{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WLNQ3VVKL2AUI7FQR24TLQN673","short_pith_number":"pith:WLNQ3VVK","canonical_record":{"source":{"id":"1810.05751","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-12T22:53:30Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"c86712528feb372c2488a34b45f129ad29277a1e0e25ebc3b4fc98389737e7dc","abstract_canon_sha256":"7a25ad7756fd38785311927e44364c3ef6a6eb53cb343a6039e58e6db95fa7dc"},"schema_version":"1.0"},"canonical_sha256":"b2db0dd6aa5e81447cb08eb935c1befefa1594d9bc2bdef4f401c32bc4ddd7d8","source":{"kind":"arxiv","id":"1810.05751","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05751","created_at":"2026-05-17T23:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05751v2","created_at":"2026-05-17T23:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05751","created_at":"2026-05-17T23:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"WLNQ3VVKL2AU","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WLNQ3VVKL2AUI7FQ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WLNQ3VVK","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WLNQ3VVKL2AUI7FQR24TLQN673","target":"record","payload":{"canonical_record":{"source":{"id":"1810.05751","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-12T22:53:30Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"c86712528feb372c2488a34b45f129ad29277a1e0e25ebc3b4fc98389737e7dc","abstract_canon_sha256":"7a25ad7756fd38785311927e44364c3ef6a6eb53cb343a6039e58e6db95fa7dc"},"schema_version":"1.0"},"canonical_sha256":"b2db0dd6aa5e81447cb08eb935c1befefa1594d9bc2bdef4f401c32bc4ddd7d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:14.042620Z","signature_b64":"Z23qUgEjVytfOMak3LY69mZSVF5d2zL3MMrST7Bh0c+vfp6AMjlMlC7QGgleRRyUElXA73IoT5FrtJKfiMovDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2db0dd6aa5e81447cb08eb935c1befefa1594d9bc2bdef4f401c32bc4ddd7d8","last_reissued_at":"2026-05-17T23:59:14.042163Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:14.042163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.05751","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":"2026-05-17T23:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AottVi5oGh7MMbUlozS9gB/17v5RMXq8MwEC2xoRsPOKVZH7WWmYxPLxUrLOXmFBVDW7HfZPdNhAJvrseRwIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:54:13.824425Z"},"content_sha256":"cc72d15a7a1a58608491d2903277ae1f00421e9436807cff218c91f732aaa49f","schema_version":"1.0","event_id":"sha256:cc72d15a7a1a58608491d2903277ae1f00421e9436807cff218c91f732aaa49f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WLNQ3VVKL2AUI7FQR24TLQN673","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Transfer with Strategy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"C. Karen Liu, Greg Turk, Wenhao Yu","submitted_at":"2018-10-12T22:53:30Z","abstract_excerpt":"Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to the differences between the two environments. Transfer learning using domain randomization is a promising approach, but it usually assumes that the target environment is close to the distribution of the training environments, thus relying heavily on accurate system identification. In this paper, we present a different approach that leverages domain randomiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05751","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":"2026-05-17T23:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TXfKcLkWTmUfx7/7XNZRiv8QqhJURkxTYFv41htGokI3uJmmdlNCfBR1fQp4GeJ/RK/faL+8cGxROkiNMZkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:54:13.825014Z"},"content_sha256":"33ac75c3b68c54ae4e20f8ec6db6560d11470130b28878656f6c2c1d504898dd","schema_version":"1.0","event_id":"sha256:33ac75c3b68c54ae4e20f8ec6db6560d11470130b28878656f6c2c1d504898dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLNQ3VVKL2AUI7FQR24TLQN673/bundle.json","state_url":"https://pith.science/pith/WLNQ3VVKL2AUI7FQR24TLQN673/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLNQ3VVKL2AUI7FQR24TLQN673/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":"2026-05-25T22:54:13Z","links":{"resolver":"https://pith.science/pith/WLNQ3VVKL2AUI7FQR24TLQN673","bundle":"https://pith.science/pith/WLNQ3VVKL2AUI7FQR24TLQN673/bundle.json","state":"https://pith.science/pith/WLNQ3VVKL2AUI7FQR24TLQN673/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLNQ3VVKL2AUI7FQR24TLQN673/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WLNQ3VVKL2AUI7FQR24TLQN673","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":"7a25ad7756fd38785311927e44364c3ef6a6eb53cb343a6039e58e6db95fa7dc","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-12T22:53:30Z","title_canon_sha256":"c86712528feb372c2488a34b45f129ad29277a1e0e25ebc3b4fc98389737e7dc"},"schema_version":"1.0","source":{"id":"1810.05751","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05751","created_at":"2026-05-17T23:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05751v2","created_at":"2026-05-17T23:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05751","created_at":"2026-05-17T23:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"WLNQ3VVKL2AU","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WLNQ3VVKL2AUI7FQ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WLNQ3VVK","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:33ac75c3b68c54ae4e20f8ec6db6560d11470130b28878656f6c2c1d504898dd","target":"graph","created_at":"2026-05-17T23:59:14Z","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":"Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to the differences between the two environments. Transfer learning using domain randomization is a promising approach, but it usually assumes that the target environment is close to the distribution of the training environments, thus relying heavily on accurate system identification. In this paper, we present a different approach that leverages domain randomiz","authors_text":"C. Karen Liu, Greg Turk, Wenhao Yu","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-12T22:53:30Z","title":"Policy Transfer with Strategy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05751","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:cc72d15a7a1a58608491d2903277ae1f00421e9436807cff218c91f732aaa49f","target":"record","created_at":"2026-05-17T23:59:14Z","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":"7a25ad7756fd38785311927e44364c3ef6a6eb53cb343a6039e58e6db95fa7dc","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-12T22:53:30Z","title_canon_sha256":"c86712528feb372c2488a34b45f129ad29277a1e0e25ebc3b4fc98389737e7dc"},"schema_version":"1.0","source":{"id":"1810.05751","kind":"arxiv","version":2}},"canonical_sha256":"b2db0dd6aa5e81447cb08eb935c1befefa1594d9bc2bdef4f401c32bc4ddd7d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2db0dd6aa5e81447cb08eb935c1befefa1594d9bc2bdef4f401c32bc4ddd7d8","first_computed_at":"2026-05-17T23:59:14.042163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:14.042163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z23qUgEjVytfOMak3LY69mZSVF5d2zL3MMrST7Bh0c+vfp6AMjlMlC7QGgleRRyUElXA73IoT5FrtJKfiMovDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:14.042620Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.05751","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc72d15a7a1a58608491d2903277ae1f00421e9436807cff218c91f732aaa49f","sha256:33ac75c3b68c54ae4e20f8ec6db6560d11470130b28878656f6c2c1d504898dd"],"state_sha256":"e3eba3fec13b93563d711d4e543cea68bb0444cfdeb0dd8604731e583ad675f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TD3UYYJPdsgRWK3xLmCfpDg02BUNmgj2z1EQUjDqdBP1cpGxJPD0571PnpgaexWACjTMTlO7rx0eLaXfEz7VCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:54:13.829052Z","bundle_sha256":"14cd4907e15f46f684aa26a2ee41bd2f6f32c53f63c6152db660b11473414df4"}}