{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GQ5HVHTX5SCZP7EVHAAK5I65O6","short_pith_number":"pith:GQ5HVHTX","canonical_record":{"source":{"id":"2107.06353","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-13T19:26:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"143e29ef06f7b0dfad670f94ec7d52ae7f51c8adfdbc9290e9f2dc04e04e7e95","abstract_canon_sha256":"65ebd56653954b928575bff2caf91e8bf1553f8e379693ebdb14498b64d06d6c"},"schema_version":"1.0"},"canonical_sha256":"343a7a9e77ec8597fc953800aea3dd779ea21f9a73cd27e69bb3d22dd6e5c82c","source":{"kind":"arxiv","id":"2107.06353","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06353","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06353v6","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06353","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"pith_short_12","alias_value":"GQ5HVHTX5SCZ","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"pith_short_16","alias_value":"GQ5HVHTX5SCZP7EV","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"pith_short_8","alias_value":"GQ5HVHTX","created_at":"2026-07-05T04:38:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GQ5HVHTX5SCZP7EVHAAK5I65O6","target":"record","payload":{"canonical_record":{"source":{"id":"2107.06353","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-13T19:26:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"143e29ef06f7b0dfad670f94ec7d52ae7f51c8adfdbc9290e9f2dc04e04e7e95","abstract_canon_sha256":"65ebd56653954b928575bff2caf91e8bf1553f8e379693ebdb14498b64d06d6c"},"schema_version":"1.0"},"canonical_sha256":"343a7a9e77ec8597fc953800aea3dd779ea21f9a73cd27e69bb3d22dd6e5c82c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:11.044598Z","signature_b64":"i+gJru0547caaNs1mp3ysiIFpJuG6bSTKAG4znrpWBcMJpBaxgatJEutm2k/7ESHLCmBAOiY9CsHfw/9w5xQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"343a7a9e77ec8597fc953800aea3dd779ea21f9a73cd27e69bb3d22dd6e5c82c","last_reissued_at":"2026-07-05T04:38:11.044139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:11.044139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.06353","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IdUwuRB5cRC+tI5DXnmIMkBPhRnknB3AabsKfTam06z+lDKBUtPMUjnyWxraY+qkYpG6vuJSXiF4bgPTfQjTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:24:59.660023Z"},"content_sha256":"158ba8965d5c05e6f8162430f0c68ebc528ea8d60aec57b11a5fe96d90ec2826","schema_version":"1.0","event_id":"sha256:158ba8965d5c05e6f8162430f0c68ebc528ea8d60aec57b11a5fe96d90ec2826"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GQ5HVHTX5SCZP7EVHAAK5I65O6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Policy Learning via Adversarial Environment Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Allen Z. Ren, Anirudha Majumdar","submitted_at":"2021-07-13T19:26:34Z","abstract_excerpt":"Our goal is to train control policies that generalize well to unseen environments. Inspired by the Distributionally Robust Optimization (DRO) framework, we propose DRAGEN - Distributionally Robust policy learning via Adversarial Generation of ENvironments - for iteratively improving robustness of policies to realistic distribution shifts by generating adversarial environments. The key idea is to learn a generative model for environments whose latent variables capture cost-predictive and realistic variations in environments. We perform DRO with respect to a Wasserstein ball around the empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06353","kind":"arxiv","version":6},"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/2107.06353/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":"2026-07-05T04:38:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ROIie5o4b2dUcccoKbygj/RJG6Oh833qmw7HG8o/c+jjliWP10s+W5ACYAoxamLPF4J9n3eqe72ikPvrUH9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:24:59.660936Z"},"content_sha256":"8ada8168fa5925ff102b116f5a2e83a62a4de3e03e3a270f2768bc39efe2c02a","schema_version":"1.0","event_id":"sha256:8ada8168fa5925ff102b116f5a2e83a62a4de3e03e3a270f2768bc39efe2c02a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6/bundle.json","state_url":"https://pith.science/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6/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":"2026-08-17T16:24:59Z","links":{"resolver":"https://pith.science/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6","bundle":"https://pith.science/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6/bundle.json","state":"https://pith.science/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQ5HVHTX5SCZP7EVHAAK5I65O6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GQ5HVHTX5SCZP7EVHAAK5I65O6","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":"65ebd56653954b928575bff2caf91e8bf1553f8e379693ebdb14498b64d06d6c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-13T19:26:34Z","title_canon_sha256":"143e29ef06f7b0dfad670f94ec7d52ae7f51c8adfdbc9290e9f2dc04e04e7e95"},"schema_version":"1.0","source":{"id":"2107.06353","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06353","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06353v6","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06353","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"pith_short_12","alias_value":"GQ5HVHTX5SCZ","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"pith_short_16","alias_value":"GQ5HVHTX5SCZP7EV","created_at":"2026-07-05T04:38:11Z"},{"alias_kind":"pith_short_8","alias_value":"GQ5HVHTX","created_at":"2026-07-05T04:38:11Z"}],"graph_snapshots":[{"event_id":"sha256:8ada8168fa5925ff102b116f5a2e83a62a4de3e03e3a270f2768bc39efe2c02a","target":"graph","created_at":"2026-07-05T04:38:11Z","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/2107.06353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our goal is to train control policies that generalize well to unseen environments. Inspired by the Distributionally Robust Optimization (DRO) framework, we propose DRAGEN - Distributionally Robust policy learning via Adversarial Generation of ENvironments - for iteratively improving robustness of policies to realistic distribution shifts by generating adversarial environments. The key idea is to learn a generative model for environments whose latent variables capture cost-predictive and realistic variations in environments. We perform DRO with respect to a Wasserstein ball around the empirical","authors_text":"Allen Z. Ren, Anirudha Majumdar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-13T19:26:34Z","title":"Distributionally Robust Policy Learning via Adversarial Environment Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06353","kind":"arxiv","version":6},"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":"sha256:158ba8965d5c05e6f8162430f0c68ebc528ea8d60aec57b11a5fe96d90ec2826","target":"record","created_at":"2026-07-05T04:38:11Z","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":"65ebd56653954b928575bff2caf91e8bf1553f8e379693ebdb14498b64d06d6c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-13T19:26:34Z","title_canon_sha256":"143e29ef06f7b0dfad670f94ec7d52ae7f51c8adfdbc9290e9f2dc04e04e7e95"},"schema_version":"1.0","source":{"id":"2107.06353","kind":"arxiv","version":6}},"canonical_sha256":"343a7a9e77ec8597fc953800aea3dd779ea21f9a73cd27e69bb3d22dd6e5c82c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"343a7a9e77ec8597fc953800aea3dd779ea21f9a73cd27e69bb3d22dd6e5c82c","first_computed_at":"2026-07-05T04:38:11.044139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:11.044139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+gJru0547caaNs1mp3ysiIFpJuG6bSTKAG4znrpWBcMJpBaxgatJEutm2k/7ESHLCmBAOiY9CsHfw/9w5xQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:11.044598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06353","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:158ba8965d5c05e6f8162430f0c68ebc528ea8d60aec57b11a5fe96d90ec2826","sha256:8ada8168fa5925ff102b116f5a2e83a62a4de3e03e3a270f2768bc39efe2c02a"],"state_sha256":"a07231a50f776026c926e960e4ba5b0ce3da64f8dc453f362d610c83d303e50d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1PtJQXtZTH/4pRt9+aVRLqjdP03Rn2CfdiTjmUn4fWhAJs/tFYG4ZpJ9bMxC/VC6QTsExULQie5MGJWlG6hEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:24:59.668348Z","bundle_sha256":"284c130effaa5f9ece54d81a2d9972673e02e1bc9754471624beeec82862df01"}}