{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MGOF76JJ3IXNP7FVZXAOXHO5RY","short_pith_number":"pith:MGOF76JJ","canonical_record":{"source":{"id":"1908.08659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-23T04:26:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a5d6560c1c58ea32a7aecd1cd11f790aaf6af91551cef4146cd062e2cdba8c3","abstract_canon_sha256":"5d0faa87f403446dc79a461c855de231c2f3ee7bc46c7a9442d6347a97ebb44f"},"schema_version":"1.0"},"canonical_sha256":"619c5ff929da2ed7fcb5cdc0eb9ddd8e08f19a918e2d6c6d40d3c1fe9b5df756","source":{"kind":"arxiv","id":"1908.08659","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08659","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08659v1","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08659","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"pith_short_12","alias_value":"MGOF76JJ3IXN","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"pith_short_16","alias_value":"MGOF76JJ3IXNP7FV","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"pith_short_8","alias_value":"MGOF76JJ","created_at":"2026-07-04T23:59:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MGOF76JJ3IXNP7FVZXAOXHO5RY","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-23T04:26:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a5d6560c1c58ea32a7aecd1cd11f790aaf6af91551cef4146cd062e2cdba8c3","abstract_canon_sha256":"5d0faa87f403446dc79a461c855de231c2f3ee7bc46c7a9442d6347a97ebb44f"},"schema_version":"1.0"},"canonical_sha256":"619c5ff929da2ed7fcb5cdc0eb9ddd8e08f19a918e2d6c6d40d3c1fe9b5df756","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:16.593639Z","signature_b64":"CK8t7Ui6aact+hVDPOc7EuNNBJK7N9oKKGfxzfWRG7HcYKWmrGkSndQao9Ige+hlYhvPnOkDERd5Lob1y4rtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"619c5ff929da2ed7fcb5cdc0eb9ddd8e08f19a918e2d6c6d40d3c1fe9b5df756","last_reissued_at":"2026-07-04T23:59:16.593204Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:16.593204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08659","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":"2026-07-04T23:59:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n19xd6Fsc0J6r4WIa4wX2o7hV0x6lrAk/dk9UecWpqCfEKH+LydY+U+phRAWzbkMz04uOMjN6ulG1nDysjHRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T06:43:27.360295Z"},"content_sha256":"8692e22ef546148c18cd69016a8ee18140cb3cac4fbed8f43f8d68d438a61d8c","schema_version":"1.0","event_id":"sha256:8692e22ef546148c18cd69016a8ee18140cb3cac4fbed8f43f8d68d438a61d8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MGOF76JJ3IXNP7FVZXAOXHO5RY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison of Action Spaces for Learning Manipulation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Lev Grossman, Patrick Varin, Scott Kuindersma","submitted_at":"2019-08-23T04:26:26Z","abstract_excerpt":"Designing reinforcement learning (RL) problems that can produce delicate and precise manipulation policies requires careful choice of the reward function, state, and action spaces. Much prior work on applying RL to manipulation tasks has defined the action space in terms of direct joint torques or reference positions for a joint-space proportional derivative (PD) controller. In practice, it is often possible to add additional structure by taking advantage of model-based controllers that support both accurate positioning and control of the dynamic response of the manipulator. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08659","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.08659/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":"2026-07-04T23:59:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h5AKkglJ4RfxhfaggNo7rhE3b5j/GppWQBr/MvXYXlt+V/VTBhnuxdJCucre6VfFtjw4ZK+tvFWPFnQc3MHIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T06:43:27.360692Z"},"content_sha256":"68ba7d5665537afea05f7acfd7b1846bd4cc8eede422cc5be86abfe7f9798fdb","schema_version":"1.0","event_id":"sha256:68ba7d5665537afea05f7acfd7b1846bd4cc8eede422cc5be86abfe7f9798fdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY/bundle.json","state_url":"https://pith.science/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY/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":"2026-07-12T06:43:27Z","links":{"resolver":"https://pith.science/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY","bundle":"https://pith.science/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY/bundle.json","state":"https://pith.science/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGOF76JJ3IXNP7FVZXAOXHO5RY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MGOF76JJ3IXNP7FVZXAOXHO5RY","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":"5d0faa87f403446dc79a461c855de231c2f3ee7bc46c7a9442d6347a97ebb44f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-23T04:26:26Z","title_canon_sha256":"0a5d6560c1c58ea32a7aecd1cd11f790aaf6af91551cef4146cd062e2cdba8c3"},"schema_version":"1.0","source":{"id":"1908.08659","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08659","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08659v1","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08659","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"pith_short_12","alias_value":"MGOF76JJ3IXN","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"pith_short_16","alias_value":"MGOF76JJ3IXNP7FV","created_at":"2026-07-04T23:59:16Z"},{"alias_kind":"pith_short_8","alias_value":"MGOF76JJ","created_at":"2026-07-04T23:59:16Z"}],"graph_snapshots":[{"event_id":"sha256:68ba7d5665537afea05f7acfd7b1846bd4cc8eede422cc5be86abfe7f9798fdb","target":"graph","created_at":"2026-07-04T23:59:16Z","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/1908.08659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing reinforcement learning (RL) problems that can produce delicate and precise manipulation policies requires careful choice of the reward function, state, and action spaces. Much prior work on applying RL to manipulation tasks has defined the action space in terms of direct joint torques or reference positions for a joint-space proportional derivative (PD) controller. In practice, it is often possible to add additional structure by taking advantage of model-based controllers that support both accurate positioning and control of the dynamic response of the manipulator. In this paper, we ","authors_text":"Lev Grossman, Patrick Varin, Scott Kuindersma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-23T04:26:26Z","title":"A Comparison of Action Spaces for Learning Manipulation Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08659","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":"sha256:8692e22ef546148c18cd69016a8ee18140cb3cac4fbed8f43f8d68d438a61d8c","target":"record","created_at":"2026-07-04T23:59:16Z","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":"5d0faa87f403446dc79a461c855de231c2f3ee7bc46c7a9442d6347a97ebb44f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-23T04:26:26Z","title_canon_sha256":"0a5d6560c1c58ea32a7aecd1cd11f790aaf6af91551cef4146cd062e2cdba8c3"},"schema_version":"1.0","source":{"id":"1908.08659","kind":"arxiv","version":1}},"canonical_sha256":"619c5ff929da2ed7fcb5cdc0eb9ddd8e08f19a918e2d6c6d40d3c1fe9b5df756","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"619c5ff929da2ed7fcb5cdc0eb9ddd8e08f19a918e2d6c6d40d3c1fe9b5df756","first_computed_at":"2026-07-04T23:59:16.593204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:16.593204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CK8t7Ui6aact+hVDPOc7EuNNBJK7N9oKKGfxzfWRG7HcYKWmrGkSndQao9Ige+hlYhvPnOkDERd5Lob1y4rtAw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:16.593639Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08659","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8692e22ef546148c18cd69016a8ee18140cb3cac4fbed8f43f8d68d438a61d8c","sha256:68ba7d5665537afea05f7acfd7b1846bd4cc8eede422cc5be86abfe7f9798fdb"],"state_sha256":"c24141197961667485e2c44d5c7337c09ed34a81022e0311e370ea1a0eb0f78d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mm1XFaAVyQI+P3/8WrI3JGrNlqB6fPm17UBd8fgHRayZjQLCOcxXHWFCMURc/dvM9EEuNpzDEHHuObibAro6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T06:43:27.363348Z","bundle_sha256":"6f929bb7d7330332e43e8e7801f7e82e15d8ff16ee28455ffeee160538b940ae"}}