{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FC7QROGDA56R2ZWRBCRMDQLFWT","short_pith_number":"pith:FC7QROGD","canonical_record":{"source":{"id":"2006.01952","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-02T21:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"b39624592c357043d252b924a53fdf20f604ac89e38a46b1d603c0e32d1c465e","abstract_canon_sha256":"c55f41e8f4ba7ea995adf6b640d52c47fb4748a45dde3d5c35661ca40f38ae5a"},"schema_version":"1.0"},"canonical_sha256":"28bf08b8c3077d1d66d108a2c1c165b4e9eae21905b2b53b070a5c72258d67f6","source":{"kind":"arxiv","id":"2006.01952","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01952","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01952v2","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01952","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"pith_short_12","alias_value":"FC7QROGDA56R","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"pith_short_16","alias_value":"FC7QROGDA56R2ZWR","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"pith_short_8","alias_value":"FC7QROGD","created_at":"2026-07-05T01:49:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FC7QROGDA56R2ZWRBCRMDQLFWT","target":"record","payload":{"canonical_record":{"source":{"id":"2006.01952","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-02T21:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"b39624592c357043d252b924a53fdf20f604ac89e38a46b1d603c0e32d1c465e","abstract_canon_sha256":"c55f41e8f4ba7ea995adf6b640d52c47fb4748a45dde3d5c35661ca40f38ae5a"},"schema_version":"1.0"},"canonical_sha256":"28bf08b8c3077d1d66d108a2c1c165b4e9eae21905b2b53b070a5c72258d67f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:37.038419Z","signature_b64":"nU+vnSmALSiqCSwXxzJdGkUIqYNQBKbdf8C/piyT6wRUNO04aKxBd4mpbJMHnKr+knuyWcz4IVrbvHFK+b78Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28bf08b8c3077d1d66d108a2c1c165b4e9eae21905b2b53b070a5c72258d67f6","last_reissued_at":"2026-07-05T01:49:37.037908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:37.037908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.01952","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":"2026-07-05T01:49:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTSkdaGwziAfq8CDYgei1xZI8d57XHjaFOVjGe7I92SLyTaddVteer2pI3V51Cljtg8vJ17uDuwaKFG1lJFHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:02:34.159006Z"},"content_sha256":"551192ccf1c35e839dfe0bce3dfbebac1f8a2f2c9ce7a71e2300dc44efc557dc","schema_version":"1.0","event_id":"sha256:551192ccf1c35e839dfe0bce3dfbebac1f8a2f2c9ce7a71e2300dc44efc557dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FC7QROGDA56R2ZWRBCRMDQLFWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Active Task-Oriented Exploration Policies for Bridging the Sim-to-Real Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jacky Liang, Oliver Kroemer, Saumya Saxena","submitted_at":"2020-06-02T21:32:58Z","abstract_excerpt":"Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The former is sensitive to the manually-specified training distribution of dynamics parameters and can result in behaviors that are overly conservative. The latter requires learning policies that concurrently perform the task and generate useful trajectories for system identification. In this work, we propose and analyze a framework for learning exploration polici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01952","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/2006.01952/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":"2026-07-05T01:49:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76EoHfWIumHkjvZXA4+HIsRzAjXvOzwozS+g1g8MyG8jxrfGXG5vuJ15lj23+xtsWAJ1qfNoG7OFbUR2V6wMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:02:34.159983Z"},"content_sha256":"c2b9e987ae2e4dec8a45f65cd27e7034f63295cf795dc6f81ec5a19e64ce0482","schema_version":"1.0","event_id":"sha256:c2b9e987ae2e4dec8a45f65cd27e7034f63295cf795dc6f81ec5a19e64ce0482"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FC7QROGDA56R2ZWRBCRMDQLFWT/bundle.json","state_url":"https://pith.science/pith/FC7QROGDA56R2ZWRBCRMDQLFWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FC7QROGDA56R2ZWRBCRMDQLFWT/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":"2026-08-04T11:02:34Z","links":{"resolver":"https://pith.science/pith/FC7QROGDA56R2ZWRBCRMDQLFWT","bundle":"https://pith.science/pith/FC7QROGDA56R2ZWRBCRMDQLFWT/bundle.json","state":"https://pith.science/pith/FC7QROGDA56R2ZWRBCRMDQLFWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FC7QROGDA56R2ZWRBCRMDQLFWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FC7QROGDA56R2ZWRBCRMDQLFWT","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":"c55f41e8f4ba7ea995adf6b640d52c47fb4748a45dde3d5c35661ca40f38ae5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-02T21:32:58Z","title_canon_sha256":"b39624592c357043d252b924a53fdf20f604ac89e38a46b1d603c0e32d1c465e"},"schema_version":"1.0","source":{"id":"2006.01952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01952","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01952v2","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01952","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"pith_short_12","alias_value":"FC7QROGDA56R","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"pith_short_16","alias_value":"FC7QROGDA56R2ZWR","created_at":"2026-07-05T01:49:37Z"},{"alias_kind":"pith_short_8","alias_value":"FC7QROGD","created_at":"2026-07-05T01:49:37Z"}],"graph_snapshots":[{"event_id":"sha256:c2b9e987ae2e4dec8a45f65cd27e7034f63295cf795dc6f81ec5a19e64ce0482","target":"graph","created_at":"2026-07-05T01:49:37Z","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/2006.01952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The former is sensitive to the manually-specified training distribution of dynamics parameters and can result in behaviors that are overly conservative. The latter requires learning policies that concurrently perform the task and generate useful trajectories for system identification. In this work, we propose and analyze a framework for learning exploration polici","authors_text":"Jacky Liang, Oliver Kroemer, Saumya Saxena","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-02T21:32:58Z","title":"Learning Active Task-Oriented Exploration Policies for Bridging the Sim-to-Real Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01952","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":"sha256:551192ccf1c35e839dfe0bce3dfbebac1f8a2f2c9ce7a71e2300dc44efc557dc","target":"record","created_at":"2026-07-05T01:49:37Z","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":"c55f41e8f4ba7ea995adf6b640d52c47fb4748a45dde3d5c35661ca40f38ae5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-02T21:32:58Z","title_canon_sha256":"b39624592c357043d252b924a53fdf20f604ac89e38a46b1d603c0e32d1c465e"},"schema_version":"1.0","source":{"id":"2006.01952","kind":"arxiv","version":2}},"canonical_sha256":"28bf08b8c3077d1d66d108a2c1c165b4e9eae21905b2b53b070a5c72258d67f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28bf08b8c3077d1d66d108a2c1c165b4e9eae21905b2b53b070a5c72258d67f6","first_computed_at":"2026-07-05T01:49:37.037908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:37.037908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nU+vnSmALSiqCSwXxzJdGkUIqYNQBKbdf8C/piyT6wRUNO04aKxBd4mpbJMHnKr+knuyWcz4IVrbvHFK+b78Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:37.038419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.01952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:551192ccf1c35e839dfe0bce3dfbebac1f8a2f2c9ce7a71e2300dc44efc557dc","sha256:c2b9e987ae2e4dec8a45f65cd27e7034f63295cf795dc6f81ec5a19e64ce0482"],"state_sha256":"8f8a1725657612bd100d9a6bc8f6c784daeb45bdf068d6cb9a93a6ea4c6c3e6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xdsEuhGjWn1qaVC2CwuK9vPOBBDrnEul2TC1t/3qAB+iHpAHQsdwYxaWlHQClPSeWjl/81cSWJiz3kvdHZFgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:02:34.166742Z","bundle_sha256":"be7c785403c15d670fb71808c5b624e38d4c750640a3da7164324fd574c566a9"}}