{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3XL6KRPY5Y62YNC36QIDKFNWX5","short_pith_number":"pith:3XL6KRPY","canonical_record":{"source":{"id":"1703.07261","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-21T15:13:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"898906c3e1f26eab35f7042ed3bd2f29f438d30f42fbc65f011aedb538b61a69","abstract_canon_sha256":"931a03ed9dde67df6e53a96edd7bdb2c2a59869c0eb6c3e6a2c2d3f1a06333a2"},"schema_version":"1.0"},"canonical_sha256":"ddd7e545f8ee3dac345bf4103515b6bf525e2ae9685705f11fafb3edd7256d76","source":{"kind":"arxiv","id":"1703.07261","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07261","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07261v2","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07261","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"3XL6KRPY5Y62","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3XL6KRPY5Y62YNC3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3XL6KRPY","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3XL6KRPY5Y62YNC36QIDKFNWX5","target":"record","payload":{"canonical_record":{"source":{"id":"1703.07261","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-21T15:13:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"898906c3e1f26eab35f7042ed3bd2f29f438d30f42fbc65f011aedb538b61a69","abstract_canon_sha256":"931a03ed9dde67df6e53a96edd7bdb2c2a59869c0eb6c3e6a2c2d3f1a06333a2"},"schema_version":"1.0"},"canonical_sha256":"ddd7e545f8ee3dac345bf4103515b6bf525e2ae9685705f11fafb3edd7256d76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.604578Z","signature_b64":"AScdeIQqRRxC5mU55WAn6ao2y20j/G9s8Z1uKleK2BAgyOOOixQ66IHf10ppGcweUu6SMQ5ETGjhlCdxA4Z7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddd7e545f8ee3dac345bf4103515b6bf525e2ae9685705f11fafb3edd7256d76","last_reissued_at":"2026-05-18T00:39:46.603852Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.603852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.07261","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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dTj8+PdCojNiXWiqPrQVq5doHCtDNTopv7J6bLiDaaLL+HNozjfYY+mXfn6ga8WJSPESDQWL/P49ExhZ1rcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:50:33.484786Z"},"content_sha256":"a1f7799f8b6476eeb7e7f823d9c827937cb6ecdf2c7ffd5669eb5271aaf39ea8","schema_version":"1.0","event_id":"sha256:a1f7799f8b6476eeb7e7f823d9c827937cb6ecdf2c7ffd5669eb5271aaf39ea8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3XL6KRPY5Y62YNC36QIDKFNWX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Black-Box Data-efficient Policy Search for Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dorian Goepp, Jean-Baptiste Mouret, Konstantinos Chatzilygeroudis, Rituraj Kaushik, Roberto Rama, Vassilis Vassiliades","submitted_at":"2017-03-21T15:13:04Z","abstract_excerpt":"The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on uncertain dynamical models: after each episode, they first learn a dynamical model of the robot, then they use an optimization algorithm to find a policy that maximizes the expected return given the model and its uncertainties. It is often believed that this optimization can be tractable only if analytical, gradient-based algorithms are used; however, these algorithms require using specific families of reward functions and policies, which greatly limits the flexibility of the overall approach. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07261","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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mV8pLDhXuQsJaonToqkoiSjRylbpwy8Oq5QPsJUIlIH4O2/kmQaoHk/Ol7836vx3vNrYC50eiNwkg0DxWHafDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:50:33.485423Z"},"content_sha256":"fe9fddaa7ee5a5e504adca4729f499f81cbe71184996bcb3d9b471f043ba6ba7","schema_version":"1.0","event_id":"sha256:fe9fddaa7ee5a5e504adca4729f499f81cbe71184996bcb3d9b471f043ba6ba7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XL6KRPY5Y62YNC36QIDKFNWX5/bundle.json","state_url":"https://pith.science/pith/3XL6KRPY5Y62YNC36QIDKFNWX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XL6KRPY5Y62YNC36QIDKFNWX5/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":"2026-06-07T21:50:33Z","links":{"resolver":"https://pith.science/pith/3XL6KRPY5Y62YNC36QIDKFNWX5","bundle":"https://pith.science/pith/3XL6KRPY5Y62YNC36QIDKFNWX5/bundle.json","state":"https://pith.science/pith/3XL6KRPY5Y62YNC36QIDKFNWX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XL6KRPY5Y62YNC36QIDKFNWX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3XL6KRPY5Y62YNC36QIDKFNWX5","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":"931a03ed9dde67df6e53a96edd7bdb2c2a59869c0eb6c3e6a2c2d3f1a06333a2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-21T15:13:04Z","title_canon_sha256":"898906c3e1f26eab35f7042ed3bd2f29f438d30f42fbc65f011aedb538b61a69"},"schema_version":"1.0","source":{"id":"1703.07261","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07261","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07261v2","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07261","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"3XL6KRPY5Y62","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3XL6KRPY5Y62YNC3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3XL6KRPY","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:fe9fddaa7ee5a5e504adca4729f499f81cbe71184996bcb3d9b471f043ba6ba7","target":"graph","created_at":"2026-05-18T00:39:46Z","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":"The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on uncertain dynamical models: after each episode, they first learn a dynamical model of the robot, then they use an optimization algorithm to find a policy that maximizes the expected return given the model and its uncertainties. It is often believed that this optimization can be tractable only if analytical, gradient-based algorithms are used; however, these algorithms require using specific families of reward functions and policies, which greatly limits the flexibility of the overall approach. In this p","authors_text":"Dorian Goepp, Jean-Baptiste Mouret, Konstantinos Chatzilygeroudis, Rituraj Kaushik, Roberto Rama, Vassilis Vassiliades","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-21T15:13:04Z","title":"Black-Box Data-efficient Policy Search for Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07261","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:a1f7799f8b6476eeb7e7f823d9c827937cb6ecdf2c7ffd5669eb5271aaf39ea8","target":"record","created_at":"2026-05-18T00:39:46Z","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":"931a03ed9dde67df6e53a96edd7bdb2c2a59869c0eb6c3e6a2c2d3f1a06333a2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-21T15:13:04Z","title_canon_sha256":"898906c3e1f26eab35f7042ed3bd2f29f438d30f42fbc65f011aedb538b61a69"},"schema_version":"1.0","source":{"id":"1703.07261","kind":"arxiv","version":2}},"canonical_sha256":"ddd7e545f8ee3dac345bf4103515b6bf525e2ae9685705f11fafb3edd7256d76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddd7e545f8ee3dac345bf4103515b6bf525e2ae9685705f11fafb3edd7256d76","first_computed_at":"2026-05-18T00:39:46.603852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:46.603852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AScdeIQqRRxC5mU55WAn6ao2y20j/G9s8Z1uKleK2BAgyOOOixQ66IHf10ppGcweUu6SMQ5ETGjhlCdxA4Z7BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:46.604578Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.07261","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f7799f8b6476eeb7e7f823d9c827937cb6ecdf2c7ffd5669eb5271aaf39ea8","sha256:fe9fddaa7ee5a5e504adca4729f499f81cbe71184996bcb3d9b471f043ba6ba7"],"state_sha256":"74a624814c959a9f1e30797e1ee5d7d42291a6834edefd9dc135bf4fc131ee8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eOtKPlU3GWUpRvgkx7ycD6OVvw90HZehCLekrgFFvnxN6IBkjHegckdll0Jrz/bNY+2iDuCcjgcNELN8+oelAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:50:33.488830Z","bundle_sha256":"e62871950f3f663d32ba9ebbc8d4d6f28fe9c179249696e8e93626e58845defe"}}