{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WFTJ626SIUVPTOIPXE34YDCFGD","short_pith_number":"pith:WFTJ626S","canonical_record":{"source":{"id":"2102.02915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-04T22:09:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"91618c87f74f2e58446d209be5957795c7b82660c827ae6d6307103df44f3339","abstract_canon_sha256":"160de4e471090298bc3cb807898df789ff0f497961d0373aaddce5f28f1a104e"},"schema_version":"1.0"},"canonical_sha256":"b1669f6bd2452af9b90fb937cc0c4530dbc1af1985104fa6386541e2ae03b94a","source":{"kind":"arxiv","id":"2102.02915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02915","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02915v1","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02915","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"WFTJ626SIUVP","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"WFTJ626SIUVPTOIP","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"WFTJ626S","created_at":"2026-07-05T02:12:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WFTJ626SIUVPTOIPXE34YDCFGD","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-04T22:09:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"91618c87f74f2e58446d209be5957795c7b82660c827ae6d6307103df44f3339","abstract_canon_sha256":"160de4e471090298bc3cb807898df789ff0f497961d0373aaddce5f28f1a104e"},"schema_version":"1.0"},"canonical_sha256":"b1669f6bd2452af9b90fb937cc0c4530dbc1af1985104fa6386541e2ae03b94a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:55.002291Z","signature_b64":"GrSyugXYxpdB2pcy4CEg5440sotzVikZRZzuo1ru7rVmdqqSu5AFvmjBh0Y3enOrdG4grX2D/e/5myEDaaHdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1669f6bd2452af9b90fb937cc0c4530dbc1af1985104fa6386541e2ae03b94a","last_reissued_at":"2026-07-05T02:12:55.001875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:55.001875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02915","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":"2026-07-05T02:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02+jhNxF6nd6dLv50ko7hZTobYg8nMmbpSIvOjVtUE76YoQoi4aUKrf35qjjxh6/XmR/XTTABxSAkxdAdaFICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T10:55:11.081810Z"},"content_sha256":"2008d889d72681ced8d8c8ae22056f87acc52843cb8bebe2f19114a8237af612","schema_version":"1.0","event_id":"sha256:2008d889d72681ced8d8c8ae22056f87acc52843cb8bebe2f19114a8237af612"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WFTJ626SIUVPTOIPXE34YDCFGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Jie Tan, Julian Ibarz, Mrinal Kalakrishnan, Peter Pastor, Sergey Levine","submitted_at":"2021-02-04T22:09:28Z","abstract_excerpt":"Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games and simulated control, which does not connect with the constraints of learning in real environments, deep RL has also demonstrated promise in enabling physical robots to learn complex skills in the real world. At the same time,real world robotics provides an appealing domain for evaluating such algorithms, as it connects directly to how humans learn; as an emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02915","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/2102.02915/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":"2026-07-05T02:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r7/cGI+GWn6k7+R/3lmzRxoUJRybIFUnyAS7FMuBygrsgsxbEO70BusHQxB8m8RiEWADvKPuXPBmhlFNim6iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T10:55:11.082176Z"},"content_sha256":"f54f53ce9772849bade614ff0b1a79b4026761fd1273e248b76486a402bc4ec6","schema_version":"1.0","event_id":"sha256:f54f53ce9772849bade614ff0b1a79b4026761fd1273e248b76486a402bc4ec6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WFTJ626SIUVPTOIPXE34YDCFGD/bundle.json","state_url":"https://pith.science/pith/WFTJ626SIUVPTOIPXE34YDCFGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WFTJ626SIUVPTOIPXE34YDCFGD/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":"2026-07-18T10:55:11Z","links":{"resolver":"https://pith.science/pith/WFTJ626SIUVPTOIPXE34YDCFGD","bundle":"https://pith.science/pith/WFTJ626SIUVPTOIPXE34YDCFGD/bundle.json","state":"https://pith.science/pith/WFTJ626SIUVPTOIPXE34YDCFGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WFTJ626SIUVPTOIPXE34YDCFGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WFTJ626SIUVPTOIPXE34YDCFGD","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":"160de4e471090298bc3cb807898df789ff0f497961d0373aaddce5f28f1a104e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-04T22:09:28Z","title_canon_sha256":"91618c87f74f2e58446d209be5957795c7b82660c827ae6d6307103df44f3339"},"schema_version":"1.0","source":{"id":"2102.02915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02915","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02915v1","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02915","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"WFTJ626SIUVP","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"WFTJ626SIUVPTOIP","created_at":"2026-07-05T02:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"WFTJ626S","created_at":"2026-07-05T02:12:55Z"}],"graph_snapshots":[{"event_id":"sha256:f54f53ce9772849bade614ff0b1a79b4026761fd1273e248b76486a402bc4ec6","target":"graph","created_at":"2026-07-05T02:12:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.02915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games and simulated control, which does not connect with the constraints of learning in real environments, deep RL has also demonstrated promise in enabling physical robots to learn complex skills in the real world. At the same time,real world robotics provides an appealing domain for evaluating such algorithms, as it connects directly to how humans learn; as an emb","authors_text":"Chelsea Finn, Jie Tan, Julian Ibarz, Mrinal Kalakrishnan, Peter Pastor, Sergey Levine","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-04T22:09:28Z","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02915","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":"sha256:2008d889d72681ced8d8c8ae22056f87acc52843cb8bebe2f19114a8237af612","target":"record","created_at":"2026-07-05T02:12:55Z","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":"160de4e471090298bc3cb807898df789ff0f497961d0373aaddce5f28f1a104e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-04T22:09:28Z","title_canon_sha256":"91618c87f74f2e58446d209be5957795c7b82660c827ae6d6307103df44f3339"},"schema_version":"1.0","source":{"id":"2102.02915","kind":"arxiv","version":1}},"canonical_sha256":"b1669f6bd2452af9b90fb937cc0c4530dbc1af1985104fa6386541e2ae03b94a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1669f6bd2452af9b90fb937cc0c4530dbc1af1985104fa6386541e2ae03b94a","first_computed_at":"2026-07-05T02:12:55.001875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:55.001875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrSyugXYxpdB2pcy4CEg5440sotzVikZRZzuo1ru7rVmdqqSu5AFvmjBh0Y3enOrdG4grX2D/e/5myEDaaHdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:55.002291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2008d889d72681ced8d8c8ae22056f87acc52843cb8bebe2f19114a8237af612","sha256:f54f53ce9772849bade614ff0b1a79b4026761fd1273e248b76486a402bc4ec6"],"state_sha256":"6a1e118f3bc58a6dda4e01dcce004dcedfb874b184bd17094ddf8090c5438992"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ZGYAOwxVCjt2ByLXEbSvpJH9Ik/poEsIbLdE9GPwNZhOX+HL45LErO7foV4ef5aC9kXoYE5EVddxGCAE3+bAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T10:55:11.084309Z","bundle_sha256":"c56e90c1b9ecd0d6d357df9e4dbfdff2e3650748e729239f290cb96c7293d7c1"}}