{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:THIULSU32LDSV2UUWGDKSK57FM","short_pith_number":"pith:THIULSU3","canonical_record":{"source":{"id":"1803.10371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-28T01:12:46Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"6334416b1c079e1ae74c854a8b669bff20cfadcc2c7df94ac02d0f98bf0be477","abstract_canon_sha256":"ce4d4a988c5b2e2d13a1dbf5236347cb75ac38b7173d780684c13c1f826a5f5a"},"schema_version":"1.0"},"canonical_sha256":"99d145ca9bd2c72aea94b186a92bbf2b0afac3566db5f26ce4d04467652396c0","source":{"kind":"arxiv","id":"1803.10371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10371","created_at":"2026-05-18T00:19:55Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10371v1","created_at":"2026-05-18T00:19:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10371","created_at":"2026-05-18T00:19:55Z"},{"alias_kind":"pith_short_12","alias_value":"THIULSU32LDS","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"THIULSU32LDSV2UU","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"THIULSU3","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:THIULSU32LDSV2UUWGDKSK57FM","target":"record","payload":{"canonical_record":{"source":{"id":"1803.10371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-28T01:12:46Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"6334416b1c079e1ae74c854a8b669bff20cfadcc2c7df94ac02d0f98bf0be477","abstract_canon_sha256":"ce4d4a988c5b2e2d13a1dbf5236347cb75ac38b7173d780684c13c1f826a5f5a"},"schema_version":"1.0"},"canonical_sha256":"99d145ca9bd2c72aea94b186a92bbf2b0afac3566db5f26ce4d04467652396c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:55.652370Z","signature_b64":"amFWGBrY4VyX1IrvX7qTP0LbsY+AHYavNWVfkVUBYg124E1HVA2SRU84TnZz+b59HUVrO64QsEmXoq+C2TTOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d145ca9bd2c72aea94b186a92bbf2b0afac3566db5f26ce4d04467652396c0","last_reissued_at":"2026-05-18T00:19:55.651623Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:55.651623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.10371","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":"2026-05-18T00:19:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhHciO0oDbXDw5UUUc3w/+N/u1Z1eO1rjy0HzaYE3VkDI9dPeDp3J3qFdW6eo9eZ+oNelKpY65ueZId9/nTaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:03:25.596401Z"},"content_sha256":"0e60acf9c70ee3f5311c76d34e516a6f2d11eceee72a246854bb74e7db706d5a","schema_version":"1.0","event_id":"sha256:0e60acf9c70ee3f5311c76d34e516a6f2d11eceee72a246854bb74e7db706d5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:THIULSU32LDSV2UUWGDKSK57FM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Aravind Rajeswaran, Emanuel Todorov, Jeremy Dao, Kendall Lowrey, Svetoslav Kolev","submitted_at":"2018-03-28T01:12:46Z","abstract_excerpt":"Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data collection methods. Model-based reinforcement learning methods provide an avenue to circumvent these challenges, but the traditional concern has been the mismatch between the simulator and the real world. Here, we show that control policies learned in simulation can successfully transfer to a physical system, composed of three Phantom robots pushing an object to v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10371","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":""},"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":"2026-05-18T00:19:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yufmMxrSjHw1gnLpZ3nvHVc3CgE3lBKtBzJzctQkFJFGP7TSyzM+RdEzlIKMBZgZC1t+BlvSJ1/pOqyHVbbxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:03:25.596755Z"},"content_sha256":"5f47586d2a7e9bf0c964d216d59b11c86bf3a52739774fe0c17420526be388ef","schema_version":"1.0","event_id":"sha256:5f47586d2a7e9bf0c964d216d59b11c86bf3a52739774fe0c17420526be388ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THIULSU32LDSV2UUWGDKSK57FM/bundle.json","state_url":"https://pith.science/pith/THIULSU32LDSV2UUWGDKSK57FM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THIULSU32LDSV2UUWGDKSK57FM/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":"2026-06-02T02:03:25Z","links":{"resolver":"https://pith.science/pith/THIULSU32LDSV2UUWGDKSK57FM","bundle":"https://pith.science/pith/THIULSU32LDSV2UUWGDKSK57FM/bundle.json","state":"https://pith.science/pith/THIULSU32LDSV2UUWGDKSK57FM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THIULSU32LDSV2UUWGDKSK57FM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:THIULSU32LDSV2UUWGDKSK57FM","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":"ce4d4a988c5b2e2d13a1dbf5236347cb75ac38b7173d780684c13c1f826a5f5a","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-28T01:12:46Z","title_canon_sha256":"6334416b1c079e1ae74c854a8b669bff20cfadcc2c7df94ac02d0f98bf0be477"},"schema_version":"1.0","source":{"id":"1803.10371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10371","created_at":"2026-05-18T00:19:55Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10371v1","created_at":"2026-05-18T00:19:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10371","created_at":"2026-05-18T00:19:55Z"},{"alias_kind":"pith_short_12","alias_value":"THIULSU32LDS","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"THIULSU32LDSV2UU","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"THIULSU3","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:5f47586d2a7e9bf0c964d216d59b11c86bf3a52739774fe0c17420526be388ef","target":"graph","created_at":"2026-05-18T00:19:55Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data collection methods. Model-based reinforcement learning methods provide an avenue to circumvent these challenges, but the traditional concern has been the mismatch between the simulator and the real world. Here, we show that control policies learned in simulation can successfully transfer to a physical system, composed of three Phantom robots pushing an object to v","authors_text":"Aravind Rajeswaran, Emanuel Todorov, Jeremy Dao, Kendall Lowrey, Svetoslav Kolev","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-28T01:12:46Z","title":"Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10371","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":"sha256:0e60acf9c70ee3f5311c76d34e516a6f2d11eceee72a246854bb74e7db706d5a","target":"record","created_at":"2026-05-18T00:19:55Z","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":"ce4d4a988c5b2e2d13a1dbf5236347cb75ac38b7173d780684c13c1f826a5f5a","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-28T01:12:46Z","title_canon_sha256":"6334416b1c079e1ae74c854a8b669bff20cfadcc2c7df94ac02d0f98bf0be477"},"schema_version":"1.0","source":{"id":"1803.10371","kind":"arxiv","version":1}},"canonical_sha256":"99d145ca9bd2c72aea94b186a92bbf2b0afac3566db5f26ce4d04467652396c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99d145ca9bd2c72aea94b186a92bbf2b0afac3566db5f26ce4d04467652396c0","first_computed_at":"2026-05-18T00:19:55.651623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:55.651623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"amFWGBrY4VyX1IrvX7qTP0LbsY+AHYavNWVfkVUBYg124E1HVA2SRU84TnZz+b59HUVrO64QsEmXoq+C2TTOAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:55.652370Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e60acf9c70ee3f5311c76d34e516a6f2d11eceee72a246854bb74e7db706d5a","sha256:5f47586d2a7e9bf0c964d216d59b11c86bf3a52739774fe0c17420526be388ef"],"state_sha256":"a07cd9e144cd17d15755cbd3f1923d7ab5e29b7704acc3a14297ae796be65fa5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XuwfBEa8FXbLin1CFqq/Wl+dQW1hv4NW7icLIY4vJi9HOGjKOLTKhtLRYpURvVbRaEwZWcdsw6qtCzZgo8W3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T02:03:25.598803Z","bundle_sha256":"c356422885ebde1550bf55bf13cc788d7dbba6ad2514f5d69707a70fd5f11eb7"}}