{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:I6BZMCFQR3O62R4GQXKECUAJ6Z","short_pith_number":"pith:I6BZMCFQ","canonical_record":{"source":{"id":"1809.07731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T16:46:04Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"a6b2996cdec611ae586337e9f3f6c52b85c9d367e9bfd84f81c2fe69d313f188","abstract_canon_sha256":"0e10f4d46601969da5d324f99da2577f5c366351462287fd1993fce001bf30c7"},"schema_version":"1.0"},"canonical_sha256":"47839608b08edded478685d4415009f6641ea4c0528d99bc5a608860007ed4b5","source":{"kind":"arxiv","id":"1809.07731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07731","created_at":"2026-05-18T00:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07731v1","created_at":"2026-05-18T00:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07731","created_at":"2026-05-18T00:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"I6BZMCFQR3O6","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I6BZMCFQR3O62R4G","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I6BZMCFQ","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:I6BZMCFQR3O62R4GQXKECUAJ6Z","target":"record","payload":{"canonical_record":{"source":{"id":"1809.07731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T16:46:04Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"a6b2996cdec611ae586337e9f3f6c52b85c9d367e9bfd84f81c2fe69d313f188","abstract_canon_sha256":"0e10f4d46601969da5d324f99da2577f5c366351462287fd1993fce001bf30c7"},"schema_version":"1.0"},"canonical_sha256":"47839608b08edded478685d4415009f6641ea4c0528d99bc5a608860007ed4b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:15.316672Z","signature_b64":"J3zP4DYmRtcycxryPHJWRNg4YehE9SeyCjmu+grGkTw13L9MNR6KfIjQ7SwkmdVZhlKDXdQ/1Uzxb7qgZUkkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47839608b08edded478685d4415009f6641ea4c0528d99bc5a608860007ed4b5","last_reissued_at":"2026-05-18T00:05:15.316154Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:15.316154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.07731","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":"2026-05-18T00:05:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOuz9fGU2r/Zq2uH2tv+MXEwv+wxVk9iZtvA/vZ2helkIWFiIWWJdrcza9AfR6jN6A7qLhIVoeb/Vpoyvol7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:33:10.499507Z"},"content_sha256":"56db42919f05bde3effefb9318917fa8297e577f1a5ba0da3fba47333982a1b1","schema_version":"1.0","event_id":"sha256:56db42919f05bde3effefb9318917fa8297e577f1a5ba0da3fba47333982a1b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:I6BZMCFQR3O62R4GQXKECUAJ6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Reinforcement Learning Algorithms on Real-World Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Dmytro Korenkevych, Gautham Vasan, James Bergstra, William Ma","submitted_at":"2018-09-20T16:46:04Z","abstract_excerpt":"Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on these results due to open source implementations of learning algorithms and simulated benchmark tasks. To carry forward these successes to real-world applications, it is crucial to withhold utilizing the unique advantages of simulations that do not transfer to the real world and experiment directly with physical robots. However, reinforcement learning research"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07731","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":"2026-05-18T00:05:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCt/hR/Ep1yLfKzNIx36cpbrnDFCnI1HFa9MbWbluQRX4JJ/J+aBewzWCtqL00d+jTOyrLhiybKjmbyKyQFwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:33:10.499861Z"},"content_sha256":"ce8faf5a9a790313faf0cbabca70f286c74b575e50f87ba7c7ed2ce1cee37105","schema_version":"1.0","event_id":"sha256:ce8faf5a9a790313faf0cbabca70f286c74b575e50f87ba7c7ed2ce1cee37105"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z/bundle.json","state_url":"https://pith.science/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z/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":"2026-05-26T19:33:10Z","links":{"resolver":"https://pith.science/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z","bundle":"https://pith.science/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z/bundle.json","state":"https://pith.science/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6BZMCFQR3O62R4GQXKECUAJ6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I6BZMCFQR3O62R4GQXKECUAJ6Z","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":"0e10f4d46601969da5d324f99da2577f5c366351462287fd1993fce001bf30c7","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T16:46:04Z","title_canon_sha256":"a6b2996cdec611ae586337e9f3f6c52b85c9d367e9bfd84f81c2fe69d313f188"},"schema_version":"1.0","source":{"id":"1809.07731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07731","created_at":"2026-05-18T00:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07731v1","created_at":"2026-05-18T00:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07731","created_at":"2026-05-18T00:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"I6BZMCFQR3O6","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I6BZMCFQR3O62R4G","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I6BZMCFQ","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:ce8faf5a9a790313faf0cbabca70f286c74b575e50f87ba7c7ed2ce1cee37105","target":"graph","created_at":"2026-05-18T00:05:15Z","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":"Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on these results due to open source implementations of learning algorithms and simulated benchmark tasks. To carry forward these successes to real-world applications, it is crucial to withhold utilizing the unique advantages of simulations that do not transfer to the real world and experiment directly with physical robots. However, reinforcement learning research","authors_text":"A. Rupam Mahmood, Dmytro Korenkevych, Gautham Vasan, James Bergstra, William Ma","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T16:46:04Z","title":"Benchmarking Reinforcement Learning Algorithms on Real-World Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07731","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":"sha256:56db42919f05bde3effefb9318917fa8297e577f1a5ba0da3fba47333982a1b1","target":"record","created_at":"2026-05-18T00:05:15Z","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":"0e10f4d46601969da5d324f99da2577f5c366351462287fd1993fce001bf30c7","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T16:46:04Z","title_canon_sha256":"a6b2996cdec611ae586337e9f3f6c52b85c9d367e9bfd84f81c2fe69d313f188"},"schema_version":"1.0","source":{"id":"1809.07731","kind":"arxiv","version":1}},"canonical_sha256":"47839608b08edded478685d4415009f6641ea4c0528d99bc5a608860007ed4b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47839608b08edded478685d4415009f6641ea4c0528d99bc5a608860007ed4b5","first_computed_at":"2026-05-18T00:05:15.316154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:15.316154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J3zP4DYmRtcycxryPHJWRNg4YehE9SeyCjmu+grGkTw13L9MNR6KfIjQ7SwkmdVZhlKDXdQ/1Uzxb7qgZUkkCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:15.316672Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.07731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56db42919f05bde3effefb9318917fa8297e577f1a5ba0da3fba47333982a1b1","sha256:ce8faf5a9a790313faf0cbabca70f286c74b575e50f87ba7c7ed2ce1cee37105"],"state_sha256":"736cee0b7a1c9416f30c60c67d7a8ccec85d7395af9487a11260956bbb0c62af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVGSxISZmTotdMwwRD5XbwOa5n9isHEYin24K6q/sjkq+Ln4hyBzuY1CH3bbaVVdwgtFNc15DkbcPxEwx6URCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:33:10.502177Z","bundle_sha256":"6bf69082a9c389358a2c9d5d106d8790d04d1a1fccc4c6bfc9b27fe26b8b4209"}}