":"TM7UVXL3","created_at":"2026-07-05T04:46:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TM7UVXL3JLDMNTUDFB6OAS2EQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2208.02376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T22:52:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2cc9f927ec2e51c3cfdc58d622e1a517a69d93c4e4883e3f3e93aba8f1fce8e","abstract_canon_sha256":"64a8226c1359f04be175ec6186ee568d7977dde0a4ea06e41786e7baf89f96fb"},"schema_version":"1.0"},"canonical_sha256":"9b3f4add7b4ac6c6ce83287ce04b4487a4137571e86359199848d14cf14308ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:03.843217Z","signature_b64":"riH/4XvCABPau3DePjSkygO8k+BqxFZ5RfXo8FANfN9aOSEigvJ+XVDKzSMyHIlftB83FoAQXo/vwHbdvGq+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b3f4add7b4ac6c6ce83287ce04b4487a4137571e86359199848d14cf14308ca","last_reissued_at":"2026-07-05T04:46:03.842775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:03.842775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.02376","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":"2026-07-05T04:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"llt4AtQKwviD6cGnClrr0+eYG0fVeKG7n54fZjvR4xS+GSt7LLDoPvL5P7w/05I/qdH4x3hXObCKDLEiRBvtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T17:06:30.787960Z"},"content_sha256":"1ad819028dc7247aee3d41d0a78f3eb7de71a4e1682d3c389cb6b1f23ca0686d","schema_version":"1.0","event_id":"sha256:1ad819028dc7247aee3d41d0a78f3eb7de71a4e1682d3c389cb6b1f23ca0686d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TM7UVXL3JLDMNTUDFB6OAS2EQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guang Kou, Wangyang Yue, Xiaochuan Zhang, Yuan Zhou, Yuchen Hua, Zhiyuan Wang","submitted_at":"2022-08-03T22:52:26Z","abstract_excerpt":"Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been proposed to deal with such situations by training agents under different environmental setups, and therefore they can be generalized to different environments during deployment. However, they usually do not incorporate the underlying environmental factor information that the agents interact with properly and thus can be overly conservative when facing changes in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.02376","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/2208.02376/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":"2026-07-05T04:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"imjD5G1eXzmNsLiZ+iT/rZ3HMYhLqrXm6vi4QNBkMl/r2EHuLo6Zvr3ErgdIdJpbERVoU/JRghqx4r/AGjkgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T17:06:30.788347Z"},"content_sha256":"1811088f86bcb7812f21e5b8f9c25b6be1715269b3e489e5a222f7873087f345","schema_version":"1.0","event_id":"sha256:1811088f86bcb7812f21e5b8f9c25b6be1715269b3e489e5a222f7873087f345"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6/bundle.json","state_url":"https://pith.science/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6/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":"2026-07-20T17:06:30Z","links":{"resolver":"https://pith.science/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6","bundle":"https://pith.science/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6/bundle.json","state":"https://pith.science/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TM7UVXL3JLDMNTUDFB6OAS2EQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TM7UVXL3JLDMNTUDFB6OAS2EQ6","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":"64a8226c1359f04be175ec6186ee568d7977dde0a4ea06e41786e7baf89f96fb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T22:52:26Z","title_canon_sha256":"a2cc9f927ec2e51c3cfdc58d622e1a517a69d93c4e4883e3f3e93aba8f1fce8e"},"schema_version":"1.0","source":{"id":"2208.02376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.02376","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"2208.02376v1","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.02376","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"TM7UVXL3JLDM","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"pith_short_16","alias_value":"TM7UVXL3JLDMNTUD","created_at":"2026-07-05T04:46:03Z"},{"alias_kind":"pith_short_8","alias_value":"TM7UVXL3","created_at":"2026-07-05T04:46:03Z"}],"graph_snapshots":[{"event_id":"sha256:1811088f86bcb7812f21e5b8f9c25b6be1715269b3e489e5a222f7873087f345","target":"graph","created_at":"2026-07-05T04:46:03Z","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/2208.02376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been proposed to deal with such situations by training agents under different environmental setups, and therefore they can be generalized to different environments during deployment. However, they usually do not incorporate the underlying environmental factor information that the agents interact with properly and thus can be overly conservative when facing changes in ","authors_text":"Guang Kou, Wangyang Yue, Xiaochuan Zhang, Yuan Zhou, Yuchen Hua, Zhiyuan Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T22:52:26Z","title":"AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.02376","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":"sha256:1ad819028dc7247aee3d41d0a78f3eb7de71a4e1682d3c389cb6b1f23ca0686d","target":"record","created_at":"2026-07-05T04:46:03Z","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":"64a8226c1359f04be175ec6186ee568d7977dde0a4ea06e41786e7baf89f96fb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T22:52:26Z","title_canon_sha256":"a2cc9f927ec2e51c3cfdc58d622e1a517a69d93c4e4883e3f3e93aba8f1fce8e"},"schema_version":"1.0","source":{"id":"2208.02376","kind":"arxiv","version":1}},"canonical_sha256":"9b3f4add7b4ac6c6ce83287ce04b4487a4137571e86359199848d14cf14308ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b3f4add7b4ac6c6ce83287ce04b4487a4137571e86359199848d14cf14308ca","first_computed_at":"2026-07-05T04:46:03.842775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:03.842775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"riH/4XvCABPau3DePjSkygO8k+BqxFZ5RfXo8FANfN9aOSEigvJ+XVDKzSMyHIlftB83FoAQXo/vwHbdvGq+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:03.843217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.02376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ad819028dc7247aee3d41d0a78f3eb7de71a4e1682d3c389cb6b1f23ca0686d","sha256:1811088f86bcb7812f21e5b8f9c25b6be1715269b3e489e5a222f7873087f345"],"state_sha256":"6db823708e45eb836a1e55ddfa01455d59c1ce4cad7d91b3dfe09cc6c30f436f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"txYceREYOZLHsag7FGzhfZ+rzkpYqS+4Y/WuxkFfncq1INh9OWn/UIaBvUszBUD1wD1TQIyjWY4xfNGSVYd7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T17:06:30.790705Z","bundle_sha256":"0adf5dfcf00353a634a2afe9457cd056c63ff9bf4cfb8a103e08ed2b8feb4014"}}