{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ODFUPPPT25BNHJ7XYAD2TGW5AK","short_pith_number":"pith:ODFUPPPT","canonical_record":{"source":{"id":"1902.04623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-12T20:31:43Z","cross_cats_sorted":[],"title_canon_sha256":"ca964d707e1417fed369a4837eb87f5ceb805ce9b56c75a0f8f76d5a81743f1d","abstract_canon_sha256":"d756053b081151b84e7ec7728c9aba4279ff8c48f755d7ddc851bfd4dafafca0"},"schema_version":"1.0"},"canonical_sha256":"70cb47bdf3d742d3a7f7c007a99add02a56a144013b3c98c8ff6f9b636b333fe","source":{"kind":"arxiv","id":"1902.04623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04623","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04623v1","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04623","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"ODFUPPPT25BN","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"ODFUPPPT25BNHJ7X","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"ODFUPPPT","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ODFUPPPT25BNHJ7XYAD2TGW5AK","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-12T20:31:43Z","cross_cats_sorted":[],"title_canon_sha256":"ca964d707e1417fed369a4837eb87f5ceb805ce9b56c75a0f8f76d5a81743f1d","abstract_canon_sha256":"d756053b081151b84e7ec7728c9aba4279ff8c48f755d7ddc851bfd4dafafca0"},"schema_version":"1.0"},"canonical_sha256":"70cb47bdf3d742d3a7f7c007a99add02a56a144013b3c98c8ff6f9b636b333fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.410473Z","signature_b64":"NNbT/6zCAkSl/QYfQh3KY/qcgxkxNwv+3CN6Pgy1nSytfi47m6fF9mkWHcLMItg8/qbichSTx/sQCjnt1HQvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70cb47bdf3d742d3a7f7c007a99add02a56a144013b3c98c8ff6f9b636b333fe","last_reissued_at":"2026-05-17T23:54:06.409859Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.409859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04623","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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnZct7XgSpDXZtlYuyhuXhEglxdCCCx37I/gVGN92AVQkhME6Dwcw8KLm1hBMXbNR4aAzlx28HLKqndckyCxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:21:47.318163Z"},"content_sha256":"e65d3edb71a1cfb81565a92c15135d8e453675bbe155647f48e01f50630a1d00","schema_version":"1.0","event_id":"sha256:e65d3edb71a1cfb81565a92c15135d8e453675bbe155647f48e01f50630a1d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ODFUPPPT25BNHJ7XYAD2TGW5AK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Value constrained model-free continuous control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abbas Abdolmaleki, Jonas Buchli, Michael Neunert, Nicolas Heess, Raia Hadsell, Steven Bohez","submitted_at":"2019-02-12T20:31:43Z","abstract_excerpt":"The naive application of Reinforcement Learning algorithms to continuous control problems -- such as locomotion and manipulation -- often results in policies which rely on high-amplitude, high-frequency control signals, known colloquially as bang-bang control. Although such solutions may indeed maximize task reward, they can be unsuitable for real world systems. Bang-bang control may lead to increased wear and tear or energy consumption, and tends to excite undesired second-order dynamics. To counteract this issue, multi-objective optimization can be used to simultaneously optimize both the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04623","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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2PpIqQ5Ug3tjR/UitQQRZXrnoYjVZ1+kUo2a4D3vHeyVZIrOIapz62t18LVxB9g7Y4sRKRyJ6hDq6uP6YvujAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:21:47.318519Z"},"content_sha256":"7697a8e0f0e16cbb2f34413707b971893b1520764c5c2f9e1fc4894317799852","schema_version":"1.0","event_id":"sha256:7697a8e0f0e16cbb2f34413707b971893b1520764c5c2f9e1fc4894317799852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK/bundle.json","state_url":"https://pith.science/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK/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":"2026-05-30T13:21:47Z","links":{"resolver":"https://pith.science/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK","bundle":"https://pith.science/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK/bundle.json","state":"https://pith.science/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ODFUPPPT25BNHJ7XYAD2TGW5AK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ODFUPPPT25BNHJ7XYAD2TGW5AK","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":"d756053b081151b84e7ec7728c9aba4279ff8c48f755d7ddc851bfd4dafafca0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-12T20:31:43Z","title_canon_sha256":"ca964d707e1417fed369a4837eb87f5ceb805ce9b56c75a0f8f76d5a81743f1d"},"schema_version":"1.0","source":{"id":"1902.04623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04623","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04623v1","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04623","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"ODFUPPPT25BN","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"ODFUPPPT25BNHJ7X","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"ODFUPPPT","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:7697a8e0f0e16cbb2f34413707b971893b1520764c5c2f9e1fc4894317799852","target":"graph","created_at":"2026-05-17T23:54:06Z","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 naive application of Reinforcement Learning algorithms to continuous control problems -- such as locomotion and manipulation -- often results in policies which rely on high-amplitude, high-frequency control signals, known colloquially as bang-bang control. Although such solutions may indeed maximize task reward, they can be unsuitable for real world systems. Bang-bang control may lead to increased wear and tear or energy consumption, and tends to excite undesired second-order dynamics. To counteract this issue, multi-objective optimization can be used to simultaneously optimize both the re","authors_text":"Abbas Abdolmaleki, Jonas Buchli, Michael Neunert, Nicolas Heess, Raia Hadsell, Steven Bohez","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-12T20:31:43Z","title":"Value constrained model-free continuous control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04623","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:e65d3edb71a1cfb81565a92c15135d8e453675bbe155647f48e01f50630a1d00","target":"record","created_at":"2026-05-17T23:54:06Z","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":"d756053b081151b84e7ec7728c9aba4279ff8c48f755d7ddc851bfd4dafafca0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-12T20:31:43Z","title_canon_sha256":"ca964d707e1417fed369a4837eb87f5ceb805ce9b56c75a0f8f76d5a81743f1d"},"schema_version":"1.0","source":{"id":"1902.04623","kind":"arxiv","version":1}},"canonical_sha256":"70cb47bdf3d742d3a7f7c007a99add02a56a144013b3c98c8ff6f9b636b333fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70cb47bdf3d742d3a7f7c007a99add02a56a144013b3c98c8ff6f9b636b333fe","first_computed_at":"2026-05-17T23:54:06.409859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:06.409859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NNbT/6zCAkSl/QYfQh3KY/qcgxkxNwv+3CN6Pgy1nSytfi47m6fF9mkWHcLMItg8/qbichSTx/sQCjnt1HQvDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:06.410473Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e65d3edb71a1cfb81565a92c15135d8e453675bbe155647f48e01f50630a1d00","sha256:7697a8e0f0e16cbb2f34413707b971893b1520764c5c2f9e1fc4894317799852"],"state_sha256":"55a28eb24792a8fe57339d4a16cd1a8581fad24b645018117a44774ab26aa89b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VsylLK8D3nAKpThLe2QhwOVRaeLeFZRIW39cf1foRwu9LjJe3bhTFf0fYCLaEWOJOJF2erX9sCN0UIV4XX+gCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:21:47.320687Z","bundle_sha256":"5658f4beb4eef47c8a7e0c2ccd06b45c679b6bb07e021549d86263d329952de1"}}