{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:D7LZO26H6IZTMQQHO76GNSBFR2","short_pith_number":"pith:D7LZO26H","canonical_record":{"source":{"id":"1809.04720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-13T00:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e5b34189ee7bc0ffd141ac09791e05912608b0d4b861f3763caaec53051f4b74","abstract_canon_sha256":"f0db0b885ad78da61619b600388696bb42d99b7e22ce533537abb905b08b6b5f"},"schema_version":"1.0"},"canonical_sha256":"1fd7976bc7f23336420777fc66c8258e8895bf952f16d3f35b17a9a682cad120","source":{"kind":"arxiv","id":"1809.04720","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04720","created_at":"2026-05-18T00:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04720v2","created_at":"2026-05-18T00:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04720","created_at":"2026-05-18T00:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"D7LZO26H6IZT","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D7LZO26H6IZTMQQH","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D7LZO26H","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:D7LZO26H6IZTMQQHO76GNSBFR2","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-13T00:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e5b34189ee7bc0ffd141ac09791e05912608b0d4b861f3763caaec53051f4b74","abstract_canon_sha256":"f0db0b885ad78da61619b600388696bb42d99b7e22ce533537abb905b08b6b5f"},"schema_version":"1.0"},"canonical_sha256":"1fd7976bc7f23336420777fc66c8258e8895bf952f16d3f35b17a9a682cad120","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:36.776624Z","signature_b64":"lqKBjadNKlerMi6TkEVeNQTSNVLO/8nfeOKm216PHCJmdU2p1fbnWXunLCbGN/XTCv2suqq1kxRY058GaEC3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fd7976bc7f23336420777fc66c8258e8895bf952f16d3f35b17a9a682cad120","last_reissued_at":"2026-05-18T00:05:36.776197Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:36.776197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04720","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":"2026-05-18T00:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zjA2IAC1mc9S5nDV0j40bFDHFO6avCaHno2erKp0MoVKSzSzGLpxdkbbLLG1x3N8pq9SSQdHdFBspkfrfskDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:58:41.172239Z"},"content_sha256":"012988e7f35bbff40d8ba5d088257c3bb2744c0e24c1f56a2d30970b4bbc2eb6","schema_version":"1.0","event_id":"sha256:012988e7f35bbff40d8ba5d088257c3bb2744c0e24c1f56a2d30970b4bbc2eb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:D7LZO26H6IZTMQQHO76GNSBFR2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Sullivan, Daniel Nikovski, Devesh Jha, Diego Romeres, Jeroen van Baar, Radu Cordorel","submitted_at":"2018-09-13T00:27:31Z","abstract_excerpt":"Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved, is that the amount of time a robot is occupied learning a task---rather than being productive---can be reduced by transferring the learned task to the real robot. Transfer learning requires some amount of fine-tuning on the real robot. For tasks which involve complex (non-linea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04720","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":""},"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":"2026-05-18T00:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pn/Rapsgit2P/BjB5LhyQMlTIdHfeIduHhBFl9vsSWIvPs4xosHoAknnKCqRbrhdILGlsPL0Og6PwkYBGn8qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:58:41.172909Z"},"content_sha256":"973ec1c9e16123e5f3e9d59ffabba41813dc87708568cf4f5035791c32a1a37d","schema_version":"1.0","event_id":"sha256:973ec1c9e16123e5f3e9d59ffabba41813dc87708568cf4f5035791c32a1a37d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7LZO26H6IZTMQQHO76GNSBFR2/bundle.json","state_url":"https://pith.science/pith/D7LZO26H6IZTMQQHO76GNSBFR2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7LZO26H6IZTMQQHO76GNSBFR2/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":"2026-05-26T11:58:41Z","links":{"resolver":"https://pith.science/pith/D7LZO26H6IZTMQQHO76GNSBFR2","bundle":"https://pith.science/pith/D7LZO26H6IZTMQQHO76GNSBFR2/bundle.json","state":"https://pith.science/pith/D7LZO26H6IZTMQQHO76GNSBFR2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7LZO26H6IZTMQQHO76GNSBFR2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:D7LZO26H6IZTMQQHO76GNSBFR2","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":"f0db0b885ad78da61619b600388696bb42d99b7e22ce533537abb905b08b6b5f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-13T00:27:31Z","title_canon_sha256":"e5b34189ee7bc0ffd141ac09791e05912608b0d4b861f3763caaec53051f4b74"},"schema_version":"1.0","source":{"id":"1809.04720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04720","created_at":"2026-05-18T00:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04720v2","created_at":"2026-05-18T00:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04720","created_at":"2026-05-18T00:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"D7LZO26H6IZT","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D7LZO26H6IZTMQQH","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D7LZO26H","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:973ec1c9e16123e5f3e9d59ffabba41813dc87708568cf4f5035791c32a1a37d","target":"graph","created_at":"2026-05-18T00:05:36Z","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":"Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved, is that the amount of time a robot is occupied learning a task---rather than being productive---can be reduced by transferring the learned task to the real robot. Transfer learning requires some amount of fine-tuning on the real robot. For tasks which involve complex (non-linea","authors_text":"Alan Sullivan, Daniel Nikovski, Devesh Jha, Diego Romeres, Jeroen van Baar, Radu Cordorel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-13T00:27:31Z","title":"Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04720","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":"sha256:012988e7f35bbff40d8ba5d088257c3bb2744c0e24c1f56a2d30970b4bbc2eb6","target":"record","created_at":"2026-05-18T00:05:36Z","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":"f0db0b885ad78da61619b600388696bb42d99b7e22ce533537abb905b08b6b5f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-13T00:27:31Z","title_canon_sha256":"e5b34189ee7bc0ffd141ac09791e05912608b0d4b861f3763caaec53051f4b74"},"schema_version":"1.0","source":{"id":"1809.04720","kind":"arxiv","version":2}},"canonical_sha256":"1fd7976bc7f23336420777fc66c8258e8895bf952f16d3f35b17a9a682cad120","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fd7976bc7f23336420777fc66c8258e8895bf952f16d3f35b17a9a682cad120","first_computed_at":"2026-05-18T00:05:36.776197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:36.776197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lqKBjadNKlerMi6TkEVeNQTSNVLO/8nfeOKm216PHCJmdU2p1fbnWXunLCbGN/XTCv2suqq1kxRY058GaEC3Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:36.776624Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:012988e7f35bbff40d8ba5d088257c3bb2744c0e24c1f56a2d30970b4bbc2eb6","sha256:973ec1c9e16123e5f3e9d59ffabba41813dc87708568cf4f5035791c32a1a37d"],"state_sha256":"d31fe9e89805ed3517483a7f3c0251c08bdfbb3b9b88ce70d2537bf7087abda3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cH7W08SuuD/mYznFSfXjKSbyRzLBHB0RT7Mk/YtLPz2VdZ4LBCt9Kb0+ARifH/mx8DFTUbgOdXT9NbLG9ov8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:58:41.175850Z","bundle_sha256":"c03ad4618a3ce4afc1794d30e9475b2a23e74bebcf95879fcac060cba87a4c69"}}