{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OCPVRAVHI3EV3MCDVHOT4JBETK","short_pith_number":"pith:OCPVRAVH","canonical_record":{"source":{"id":"1710.00022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-29T18:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"647f435de683c902d88b6cd06e654287c292379a8a0ef1aaa5763e60a7d9cdab","abstract_canon_sha256":"c67fbc9c108c3fdcc3eeb72415a75fd047dd0a9e61c69310b0fdefd5a657883b"},"schema_version":"1.0"},"canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","source":{"kind":"arxiv","id":"1710.00022","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00022","created_at":"2026-05-18T00:08:55Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00022v2","created_at":"2026-05-18T00:08:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00022","created_at":"2026-05-18T00:08:55Z"},{"alias_kind":"pith_short_12","alias_value":"OCPVRAVHI3EV","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OCPVRAVHI3EV3MCD","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OCPVRAVH","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OCPVRAVHI3EV3MCDVHOT4JBETK","target":"record","payload":{"canonical_record":{"source":{"id":"1710.00022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-29T18:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"647f435de683c902d88b6cd06e654287c292379a8a0ef1aaa5763e60a7d9cdab","abstract_canon_sha256":"c67fbc9c108c3fdcc3eeb72415a75fd047dd0a9e61c69310b0fdefd5a657883b"},"schema_version":"1.0"},"canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:55.093011Z","signature_b64":"158TOLmQq+sat4EFC/6HI1O9fBnvgcFMERTXsIsaRvpI7tELwIdbIcmk6vn33f+mU1HQIO3p7zOnCUK1s5OMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","last_reissued_at":"2026-05-18T00:08:55.092524Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:55.092524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.00022","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":"2026-05-18T00:08:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jyaZ3pwnvxakXHNRHYIjCRXnTUB2PSd+umCGiGtpcueKnx3KRzF04PEK5ZmQGBvXYf8DutvULPqgMO8M+sYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:46:07.582868Z"},"content_sha256":"e059ab928f64d23c81e533b4f7d30fed287b8fb61b1efd58150c131cbd480c5b","schema_version":"1.0","event_id":"sha256:e059ab928f64d23c81e533b4f7d30fed287b8fb61b1efd58150c131cbd480c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OCPVRAVHI3EV3MCDVHOT4JBETK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Structured Neural Network Policy for a Hopping Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Herzog, Jules Kozolinsky, Julian Viereck, Ludovic Righetti","submitted_at":"2017-09-29T18:35:54Z","abstract_excerpt":"In this work we present a method for learning a reactive policy for a simple dynamic locomotion task involving hard impact and switching contacts where we assume the contact location and contact timing to be unknown. To learn such a policy, we use optimal control to optimize a local controller for a fixed environment and contacts. We learn the contact-rich dynamics for our underactuated systems along these trajectories in a sample efficient manner. We use the optimized policies to learn the reactive policy in form of a neural network. Using a new neural network architecture, we are able to pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00022","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":"2026-05-18T00:08:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ll6ZTXiQltb5ae6CHcd5UAsK7lYkVVI1oIXfqWbxyRMTG39SL1JTYjlg4xd0MrFgWMBIcN5nK9bRfq+ttACwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:46:07.583204Z"},"content_sha256":"0543f9917f4ce5812dce275f948e15cd73e23ab9f7793a11b72b61b3b4f17767","schema_version":"1.0","event_id":"sha256:0543f9917f4ce5812dce275f948e15cd73e23ab9f7793a11b72b61b3b4f17767"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/bundle.json","state_url":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/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":"2026-06-01T06:46:07Z","links":{"resolver":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK","bundle":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/bundle.json","state":"https://pith.science/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCPVRAVHI3EV3MCDVHOT4JBETK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OCPVRAVHI3EV3MCDVHOT4JBETK","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":"c67fbc9c108c3fdcc3eeb72415a75fd047dd0a9e61c69310b0fdefd5a657883b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-29T18:35:54Z","title_canon_sha256":"647f435de683c902d88b6cd06e654287c292379a8a0ef1aaa5763e60a7d9cdab"},"schema_version":"1.0","source":{"id":"1710.00022","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00022","created_at":"2026-05-18T00:08:55Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00022v2","created_at":"2026-05-18T00:08:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00022","created_at":"2026-05-18T00:08:55Z"},{"alias_kind":"pith_short_12","alias_value":"OCPVRAVHI3EV","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OCPVRAVHI3EV3MCD","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OCPVRAVH","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:0543f9917f4ce5812dce275f948e15cd73e23ab9f7793a11b72b61b3b4f17767","target":"graph","created_at":"2026-05-18T00:08:55Z","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":"In this work we present a method for learning a reactive policy for a simple dynamic locomotion task involving hard impact and switching contacts where we assume the contact location and contact timing to be unknown. To learn such a policy, we use optimal control to optimize a local controller for a fixed environment and contacts. We learn the contact-rich dynamics for our underactuated systems along these trajectories in a sample efficient manner. We use the optimized policies to learn the reactive policy in form of a neural network. Using a new neural network architecture, we are able to pre","authors_text":"Alexander Herzog, Jules Kozolinsky, Julian Viereck, Ludovic Righetti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-29T18:35:54Z","title":"Learning a Structured Neural Network Policy for a Hopping Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00022","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:e059ab928f64d23c81e533b4f7d30fed287b8fb61b1efd58150c131cbd480c5b","target":"record","created_at":"2026-05-18T00:08:55Z","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":"c67fbc9c108c3fdcc3eeb72415a75fd047dd0a9e61c69310b0fdefd5a657883b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-29T18:35:54Z","title_canon_sha256":"647f435de683c902d88b6cd06e654287c292379a8a0ef1aaa5763e60a7d9cdab"},"schema_version":"1.0","source":{"id":"1710.00022","kind":"arxiv","version":2}},"canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"709f5882a746c95db043a9dd3e24249ab8f7789bdaeda05ac10f4a62602f2d4c","first_computed_at":"2026-05-18T00:08:55.092524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:55.092524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"158TOLmQq+sat4EFC/6HI1O9fBnvgcFMERTXsIsaRvpI7tELwIdbIcmk6vn33f+mU1HQIO3p7zOnCUK1s5OMCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:55.093011Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.00022","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e059ab928f64d23c81e533b4f7d30fed287b8fb61b1efd58150c131cbd480c5b","sha256:0543f9917f4ce5812dce275f948e15cd73e23ab9f7793a11b72b61b3b4f17767"],"state_sha256":"f8e40cd32065720b3a5111fdf57556eb3f3613ae178162bd3923cab8ee9ef388"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrP073g6TtsV9oW4xXXfuSCLOLQ6GIsO/BiR3hTcmbbMqU7EElfjxeR8aoFVRMoAmjOjrarZ4YxU+yRcPc+wAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:46:07.586240Z","bundle_sha256":"ef22f62761aed372f7f5b55984588c2d07f829a8a59930a6e7a7d6f49bacf498"}}