{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CIEZAZVBSVQQRE4256BYL6G3LQ","short_pith_number":"pith:CIEZAZVB","canonical_record":{"source":{"id":"2107.10253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"effe37b82ff1c7b90ae8726bcc43e9d9d1ea65c4aaef17bfaa8ee2686df306c7","abstract_canon_sha256":"f03664dc093564893547be27c98497109fbdcca7258617a6b7c61b3514ca3077"},"schema_version":"1.0"},"canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","source":{"kind":"arxiv","id":"2107.10253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.10253","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"arxiv_version","alias_value":"2107.10253v1","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10253","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"pith_short_12","alias_value":"CIEZAZVBSVQQ","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"pith_short_16","alias_value":"CIEZAZVBSVQQRE42","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"pith_short_8","alias_value":"CIEZAZVB","created_at":"2026-07-05T02:59:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CIEZAZVBSVQQRE4256BYL6G3LQ","target":"record","payload":{"canonical_record":{"source":{"id":"2107.10253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"effe37b82ff1c7b90ae8726bcc43e9d9d1ea65c4aaef17bfaa8ee2686df306c7","abstract_canon_sha256":"f03664dc093564893547be27c98497109fbdcca7258617a6b7c61b3514ca3077"},"schema_version":"1.0"},"canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:50.407462Z","signature_b64":"walmPgplrsN/vWFKfBQaW6qrq/ZTAIq1L9v9jFDgaTjtsCKGLaphAT5IFpDq6R5QtwCfckIhCySq+K8PEegUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","last_reissued_at":"2026-07-05T02:59:50.406987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:50.406987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.10253","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":"2026-07-05T02:59:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"758kzA0dkBM0ZG1gMkoyyIKVn+PChJu+JPuXZr659sqZCzGi7XFKa8lxwfeWPPzNc+CBKMCpRl8HiMlc4evdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:40:55.810727Z"},"content_sha256":"9874c7c588b4b38000db5bc9474fe9305635aca0f41f008c5546f4aafafc561c","schema_version":"1.0","event_id":"sha256:9874c7c588b4b38000db5bc9474fe9305635aca0f41f008c5546f4aafafc561c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CIEZAZVBSVQQRE4256BYL6G3LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demonstration-Guided Reinforcement Learning with Learned Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Joseph J. Lim, Karl Pertsch, Youngwoon Lee, Yue Wu","submitted_at":"2021-07-21T17:59:34Z","abstract_excerpt":"Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10253","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/2107.10253/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":"2026-07-05T02:59:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"89ZAZZfRdw/Kp5uh0vRRUME64tLJUXZz7ds64PtInn4pKd8qo01tydHrSlxfV42ZuF0QBpKcyLL5KIeW4FkBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:40:55.811113Z"},"content_sha256":"b4e8f8029c241f15156bac6fb8869c402a0644a362f58f98898bc935afba6335","schema_version":"1.0","event_id":"sha256:b4e8f8029c241f15156bac6fb8869c402a0644a362f58f98898bc935afba6335"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/bundle.json","state_url":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/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":"2026-08-20T16:40:55Z","links":{"resolver":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ","bundle":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/bundle.json","state":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CIEZAZVBSVQQRE4256BYL6G3LQ","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":"f03664dc093564893547be27c98497109fbdcca7258617a6b7c61b3514ca3077","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","title_canon_sha256":"effe37b82ff1c7b90ae8726bcc43e9d9d1ea65c4aaef17bfaa8ee2686df306c7"},"schema_version":"1.0","source":{"id":"2107.10253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.10253","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"arxiv_version","alias_value":"2107.10253v1","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10253","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"pith_short_12","alias_value":"CIEZAZVBSVQQ","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"pith_short_16","alias_value":"CIEZAZVBSVQQRE42","created_at":"2026-07-05T02:59:50Z"},{"alias_kind":"pith_short_8","alias_value":"CIEZAZVB","created_at":"2026-07-05T02:59:50Z"}],"graph_snapshots":[{"event_id":"sha256:b4e8f8029c241f15156bac6fb8869c402a0644a362f58f98898bc935afba6335","target":"graph","created_at":"2026-07-05T02:59:50Z","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/2107.10253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have pre","authors_text":"Joseph J. Lim, Karl Pertsch, Youngwoon Lee, Yue Wu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","title":"Demonstration-Guided Reinforcement Learning with Learned Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10253","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":"sha256:9874c7c588b4b38000db5bc9474fe9305635aca0f41f008c5546f4aafafc561c","target":"record","created_at":"2026-07-05T02:59:50Z","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":"f03664dc093564893547be27c98497109fbdcca7258617a6b7c61b3514ca3077","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","title_canon_sha256":"effe37b82ff1c7b90ae8726bcc43e9d9d1ea65c4aaef17bfaa8ee2686df306c7"},"schema_version":"1.0","source":{"id":"2107.10253","kind":"arxiv","version":1}},"canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","first_computed_at":"2026-07-05T02:59:50.406987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:50.406987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"walmPgplrsN/vWFKfBQaW6qrq/ZTAIq1L9v9jFDgaTjtsCKGLaphAT5IFpDq6R5QtwCfckIhCySq+K8PEegUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:50.407462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.10253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9874c7c588b4b38000db5bc9474fe9305635aca0f41f008c5546f4aafafc561c","sha256:b4e8f8029c241f15156bac6fb8869c402a0644a362f58f98898bc935afba6335"],"state_sha256":"29a7bce80991021a50fddb7a719aac63a1c146e4801c4a4af9329a96b3b624b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+1lSfzDJLTjZqhPJfnw/0gDLZhiV1iXCLgXygz298J3N2jrcPdEgJTg0HzLuZaMw9R22EttPOsAhvv4OTCNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T16:40:55.813670Z","bundle_sha256":"8215577425253265eef20300276575d142aacd9b08ac16c9c5a8aacedbfc09b2"}}