{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BNO2QNSVWCA46QR5URB7LTX6Q3","short_pith_number":"pith:BNO2QNSV","canonical_record":{"source":{"id":"2108.08448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T02:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"5bd5a733ca1c00a8dd60fe8dade1190af18d7d896fb3c2191db8a9a8e3bf87ba","abstract_canon_sha256":"390d703e563442e1dde8231046b54999bccfbd569c97895ffc0013d6d3804ff8"},"schema_version":"1.0"},"canonical_sha256":"0b5da83655b081cf423da443f5cefe86d26a5b11d08f535265f117de5a4ad072","source":{"kind":"arxiv","id":"2108.08448","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08448","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08448v2","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08448","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_12","alias_value":"BNO2QNSVWCA4","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_16","alias_value":"BNO2QNSVWCA46QR5","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_8","alias_value":"BNO2QNSV","created_at":"2026-07-05T05:40:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BNO2QNSVWCA46QR5URB7LTX6Q3","target":"record","payload":{"canonical_record":{"source":{"id":"2108.08448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T02:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"5bd5a733ca1c00a8dd60fe8dade1190af18d7d896fb3c2191db8a9a8e3bf87ba","abstract_canon_sha256":"390d703e563442e1dde8231046b54999bccfbd569c97895ffc0013d6d3804ff8"},"schema_version":"1.0"},"canonical_sha256":"0b5da83655b081cf423da443f5cefe86d26a5b11d08f535265f117de5a4ad072","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:04.216143Z","signature_b64":"L87L2l/X3DXqh21Pp7oZe7IGrTcjq//hNJdWm1zvgtGEaSoq3ePiPfRl+Gyaw/h2+88kcotBenj3QYT9nyzlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b5da83655b081cf423da443f5cefe86d26a5b11d08f535265f117de5a4ad072","last_reissued_at":"2026-07-05T05:40:04.215652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:04.215652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.08448","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngJeGw15gM3oFvNw3iY60FcMahgoanXKcftWpjaze0BqgTUN7T+UdsI4cKVImNPCHLVvLqqfKmGlhz1L7Ic+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:39:38.650747Z"},"content_sha256":"c22565217b7607f411d639f67c01d50db9fdb9b1cdd626c96256e984853659ab","schema_version":"1.0","event_id":"sha256:c22565217b7607f411d639f67c01d50db9fdb9b1cdd626c96256e984853659ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BNO2QNSVWCA46QR5URB7LTX6Q3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baljeet Singh, Dimitar Filev, H. Eric Tseng, Huei Peng, Lu Wen, Songan Zhang","submitted_at":"2021-08-19T02:33:43Z","abstract_excerpt":"Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \\textit{Probabilistic embeddings for actor-critic RL} (PEARL) is a leading approach for multi-MDP adaptation problems. A major drawback of many existing Meta-RL methods, including PEARL, is that they do not explicitly consider the safety of the prior policy when it is exposed to a new task for the first time. Safety is essential for many real-world applications, including field robots and Autonomous Vehicles (AV"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08448","kind":"arxiv","version":2},"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/2108.08448/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":"2026-07-05T05:40:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IXx4icCDkPhd/+NAG0wA9XNI5QcubXUlJG+MqKwiy8fEZi1iKzb/LdM350211dW6awUNAjxV/vir80JU6ndFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:39:38.651325Z"},"content_sha256":"b23ed2cdfae199b3a0a33773853f4ee8cf744e966873ad7edd595370b7f099db","schema_version":"1.0","event_id":"sha256:b23ed2cdfae199b3a0a33773853f4ee8cf744e966873ad7edd595370b7f099db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNO2QNSVWCA46QR5URB7LTX6Q3/bundle.json","state_url":"https://pith.science/pith/BNO2QNSVWCA46QR5URB7LTX6Q3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNO2QNSVWCA46QR5URB7LTX6Q3/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":"2026-08-18T10:39:38Z","links":{"resolver":"https://pith.science/pith/BNO2QNSVWCA46QR5URB7LTX6Q3","bundle":"https://pith.science/pith/BNO2QNSVWCA46QR5URB7LTX6Q3/bundle.json","state":"https://pith.science/pith/BNO2QNSVWCA46QR5URB7LTX6Q3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNO2QNSVWCA46QR5URB7LTX6Q3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BNO2QNSVWCA46QR5URB7LTX6Q3","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":"390d703e563442e1dde8231046b54999bccfbd569c97895ffc0013d6d3804ff8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T02:33:43Z","title_canon_sha256":"5bd5a733ca1c00a8dd60fe8dade1190af18d7d896fb3c2191db8a9a8e3bf87ba"},"schema_version":"1.0","source":{"id":"2108.08448","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08448","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08448v2","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08448","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_12","alias_value":"BNO2QNSVWCA4","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_16","alias_value":"BNO2QNSVWCA46QR5","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_8","alias_value":"BNO2QNSV","created_at":"2026-07-05T05:40:04Z"}],"graph_snapshots":[{"event_id":"sha256:b23ed2cdfae199b3a0a33773853f4ee8cf744e966873ad7edd595370b7f099db","target":"graph","created_at":"2026-07-05T05:40:04Z","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/2108.08448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \\textit{Probabilistic embeddings for actor-critic RL} (PEARL) is a leading approach for multi-MDP adaptation problems. A major drawback of many existing Meta-RL methods, including PEARL, is that they do not explicitly consider the safety of the prior policy when it is exposed to a new task for the first time. Safety is essential for many real-world applications, including field robots and Autonomous Vehicles (AV","authors_text":"Baljeet Singh, Dimitar Filev, H. Eric Tseng, Huei Peng, Lu Wen, Songan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T02:33:43Z","title":"Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08448","kind":"arxiv","version":2},"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:c22565217b7607f411d639f67c01d50db9fdb9b1cdd626c96256e984853659ab","target":"record","created_at":"2026-07-05T05:40:04Z","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":"390d703e563442e1dde8231046b54999bccfbd569c97895ffc0013d6d3804ff8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T02:33:43Z","title_canon_sha256":"5bd5a733ca1c00a8dd60fe8dade1190af18d7d896fb3c2191db8a9a8e3bf87ba"},"schema_version":"1.0","source":{"id":"2108.08448","kind":"arxiv","version":2}},"canonical_sha256":"0b5da83655b081cf423da443f5cefe86d26a5b11d08f535265f117de5a4ad072","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b5da83655b081cf423da443f5cefe86d26a5b11d08f535265f117de5a4ad072","first_computed_at":"2026-07-05T05:40:04.215652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:04.215652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L87L2l/X3DXqh21Pp7oZe7IGrTcjq//hNJdWm1zvgtGEaSoq3ePiPfRl+Gyaw/h2+88kcotBenj3QYT9nyzlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:04.216143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.08448","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c22565217b7607f411d639f67c01d50db9fdb9b1cdd626c96256e984853659ab","sha256:b23ed2cdfae199b3a0a33773853f4ee8cf744e966873ad7edd595370b7f099db"],"state_sha256":"15eaf645b9c5710a5df3d5152f4159c8e9c77e2ea90c526eba95a63d609f76b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WsVcSo/QuXZNExBtaf8gf8vtg15ThmNhKJ+ZLr5E1n5CST/hhHnTPSXnefvsXtqv/aiXjAZAU9vhV3veBY//Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:39:38.655060Z","bundle_sha256":"25497f275e667a6a94e014b957622a944f2b494c8c1fd05348c68bf56c9c4d80"}}