{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CM2Y4M4XV6S3LKOU5G3GKVJKTD","short_pith_number":"pith:CM2Y4M4X","canonical_record":{"source":{"id":"2112.00597","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-01T16:12:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0c869c3ff1c6590d4f7a7d14829965f891225442ed9660705f7a81aea52850a0","abstract_canon_sha256":"918c14a47f9452219e7985e7be8b90e656ae97e2ff798e22df3127230e89b932"},"schema_version":"1.0"},"canonical_sha256":"13358e3397afa5b5a9d4e9b665552a98c369558373c72320518d889b4de3f99d","source":{"kind":"arxiv","id":"2112.00597","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00597","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00597v3","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00597","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"CM2Y4M4XV6S3","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"CM2Y4M4XV6S3LKOU","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"CM2Y4M4X","created_at":"2026-07-05T04:07:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CM2Y4M4XV6S3LKOU5G3GKVJKTD","target":"record","payload":{"canonical_record":{"source":{"id":"2112.00597","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-01T16:12:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0c869c3ff1c6590d4f7a7d14829965f891225442ed9660705f7a81aea52850a0","abstract_canon_sha256":"918c14a47f9452219e7985e7be8b90e656ae97e2ff798e22df3127230e89b932"},"schema_version":"1.0"},"canonical_sha256":"13358e3397afa5b5a9d4e9b665552a98c369558373c72320518d889b4de3f99d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:06.755620Z","signature_b64":"4c9eIFZjfPvyJ4BzY53IazDqm/Nu/gM2lix540mDqcVpSUbg7LEzA/tujP8NGlCoG82oASLOOwXKz4I8JuL7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13358e3397afa5b5a9d4e9b665552a98c369558373c72320518d889b4de3f99d","last_reissued_at":"2026-07-05T04:07:06.755212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:06.755212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.00597","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MBIh8ky10dtP3bVFo9sHPbEPcN9ZEytsY/ldPq/D+80xtYub44hhkfRLTA35fOyJgayezXlltrXyJEuhMST5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:09:59.674470Z"},"content_sha256":"3816f088d581e211ceb9dfa4998d1f31ac767dcb041edeaff3f30cc546e824ba","schema_version":"1.0","event_id":"sha256:3816f088d581e211ceb9dfa4998d1f31ac767dcb041edeaff3f30cc546e824ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CM2Y4M4XV6S3LKOU5G3GKVJKTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.RO","authors_text":"Jean-Baptiste Regli, Jon Scholz, Markus Wulfmeier, Oleg Sushkov, Stefan Schaal, Todor Davchev, Yusuf Aytar","submitted_at":"2021-12-01T16:12:32Z","abstract_excerpt":"Complex sequential tasks in continuous-control settings often require agents to successfully traverse a set of \"narrow passages\" in their state space. Solving such tasks with a sparse reward in a sample-efficient manner poses a challenge to modern reinforcement learning (RL) due to the associated long-horizon nature of the problem and the lack of sufficient positive signal during learning. Various tools have been applied to address this challenge. When available, large sets of demonstrations can guide agent exploration. Hindsight relabelling on the other hand does not require additional source"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00597","kind":"arxiv","version":3},"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/2112.00597/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":"2026-07-05T04:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F0Y1OmIssBFaQOWGqSH2/kdv7q95JkYv4ob6XPLg9E1CS6PWCxK9qIV/rkD+X7wZkjIMXD3kuysE0wndpXC7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:09:59.675160Z"},"content_sha256":"6ad60d56cfd7a5049c567b5b1066d16a6610308767b34ca6fa3c39c59a208f15","schema_version":"1.0","event_id":"sha256:6ad60d56cfd7a5049c567b5b1066d16a6610308767b34ca6fa3c39c59a208f15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD/bundle.json","state_url":"https://pith.science/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD/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":"2026-08-09T22:09:59Z","links":{"resolver":"https://pith.science/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD","bundle":"https://pith.science/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD/bundle.json","state":"https://pith.science/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CM2Y4M4XV6S3LKOU5G3GKVJKTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CM2Y4M4XV6S3LKOU5G3GKVJKTD","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":"918c14a47f9452219e7985e7be8b90e656ae97e2ff798e22df3127230e89b932","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-01T16:12:32Z","title_canon_sha256":"0c869c3ff1c6590d4f7a7d14829965f891225442ed9660705f7a81aea52850a0"},"schema_version":"1.0","source":{"id":"2112.00597","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00597","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00597v3","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00597","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"CM2Y4M4XV6S3","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"CM2Y4M4XV6S3LKOU","created_at":"2026-07-05T04:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"CM2Y4M4X","created_at":"2026-07-05T04:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:6ad60d56cfd7a5049c567b5b1066d16a6610308767b34ca6fa3c39c59a208f15","target":"graph","created_at":"2026-07-05T04:07:06Z","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/2112.00597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Complex sequential tasks in continuous-control settings often require agents to successfully traverse a set of \"narrow passages\" in their state space. Solving such tasks with a sparse reward in a sample-efficient manner poses a challenge to modern reinforcement learning (RL) due to the associated long-horizon nature of the problem and the lack of sufficient positive signal during learning. Various tools have been applied to address this challenge. When available, large sets of demonstrations can guide agent exploration. Hindsight relabelling on the other hand does not require additional source","authors_text":"Jean-Baptiste Regli, Jon Scholz, Markus Wulfmeier, Oleg Sushkov, Stefan Schaal, Todor Davchev, Yusuf Aytar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-01T16:12:32Z","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00597","kind":"arxiv","version":3},"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":"sha256:3816f088d581e211ceb9dfa4998d1f31ac767dcb041edeaff3f30cc546e824ba","target":"record","created_at":"2026-07-05T04:07:06Z","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":"918c14a47f9452219e7985e7be8b90e656ae97e2ff798e22df3127230e89b932","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-01T16:12:32Z","title_canon_sha256":"0c869c3ff1c6590d4f7a7d14829965f891225442ed9660705f7a81aea52850a0"},"schema_version":"1.0","source":{"id":"2112.00597","kind":"arxiv","version":3}},"canonical_sha256":"13358e3397afa5b5a9d4e9b665552a98c369558373c72320518d889b4de3f99d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13358e3397afa5b5a9d4e9b665552a98c369558373c72320518d889b4de3f99d","first_computed_at":"2026-07-05T04:07:06.755212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:06.755212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4c9eIFZjfPvyJ4BzY53IazDqm/Nu/gM2lix540mDqcVpSUbg7LEzA/tujP8NGlCoG82oASLOOwXKz4I8JuL7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:06.755620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00597","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3816f088d581e211ceb9dfa4998d1f31ac767dcb041edeaff3f30cc546e824ba","sha256:6ad60d56cfd7a5049c567b5b1066d16a6610308767b34ca6fa3c39c59a208f15"],"state_sha256":"d77ed38986011f67e49ddedfbf6b9d22ec0acb4f37e097f9715ad3029912bab7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKLCi5nZ7uSAvReJYT3gQZBa8f7KYmt0r1QtSDbMNb9XAclf/yAlHhqaJ1843OGHNVKrTGkCTESUg6GwS1jsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:09:59.680579Z","bundle_sha256":"848170183f3ecf09f5e72b5d52d545fe03c49f49e2fe68e2db4119df475cffd0"}}