{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QA3OHL2V5DBUABWRUZ6NYE2MXA","short_pith_number":"pith:QA3OHL2V","canonical_record":{"source":{"id":"2206.02462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-06-06T09:56:16Z","cross_cats_sorted":[],"title_canon_sha256":"f08e6cbe833075f5daece7557cba9eb75c97f72beac117be79e34c2c603af6f7","abstract_canon_sha256":"ab486a6b127ccee88ed8c2855824aa34f1a30602f2a64b15c4a2bc109b90be9a"},"schema_version":"1.0"},"canonical_sha256":"8036e3af55e8c34006d1a67cdc134cb81c9dd27ac87d0d6d13070213a02a04cf","source":{"kind":"arxiv","id":"2206.02462","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02462","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02462v2","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02462","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"QA3OHL2V5DBU","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"QA3OHL2V5DBUABWR","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"QA3OHL2V","created_at":"2026-07-05T06:02:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QA3OHL2V5DBUABWRUZ6NYE2MXA","target":"record","payload":{"canonical_record":{"source":{"id":"2206.02462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-06-06T09:56:16Z","cross_cats_sorted":[],"title_canon_sha256":"f08e6cbe833075f5daece7557cba9eb75c97f72beac117be79e34c2c603af6f7","abstract_canon_sha256":"ab486a6b127ccee88ed8c2855824aa34f1a30602f2a64b15c4a2bc109b90be9a"},"schema_version":"1.0"},"canonical_sha256":"8036e3af55e8c34006d1a67cdc134cb81c9dd27ac87d0d6d13070213a02a04cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:46.273211Z","signature_b64":"hk7cCSF5enOB8cp6vHLq3h4t/UsYG7fSXw4BSloMsG7NugVRMkD1SDpIagGcyk0j0AxK8Scrht2NQNeJySrfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8036e3af55e8c34006d1a67cdc134cb81c9dd27ac87d0d6d13070213a02a04cf","last_reissued_at":"2026-07-05T06:02:46.272855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:46.272855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.02462","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":"2026-07-05T06:02:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCb2knkrfQrOeCKwIWy0RpDO0u++BX2E2FYHd+gBkdTjTeyISkSI/sCUMvBgF0cKCH/p0KO0QGPW1du2eOfAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:55:46.293644Z"},"content_sha256":"03ef6cbaee0780cb41770f057dbb04a5246b6babecdffc2bc75807288bbc09c1","schema_version":"1.0","event_id":"sha256:03ef6cbaee0780cb41770f057dbb04a5246b6babecdffc2bc75807288bbc09c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QA3OHL2V5DBUABWRUZ6NYE2MXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Achieving Goals using Reward Shaping and Curriculum Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dabal Pedamonti, Jonathan D. Thomas, Mark Hansen, Matthew Studley, Mihai Anca","submitted_at":"2022-06-06T09:56:16Z","abstract_excerpt":"Real-time control for robotics is a popular research area in the reinforcement learning community. Through the use of techniques such as reward shaping, researchers have managed to train online agents across a multitude of domains. Despite these advances, solving goal-oriented tasks still requires complex architectural changes or hard constraints to be placed on the problem. In this article, we solve the problem of stacking multiple cubes by combining curriculum learning, reward shaping, and a high number of efficiently parallelized environments. We introduce two curriculum learning settings t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02462","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.02462/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":"2026-07-05T06:02:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6lOiBGcBjEsxOve2bYFYQhbcIrv6NybpJWj7fhNcYtVGp/ogMcUNuclISfqgU3UTcXsbimtXC86ms+B7SKoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:55:46.294183Z"},"content_sha256":"af90723c97628421648a745c2938c5f68d87ad5b344f9a6c82b75d324a747d8b","schema_version":"1.0","event_id":"sha256:af90723c97628421648a745c2938c5f68d87ad5b344f9a6c82b75d324a747d8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA/bundle.json","state_url":"https://pith.science/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA/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":"2026-08-21T17:55:46Z","links":{"resolver":"https://pith.science/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA","bundle":"https://pith.science/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA/bundle.json","state":"https://pith.science/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QA3OHL2V5DBUABWRUZ6NYE2MXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QA3OHL2V5DBUABWRUZ6NYE2MXA","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":"ab486a6b127ccee88ed8c2855824aa34f1a30602f2a64b15c4a2bc109b90be9a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-06-06T09:56:16Z","title_canon_sha256":"f08e6cbe833075f5daece7557cba9eb75c97f72beac117be79e34c2c603af6f7"},"schema_version":"1.0","source":{"id":"2206.02462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02462","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02462v2","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02462","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"QA3OHL2V5DBU","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"QA3OHL2V5DBUABWR","created_at":"2026-07-05T06:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"QA3OHL2V","created_at":"2026-07-05T06:02:46Z"}],"graph_snapshots":[{"event_id":"sha256:af90723c97628421648a745c2938c5f68d87ad5b344f9a6c82b75d324a747d8b","target":"graph","created_at":"2026-07-05T06:02:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.02462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time control for robotics is a popular research area in the reinforcement learning community. Through the use of techniques such as reward shaping, researchers have managed to train online agents across a multitude of domains. Despite these advances, solving goal-oriented tasks still requires complex architectural changes or hard constraints to be placed on the problem. In this article, we solve the problem of stacking multiple cubes by combining curriculum learning, reward shaping, and a high number of efficiently parallelized environments. We introduce two curriculum learning settings t","authors_text":"Dabal Pedamonti, Jonathan D. Thomas, Mark Hansen, Matthew Studley, Mihai Anca","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-06-06T09:56:16Z","title":"Achieving Goals using Reward Shaping and Curriculum Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02462","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":"sha256:03ef6cbaee0780cb41770f057dbb04a5246b6babecdffc2bc75807288bbc09c1","target":"record","created_at":"2026-07-05T06:02:46Z","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":"ab486a6b127ccee88ed8c2855824aa34f1a30602f2a64b15c4a2bc109b90be9a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-06-06T09:56:16Z","title_canon_sha256":"f08e6cbe833075f5daece7557cba9eb75c97f72beac117be79e34c2c603af6f7"},"schema_version":"1.0","source":{"id":"2206.02462","kind":"arxiv","version":2}},"canonical_sha256":"8036e3af55e8c34006d1a67cdc134cb81c9dd27ac87d0d6d13070213a02a04cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8036e3af55e8c34006d1a67cdc134cb81c9dd27ac87d0d6d13070213a02a04cf","first_computed_at":"2026-07-05T06:02:46.272855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:46.272855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hk7cCSF5enOB8cp6vHLq3h4t/UsYG7fSXw4BSloMsG7NugVRMkD1SDpIagGcyk0j0AxK8Scrht2NQNeJySrfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:46.273211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03ef6cbaee0780cb41770f057dbb04a5246b6babecdffc2bc75807288bbc09c1","sha256:af90723c97628421648a745c2938c5f68d87ad5b344f9a6c82b75d324a747d8b"],"state_sha256":"5ab9a5ff1a23873d8ce682f7739c70692b5e1b777fb747d526e5f89db04ce480"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrGRON9RUBqZXY3fU3HfyZ2PBwfkJGG6Sb5riSaaBCKfCuTfwOPFXv3MIcF1LnT36q5xxdvhjX4n2km4JNJbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:55:46.298657Z","bundle_sha256":"f04ab1dc11f8c72b44699e774fd0663b5059ab0a14ab88b15ae3b1cc1059f864"}}