{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MUJWJJO4RMJGPLHJHBSAHI3PFI","short_pith_number":"pith:MUJWJJO4","canonical_record":{"source":{"id":"2006.13916","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:47:37Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"7dbd214ceb1d3420a96c4cadb37860d71dd9f3b3626375cf96da4f20339569e7","abstract_canon_sha256":"11c94c5f8f62488d66843524c4c14257f1addb299a3b596991de1313b35d1d7e"},"schema_version":"1.0"},"canonical_sha256":"651364a5dc8b1267ace9386403a36f2a2946badd66cf3f7c9152d623b8eaf8ce","source":{"kind":"arxiv","id":"2006.13916","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13916","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13916v2","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13916","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"MUJWJJO4RMJG","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"MUJWJJO4RMJGPLHJ","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"MUJWJJO4","created_at":"2026-07-05T02:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MUJWJJO4RMJGPLHJHBSAHI3PFI","target":"record","payload":{"canonical_record":{"source":{"id":"2006.13916","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:47:37Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"7dbd214ceb1d3420a96c4cadb37860d71dd9f3b3626375cf96da4f20339569e7","abstract_canon_sha256":"11c94c5f8f62488d66843524c4c14257f1addb299a3b596991de1313b35d1d7e"},"schema_version":"1.0"},"canonical_sha256":"651364a5dc8b1267ace9386403a36f2a2946badd66cf3f7c9152d623b8eaf8ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:13.056122Z","signature_b64":"w853ebMUVdvJReDwq8OhmdcQekQz9+XVHYrlCeis7h+QdCdZmJjvT7Wpa4VJvz2NukZo//MR9B8sJJSeu2WLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"651364a5dc8b1267ace9386403a36f2a2946badd66cf3f7c9152d623b8eaf8ce","last_reissued_at":"2026-07-05T02:32:13.055621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:13.055621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.13916","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":"2026-07-05T02:32:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2Dv2bt8o/+GHtd9qseXsgVw52TqwwWVmms4Y/mM9eyq4jHe/rml1vg9YBcQlAL3/GdwlP7KQn9uEa3eKqyvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:40.623876Z"},"content_sha256":"78f843e3e3a66bc26f365b1c632398242abc8648170386e110ce86f466d8f304","schema_version":"1.0","event_id":"sha256:78f843e3e3a66bc26f365b1c632398242abc8648170386e110ce86f466d8f304"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MUJWJJO4RMJGPLHJHBSAHI3PFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Shreyas Chaudhari, Swapnil Asawa","submitted_at":"2020-06-24T17:47:37Z","abstract_excerpt":"We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we formally show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the modi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13916","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/2006.13916/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":"2026-07-05T02:32:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mw/o20NsBS+NQkgWzQkRSO5ZSjm0t8qUIqTexwVbt6+/uRg9Ev3maO0JFqQuaUrWfEmLgde+RsNnBR8B4RUxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:40.624880Z"},"content_sha256":"3683616a059c5ecd4dd0b77d76a5e31c3b2c9c3ab7eccd74ab4da3174e55621d","schema_version":"1.0","event_id":"sha256:3683616a059c5ecd4dd0b77d76a5e31c3b2c9c3ab7eccd74ab4da3174e55621d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI/bundle.json","state_url":"https://pith.science/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI/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":"2026-08-10T06:31:40Z","links":{"resolver":"https://pith.science/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI","bundle":"https://pith.science/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI/bundle.json","state":"https://pith.science/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MUJWJJO4RMJGPLHJHBSAHI3PFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MUJWJJO4RMJGPLHJHBSAHI3PFI","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":"11c94c5f8f62488d66843524c4c14257f1addb299a3b596991de1313b35d1d7e","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:47:37Z","title_canon_sha256":"7dbd214ceb1d3420a96c4cadb37860d71dd9f3b3626375cf96da4f20339569e7"},"schema_version":"1.0","source":{"id":"2006.13916","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13916","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13916v2","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13916","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"MUJWJJO4RMJG","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"MUJWJJO4RMJGPLHJ","created_at":"2026-07-05T02:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"MUJWJJO4","created_at":"2026-07-05T02:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:3683616a059c5ecd4dd0b77d76a5e31c3b2c9c3ab7eccd74ab4da3174e55621d","target":"graph","created_at":"2026-07-05T02:32:13Z","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/2006.13916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we formally show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the modi","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Shreyas Chaudhari, Swapnil Asawa","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:47:37Z","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13916","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":"sha256:78f843e3e3a66bc26f365b1c632398242abc8648170386e110ce86f466d8f304","target":"record","created_at":"2026-07-05T02:32:13Z","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":"11c94c5f8f62488d66843524c4c14257f1addb299a3b596991de1313b35d1d7e","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:47:37Z","title_canon_sha256":"7dbd214ceb1d3420a96c4cadb37860d71dd9f3b3626375cf96da4f20339569e7"},"schema_version":"1.0","source":{"id":"2006.13916","kind":"arxiv","version":2}},"canonical_sha256":"651364a5dc8b1267ace9386403a36f2a2946badd66cf3f7c9152d623b8eaf8ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"651364a5dc8b1267ace9386403a36f2a2946badd66cf3f7c9152d623b8eaf8ce","first_computed_at":"2026-07-05T02:32:13.055621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:13.055621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w853ebMUVdvJReDwq8OhmdcQekQz9+XVHYrlCeis7h+QdCdZmJjvT7Wpa4VJvz2NukZo//MR9B8sJJSeu2WLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:13.056122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13916","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78f843e3e3a66bc26f365b1c632398242abc8648170386e110ce86f466d8f304","sha256:3683616a059c5ecd4dd0b77d76a5e31c3b2c9c3ab7eccd74ab4da3174e55621d"],"state_sha256":"9185acafdd11d1429d9cf4e8f2c9ecd68e6169ec8c267bd8fcb923ccac9156f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PuZvmIpZzEdaDAko+jVxQpQrrdxC1sETFHTl2VsSR42sHQH0IePXMHQqwThdKTaOHlPSONNtvXyU81MH0yapDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:31:40.634279Z","bundle_sha256":"0d2a54ef9274624a911553c8f1bc1f04b3cd6668589b6b07b73f7adf34a60d1b"}}