{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NZBPAJVOZHR5H47ALK2CIVFD3D","short_pith_number":"pith:NZBPAJVO","canonical_record":{"source":{"id":"2009.09595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-21T03:09:53Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5150ab7f0b935b55aaf0b6bd91da53e558eddf8631618b8652475a959cc298b8","abstract_canon_sha256":"2784dc2ed6e25984fe5ab9032582faeee9fe6adb0c53dc63ab5dcebec6cb3ccc"},"schema_version":"1.0"},"canonical_sha256":"6e42f026aec9e3d3f3e05ab42454a3d8e2cbd1311bae588a5e5caf2fa8431367","source":{"kind":"arxiv","id":"2009.09595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09595","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09595v1","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09595","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"pith_short_12","alias_value":"NZBPAJVOZHR5","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"pith_short_16","alias_value":"NZBPAJVOZHR5H47A","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"pith_short_8","alias_value":"NZBPAJVO","created_at":"2026-07-05T01:36:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NZBPAJVOZHR5H47ALK2CIVFD3D","target":"record","payload":{"canonical_record":{"source":{"id":"2009.09595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-21T03:09:53Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5150ab7f0b935b55aaf0b6bd91da53e558eddf8631618b8652475a959cc298b8","abstract_canon_sha256":"2784dc2ed6e25984fe5ab9032582faeee9fe6adb0c53dc63ab5dcebec6cb3ccc"},"schema_version":"1.0"},"canonical_sha256":"6e42f026aec9e3d3f3e05ab42454a3d8e2cbd1311bae588a5e5caf2fa8431367","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:42.264954Z","signature_b64":"UdodZSwpKxYyMlosPqF3uaeRobnBsT6YlFJMKwjoYkoodT8b9BM+rYr8UrhjPxGZqDD+3IMfkJTiEfXEpjNFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e42f026aec9e3d3f3e05ab42454a3d8e2cbd1311bae588a5e5caf2fa8431367","last_reissued_at":"2026-07-05T01:36:42.264568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:42.264568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.09595","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":"2026-07-05T01:36:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+bef81S4QxftzZPTJIOHTiwTr9SksznZ2H62hGr/mjGadWWGveM0solbtPidfTzWNZfdxeDDViz4FwM8WQFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:19:09.844148Z"},"content_sha256":"32caf72602e0175e9c625548760a5d4e3efc3def45a63b2a9c472034a564dbf5","schema_version":"1.0","event_id":"sha256:32caf72602e0175e9c625548760a5d4e3efc3def45a63b2a9c472034a564dbf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NZBPAJVOZHR5H47ALK2CIVFD3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL STaR Platform: Reinforcement Learning for Simulation based Training of Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Gabin Paillet, Kazuya Yoshida, Mickael Laine, Tamir Blum","submitted_at":"2020-09-21T03:09:53Z","abstract_excerpt":"Reinforcement learning (RL) is a promising field to enhance robotic autonomy and decision making capabilities for space robotics, something which is challenging with traditional techniques due to stochasticity and uncertainty within the environment. RL can be used to enable lunar cave exploration with infrequent human feedback, faster and safer lunar surface locomotion or the coordination and collaboration of multi-robot systems. However, there are many hurdles making research challenging for space robotic applications using RL and machine learning, particularly due to insufficient resources f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09595","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/2009.09595/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":"2026-07-05T01:36:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyQiogzFzv+Kn1Crh6Q6drhk7odLQ9WF2DlpuZoXc0BGwOkNmbP1KZhLxrViTuXAf/48Fbqr5rf5GmLsAXqbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:19:09.844646Z"},"content_sha256":"75228c4c27574653d942285bf1fe68b3496166660ff9235f2ce39b0f527dd83d","schema_version":"1.0","event_id":"sha256:75228c4c27574653d942285bf1fe68b3496166660ff9235f2ce39b0f527dd83d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZBPAJVOZHR5H47ALK2CIVFD3D/bundle.json","state_url":"https://pith.science/pith/NZBPAJVOZHR5H47ALK2CIVFD3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZBPAJVOZHR5H47ALK2CIVFD3D/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":"2026-08-22T14:19:09Z","links":{"resolver":"https://pith.science/pith/NZBPAJVOZHR5H47ALK2CIVFD3D","bundle":"https://pith.science/pith/NZBPAJVOZHR5H47ALK2CIVFD3D/bundle.json","state":"https://pith.science/pith/NZBPAJVOZHR5H47ALK2CIVFD3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZBPAJVOZHR5H47ALK2CIVFD3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NZBPAJVOZHR5H47ALK2CIVFD3D","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":"2784dc2ed6e25984fe5ab9032582faeee9fe6adb0c53dc63ab5dcebec6cb3ccc","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-21T03:09:53Z","title_canon_sha256":"5150ab7f0b935b55aaf0b6bd91da53e558eddf8631618b8652475a959cc298b8"},"schema_version":"1.0","source":{"id":"2009.09595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09595","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09595v1","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09595","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"pith_short_12","alias_value":"NZBPAJVOZHR5","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"pith_short_16","alias_value":"NZBPAJVOZHR5H47A","created_at":"2026-07-05T01:36:42Z"},{"alias_kind":"pith_short_8","alias_value":"NZBPAJVO","created_at":"2026-07-05T01:36:42Z"}],"graph_snapshots":[{"event_id":"sha256:75228c4c27574653d942285bf1fe68b3496166660ff9235f2ce39b0f527dd83d","target":"graph","created_at":"2026-07-05T01:36:42Z","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/2009.09595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a promising field to enhance robotic autonomy and decision making capabilities for space robotics, something which is challenging with traditional techniques due to stochasticity and uncertainty within the environment. RL can be used to enable lunar cave exploration with infrequent human feedback, faster and safer lunar surface locomotion or the coordination and collaboration of multi-robot systems. However, there are many hurdles making research challenging for space robotic applications using RL and machine learning, particularly due to insufficient resources f","authors_text":"Gabin Paillet, Kazuya Yoshida, Mickael Laine, Tamir Blum","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-21T03:09:53Z","title":"RL STaR Platform: Reinforcement Learning for Simulation based Training of Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09595","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":"sha256:32caf72602e0175e9c625548760a5d4e3efc3def45a63b2a9c472034a564dbf5","target":"record","created_at":"2026-07-05T01:36:42Z","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":"2784dc2ed6e25984fe5ab9032582faeee9fe6adb0c53dc63ab5dcebec6cb3ccc","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-21T03:09:53Z","title_canon_sha256":"5150ab7f0b935b55aaf0b6bd91da53e558eddf8631618b8652475a959cc298b8"},"schema_version":"1.0","source":{"id":"2009.09595","kind":"arxiv","version":1}},"canonical_sha256":"6e42f026aec9e3d3f3e05ab42454a3d8e2cbd1311bae588a5e5caf2fa8431367","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e42f026aec9e3d3f3e05ab42454a3d8e2cbd1311bae588a5e5caf2fa8431367","first_computed_at":"2026-07-05T01:36:42.264568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:42.264568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UdodZSwpKxYyMlosPqF3uaeRobnBsT6YlFJMKwjoYkoodT8b9BM+rYr8UrhjPxGZqDD+3IMfkJTiEfXEpjNFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:42.264954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.09595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32caf72602e0175e9c625548760a5d4e3efc3def45a63b2a9c472034a564dbf5","sha256:75228c4c27574653d942285bf1fe68b3496166660ff9235f2ce39b0f527dd83d"],"state_sha256":"d694064c2c903c4bebd660d98a9ed09833c3e2ce468d6e59afd167cd67aaaf73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJnY4sD1WFKPvynOgfcUVn/gJLEG+RqZOadGmdRVgjNh/SDOVL2VJl81GDvLe/m4ElausIHsafYpa9/UXJ28BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T14:19:09.848321Z","bundle_sha256":"a521e021e8425b252e86ebbe5846da9fc9dadfda0f8fdfb6b4b32d21104f20b9"}}