{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WF2JMES33EAXZDEOT3CVPVUYPS","short_pith_number":"pith:WF2JMES3","canonical_record":{"source":{"id":"1909.12906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-16T11:59:40Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"582bb218fa9700950354a7d6e466b909295b16ce77bbae77f2e97f53e3ca39e0","abstract_canon_sha256":"da3d268c02d8c2cc9411cf6883c9ae478d726c101bfa4c3ccc068137435d68d1"},"schema_version":"1.0"},"canonical_sha256":"b17496125bd9017c8c8e9ec557d6987c8a8516714c6d41c0dd5b2086e12a048c","source":{"kind":"arxiv","id":"1909.12906","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.12906","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"arxiv_version","alias_value":"1909.12906v1","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12906","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"pith_short_12","alias_value":"WF2JMES33EAX","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"pith_short_16","alias_value":"WF2JMES33EAXZDEO","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"pith_short_8","alias_value":"WF2JMES3","created_at":"2026-07-05T00:07:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WF2JMES33EAXZDEOT3CVPVUYPS","target":"record","payload":{"canonical_record":{"source":{"id":"1909.12906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-16T11:59:40Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"582bb218fa9700950354a7d6e466b909295b16ce77bbae77f2e97f53e3ca39e0","abstract_canon_sha256":"da3d268c02d8c2cc9411cf6883c9ae478d726c101bfa4c3ccc068137435d68d1"},"schema_version":"1.0"},"canonical_sha256":"b17496125bd9017c8c8e9ec557d6987c8a8516714c6d41c0dd5b2086e12a048c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:53.772406Z","signature_b64":"2FqxLDF9gqBwQtFfTU/f1P7p9V6qFYyS8XnnLiBOVlBP2mZpKf8H5Bp5wk3mJ2ZjSzGnFAl0jLec2g8nfLiHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17496125bd9017c8c8e9ec557d6987c8a8516714c6d41c0dd5b2086e12a048c","last_reissued_at":"2026-07-05T00:07:53.771953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:53.771953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.12906","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":"2026-07-05T00:07:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tw5/06g1uSuXIzxzNhVOxsKyB7gIpUNKyyBIaB3isaJUmgfm3VaCiCmMdmlhxxBaMmuWpwn/9oS+x3f3u87Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:34:04.787132Z"},"content_sha256":"aaa3cf22ac52c416a36aca590f41ff3f7008bc975fee00d3be78120046809ef0","schema_version":"1.0","event_id":"sha256:aaa3cf22ac52c416a36aca590f41ff3f7008bc975fee00d3be78120046809ef0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WF2JMES33EAXZDEOT3CVPVUYPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ali Ghadirzadeh, Karol Arndt, Murtaza Hazara, Ville Kyrki","submitted_at":"2019-09-16T11:59:40Z","abstract_excerpt":"Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this work, we propose to address the problem of sim-to-real domain transfer by using meta learning to train a policy that can adapt to a variety of dynamic conditions, and using a task-specific trajectory generation model to provide an action space that facilitates quick exploration. We evaluate the method by performing domain adaptation in simulation and analyzing the structure of the latent space during adaptation. We the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12906","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/1909.12906/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":"2026-07-05T00:07:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bhJ+7S7hxVf82SsPHEmCMoEb0HnP+ZJsqA7NuNaJ37YwvoU1aQAGDnAVoRb9+zlC37xI4h1gXUo1jY1okazCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:34:04.788016Z"},"content_sha256":"b13e3c470924193759adea46edbff2c89c5c98e857935b75c261f98c387b7532","schema_version":"1.0","event_id":"sha256:b13e3c470924193759adea46edbff2c89c5c98e857935b75c261f98c387b7532"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WF2JMES33EAXZDEOT3CVPVUYPS/bundle.json","state_url":"https://pith.science/pith/WF2JMES33EAXZDEOT3CVPVUYPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WF2JMES33EAXZDEOT3CVPVUYPS/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":"2026-08-08T23:34:04Z","links":{"resolver":"https://pith.science/pith/WF2JMES33EAXZDEOT3CVPVUYPS","bundle":"https://pith.science/pith/WF2JMES33EAXZDEOT3CVPVUYPS/bundle.json","state":"https://pith.science/pith/WF2JMES33EAXZDEOT3CVPVUYPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WF2JMES33EAXZDEOT3CVPVUYPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WF2JMES33EAXZDEOT3CVPVUYPS","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":"da3d268c02d8c2cc9411cf6883c9ae478d726c101bfa4c3ccc068137435d68d1","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-16T11:59:40Z","title_canon_sha256":"582bb218fa9700950354a7d6e466b909295b16ce77bbae77f2e97f53e3ca39e0"},"schema_version":"1.0","source":{"id":"1909.12906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.12906","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"arxiv_version","alias_value":"1909.12906v1","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12906","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"pith_short_12","alias_value":"WF2JMES33EAX","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"pith_short_16","alias_value":"WF2JMES33EAXZDEO","created_at":"2026-07-05T00:07:53Z"},{"alias_kind":"pith_short_8","alias_value":"WF2JMES3","created_at":"2026-07-05T00:07:53Z"}],"graph_snapshots":[{"event_id":"sha256:b13e3c470924193759adea46edbff2c89c5c98e857935b75c261f98c387b7532","target":"graph","created_at":"2026-07-05T00:07:53Z","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/1909.12906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this work, we propose to address the problem of sim-to-real domain transfer by using meta learning to train a policy that can adapt to a variety of dynamic conditions, and using a task-specific trajectory generation model to provide an action space that facilitates quick exploration. We evaluate the method by performing domain adaptation in simulation and analyzing the structure of the latent space during adaptation. We the","authors_text":"Ali Ghadirzadeh, Karol Arndt, Murtaza Hazara, Ville Kyrki","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-16T11:59:40Z","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12906","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:aaa3cf22ac52c416a36aca590f41ff3f7008bc975fee00d3be78120046809ef0","target":"record","created_at":"2026-07-05T00:07:53Z","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":"da3d268c02d8c2cc9411cf6883c9ae478d726c101bfa4c3ccc068137435d68d1","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-16T11:59:40Z","title_canon_sha256":"582bb218fa9700950354a7d6e466b909295b16ce77bbae77f2e97f53e3ca39e0"},"schema_version":"1.0","source":{"id":"1909.12906","kind":"arxiv","version":1}},"canonical_sha256":"b17496125bd9017c8c8e9ec557d6987c8a8516714c6d41c0dd5b2086e12a048c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b17496125bd9017c8c8e9ec557d6987c8a8516714c6d41c0dd5b2086e12a048c","first_computed_at":"2026-07-05T00:07:53.771953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:53.771953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2FqxLDF9gqBwQtFfTU/f1P7p9V6qFYyS8XnnLiBOVlBP2mZpKf8H5Bp5wk3mJ2ZjSzGnFAl0jLec2g8nfLiHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:53.772406Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.12906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaa3cf22ac52c416a36aca590f41ff3f7008bc975fee00d3be78120046809ef0","sha256:b13e3c470924193759adea46edbff2c89c5c98e857935b75c261f98c387b7532"],"state_sha256":"9a4c3eda2d2b1ab24aa59f8ae34d8dda1bd871b1b5d37f4dbf9224ed6a8719a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBmS9tY240JL9e3pS7Cf9/3ey+jYGyW3ea5SE5IOUp7mk+hN7NrVHnf5tYOVZUWLjtFqGEPultLrB0PonMy8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:34:04.793859Z","bundle_sha256":"2aafdba65bb1d08382a79665002c49ef18c8ec608ea9d17c61e9b6e6943cce65"}}