{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XGG2UFMMEH7HVOLR2KNAH6PEWQ","short_pith_number":"pith:XGG2UFMM","canonical_record":{"source":{"id":"2203.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-29T17:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"8e701d64beca44f6000a3e0c81ba4d141cef7ed4f5b5494220223776f01fc876","abstract_canon_sha256":"736ace80bef3bb6fceca5ed9717bf5dba3fdbb65e563901c213e2f3d4fe6878f"},"schema_version":"1.0"},"canonical_sha256":"b98daa158c21fe7ab971d29a03f9e4b40793eb6bb227bcf1b49ee32ac8c7d387","source":{"kind":"arxiv","id":"2203.15755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15755","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15755v1","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15755","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"XGG2UFMMEH7H","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"XGG2UFMMEH7HVOLR","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"XGG2UFMM","created_at":"2026-07-05T04:09:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XGG2UFMMEH7HVOLR2KNAH6PEWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-29T17:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"8e701d64beca44f6000a3e0c81ba4d141cef7ed4f5b5494220223776f01fc876","abstract_canon_sha256":"736ace80bef3bb6fceca5ed9717bf5dba3fdbb65e563901c213e2f3d4fe6878f"},"schema_version":"1.0"},"canonical_sha256":"b98daa158c21fe7ab971d29a03f9e4b40793eb6bb227bcf1b49ee32ac8c7d387","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:52.683201Z","signature_b64":"yTMmEui14rJyFsVqv+tHtPUzEuIpJ5tY/X24ncD0OjUkX/O64Y8jAJTzJIPXRtpBfLyXim2UmDnIMr7d9KGiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b98daa158c21fe7ab971d29a03f9e4b40793eb6bb227bcf1b49ee32ac8c7d387","last_reissued_at":"2026-07-05T04:09:52.682815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:52.682815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.15755","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":"2026-07-05T04:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDs21qBC82dDZn2l/k30ooWyByaLJdkwz332ppFMzsgBWLndm8WLHWMrxCsPP8g4TGMwC/inGRfdqDU5xWfCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:41:56.925533Z"},"content_sha256":"34dd4ceabf03ee6d9b96d57a6b6b257eaa0d283843b5d3b8368bbc86ee4fa866","schema_version":"1.0","event_id":"sha256:34dd4ceabf03ee6d9b96d57a6b6b257eaa0d283843b5d3b8368bbc86ee4fa866"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XGG2UFMMEH7HVOLR2KNAH6PEWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Brandon Kinman, Corey Lynch, Garrett Peake, Karol Hausman, Sergey Levine","submitted_at":"2022-03-29T17:08:14Z","abstract_excerpt":"Reinforcement learning systems have the potential to enable continuous improvement in unstructured environments, leveraging data collected autonomously. However, in practice these systems require significant amounts of instrumentation or human intervention to learn in the real world. In this work, we propose a system for reinforcement learning that leverages multi-task reinforcement learning bootstrapped with prior data to enable continuous autonomous practicing, minimizing the number of resets needed while being able to learn temporally extended behaviors. We show how appropriately provided p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15755","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/2203.15755/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":"2026-07-05T04:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WudjNPRfvVV1CI7l2gN0l6JmNohDPaG93y69gewWSsllzt+ml0YIoBWGN7TYwKemqi4kuhbOsDvf4yBnEI3WDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:41:56.925890Z"},"content_sha256":"b44622a5b509bf8a54a2c2edb682c35e851a4bfe42f61dc7c04ff8973436c7a8","schema_version":"1.0","event_id":"sha256:b44622a5b509bf8a54a2c2edb682c35e851a4bfe42f61dc7c04ff8973436c7a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ/bundle.json","state_url":"https://pith.science/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ/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":"2026-07-17T00:41:56Z","links":{"resolver":"https://pith.science/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ","bundle":"https://pith.science/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ/bundle.json","state":"https://pith.science/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGG2UFMMEH7HVOLR2KNAH6PEWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XGG2UFMMEH7HVOLR2KNAH6PEWQ","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":"736ace80bef3bb6fceca5ed9717bf5dba3fdbb65e563901c213e2f3d4fe6878f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-29T17:08:14Z","title_canon_sha256":"8e701d64beca44f6000a3e0c81ba4d141cef7ed4f5b5494220223776f01fc876"},"schema_version":"1.0","source":{"id":"2203.15755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15755","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15755v1","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15755","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"XGG2UFMMEH7H","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"XGG2UFMMEH7HVOLR","created_at":"2026-07-05T04:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"XGG2UFMM","created_at":"2026-07-05T04:09:52Z"}],"graph_snapshots":[{"event_id":"sha256:b44622a5b509bf8a54a2c2edb682c35e851a4bfe42f61dc7c04ff8973436c7a8","target":"graph","created_at":"2026-07-05T04:09:52Z","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/2203.15755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning systems have the potential to enable continuous improvement in unstructured environments, leveraging data collected autonomously. However, in practice these systems require significant amounts of instrumentation or human intervention to learn in the real world. In this work, we propose a system for reinforcement learning that leverages multi-task reinforcement learning bootstrapped with prior data to enable continuous autonomous practicing, minimizing the number of resets needed while being able to learn temporally extended behaviors. We show how appropriately provided p","authors_text":"Abhishek Gupta, Brandon Kinman, Corey Lynch, Garrett Peake, Karol Hausman, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-29T17:08:14Z","title":"Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15755","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":"sha256:34dd4ceabf03ee6d9b96d57a6b6b257eaa0d283843b5d3b8368bbc86ee4fa866","target":"record","created_at":"2026-07-05T04:09:52Z","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":"736ace80bef3bb6fceca5ed9717bf5dba3fdbb65e563901c213e2f3d4fe6878f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-29T17:08:14Z","title_canon_sha256":"8e701d64beca44f6000a3e0c81ba4d141cef7ed4f5b5494220223776f01fc876"},"schema_version":"1.0","source":{"id":"2203.15755","kind":"arxiv","version":1}},"canonical_sha256":"b98daa158c21fe7ab971d29a03f9e4b40793eb6bb227bcf1b49ee32ac8c7d387","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b98daa158c21fe7ab971d29a03f9e4b40793eb6bb227bcf1b49ee32ac8c7d387","first_computed_at":"2026-07-05T04:09:52.682815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:52.682815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yTMmEui14rJyFsVqv+tHtPUzEuIpJ5tY/X24ncD0OjUkX/O64Y8jAJTzJIPXRtpBfLyXim2UmDnIMr7d9KGiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:52.683201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34dd4ceabf03ee6d9b96d57a6b6b257eaa0d283843b5d3b8368bbc86ee4fa866","sha256:b44622a5b509bf8a54a2c2edb682c35e851a4bfe42f61dc7c04ff8973436c7a8"],"state_sha256":"819c53bd0e3b3e07230528441775ffa819058d2fbc92c9c954b968df50ddd9a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4jBzGnbaIWwqvH3ZEehRYDgKVWV7Lzwhjj+LPb4SpkweHvJvT24SiasCoF5pDKRgCQt098+1iqmRaNhVQrEKCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T00:41:56.927890Z","bundle_sha256":"993b1a6a6d453fc54fdcb6eff25ca38dfd7e0c59a291c3d4beb80f2dfa847e73"}}