{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QUBRG33WY73TP4UBW67BJ3KXBJ","short_pith_number":"pith:QUBRG33W","canonical_record":{"source":{"id":"2006.08051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a512305b6df7ab8c2e3581e4f4271957c1fed11fa0d952054e52326500a6223","abstract_canon_sha256":"e86f00bb34deaa00b7526f7ee3eb367235c271837b8514d6ce959a162acee428"},"schema_version":"1.0"},"canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","source":{"kind":"arxiv","id":"2006.08051","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08051","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08051v1","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08051","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"QUBRG33WY73T","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"QUBRG33WY73TP4UB","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"QUBRG33W","created_at":"2026-07-05T01:10:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QUBRG33WY73TP4UBW67BJ3KXBJ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.08051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a512305b6df7ab8c2e3581e4f4271957c1fed11fa0d952054e52326500a6223","abstract_canon_sha256":"e86f00bb34deaa00b7526f7ee3eb367235c271837b8514d6ce959a162acee428"},"schema_version":"1.0"},"canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:17.871519Z","signature_b64":"/VTEByIWOvhPg7C6jFHjsS6JiFIkTE6o9nS/vxGh2hdDm1Ev9yqC461ryM93eyeHmzT3GV99zMkdBU/W0ZphAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","last_reissued_at":"2026-07-05T01:10:17.871040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:17.871040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.08051","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":"2026-07-05T01:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XAg7i6KmqYmsm3LQ/hFvu5BdfbW635eFv/0ReoM6hV19ZZH7tkh4nxSTEMTCO3PMIbiICpd+1G1cD/1W7B0ODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:05:49.947401Z"},"content_sha256":"cdd36a8e3896c8bb900141e7f100da6ffe9b997994a20cbc781f2440a0217585","schema_version":"1.0","event_id":"sha256:cdd36a8e3896c8bb900141e7f100da6ffe9b997994a20cbc781f2440a0217585"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QUBRG33WY73TP4UBW67BJ3KXBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Model-based Policy Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditi Mavalankar, Sicun Gao, Wen Sun, Yuda Song","submitted_at":"2020-06-14T23:16:20Z","abstract_excerpt":"The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on domain randomization and meta-learning, by sampling from some distribution of target environments during pre-training, and thus face difficulty on out-of-distribution target environments. We propose new model-based mechanisms that are able to make online adaptation in unseen target environments, by combining ideas from no-regret online learning and adaptive co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08051","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/2006.08051/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":"2026-07-05T01:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IROTH6S2vrAIoCNXJ7ynf4uGRmv62/mFxfDBSKqXh7bTOINZJ1ljL8azh0pOGc1DsiNGdvytrAn2Zs0w+aJ1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:05:49.947874Z"},"content_sha256":"0b3ebbe6f9cb624ba892b2db3c523430bf9bf115f4a1be0ded86d05efaa8d792","schema_version":"1.0","event_id":"sha256:0b3ebbe6f9cb624ba892b2db3c523430bf9bf115f4a1be0ded86d05efaa8d792"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUBRG33WY73TP4UBW67BJ3KXBJ/bundle.json","state_url":"https://pith.science/pith/QUBRG33WY73TP4UBW67BJ3KXBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUBRG33WY73TP4UBW67BJ3KXBJ/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":"2026-08-07T00:05:49Z","links":{"resolver":"https://pith.science/pith/QUBRG33WY73TP4UBW67BJ3KXBJ","bundle":"https://pith.science/pith/QUBRG33WY73TP4UBW67BJ3KXBJ/bundle.json","state":"https://pith.science/pith/QUBRG33WY73TP4UBW67BJ3KXBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUBRG33WY73TP4UBW67BJ3KXBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QUBRG33WY73TP4UBW67BJ3KXBJ","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":"e86f00bb34deaa00b7526f7ee3eb367235c271837b8514d6ce959a162acee428","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","title_canon_sha256":"5a512305b6df7ab8c2e3581e4f4271957c1fed11fa0d952054e52326500a6223"},"schema_version":"1.0","source":{"id":"2006.08051","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08051","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08051v1","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08051","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"QUBRG33WY73T","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"QUBRG33WY73TP4UB","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"QUBRG33W","created_at":"2026-07-05T01:10:17Z"}],"graph_snapshots":[{"event_id":"sha256:0b3ebbe6f9cb624ba892b2db3c523430bf9bf115f4a1be0ded86d05efaa8d792","target":"graph","created_at":"2026-07-05T01:10:17Z","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/2006.08051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on domain randomization and meta-learning, by sampling from some distribution of target environments during pre-training, and thus face difficulty on out-of-distribution target environments. We propose new model-based mechanisms that are able to make online adaptation in unseen target environments, by combining ideas from no-regret online learning and adaptive co","authors_text":"Aditi Mavalankar, Sicun Gao, Wen Sun, Yuda Song","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","title":"Provably Efficient Model-based Policy Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08051","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:cdd36a8e3896c8bb900141e7f100da6ffe9b997994a20cbc781f2440a0217585","target":"record","created_at":"2026-07-05T01:10:17Z","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":"e86f00bb34deaa00b7526f7ee3eb367235c271837b8514d6ce959a162acee428","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","title_canon_sha256":"5a512305b6df7ab8c2e3581e4f4271957c1fed11fa0d952054e52326500a6223"},"schema_version":"1.0","source":{"id":"2006.08051","kind":"arxiv","version":1}},"canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","first_computed_at":"2026-07-05T01:10:17.871040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:17.871040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/VTEByIWOvhPg7C6jFHjsS6JiFIkTE6o9nS/vxGh2hdDm1Ev9yqC461ryM93eyeHmzT3GV99zMkdBU/W0ZphAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:17.871519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08051","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdd36a8e3896c8bb900141e7f100da6ffe9b997994a20cbc781f2440a0217585","sha256:0b3ebbe6f9cb624ba892b2db3c523430bf9bf115f4a1be0ded86d05efaa8d792"],"state_sha256":"db81aed21564539d1fdc33710a12208c14ea25bd12af4681dd48d126ed025dcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"463/6SVD7tFYX1p/1zUnsqRzpvHFcAqULQSH2OlT5ISLut3msKhIPylPspiaCyJVZH7RtUxdPVebmteJ+fMlBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:05:49.951423Z","bundle_sha256":"1ba1c8854488ee68d3f50b83b711a66087123fd0cf0d1cbeb3154b6d763c2825"}}