{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F6HJTJNUOTKD77XUN5A3I5M3SN","short_pith_number":"pith:F6HJTJNU","canonical_record":{"source":{"id":"2301.11741","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T14:25:04Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f7c9a61ab5c424f6fd2ab92ca0cf62e0d11acb9186b567a2baf8c679e9ef036a","abstract_canon_sha256":"5a7f6fef0d98f7c3c0eae8e214e8d6550aac1eea54f088f931f1aabefe1b6f65"},"schema_version":"1.0"},"canonical_sha256":"2f8e99a5b474d43ffef46f41b4759b9379af5268a864fa7fc9da8b8c7ba4132e","source":{"kind":"arxiv","id":"2301.11741","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11741","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11741v3","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11741","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"F6HJTJNUOTKD","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"F6HJTJNUOTKD77XU","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"F6HJTJNU","created_at":"2026-07-05T05:43:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F6HJTJNUOTKD77XUN5A3I5M3SN","target":"record","payload":{"canonical_record":{"source":{"id":"2301.11741","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T14:25:04Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f7c9a61ab5c424f6fd2ab92ca0cf62e0d11acb9186b567a2baf8c679e9ef036a","abstract_canon_sha256":"5a7f6fef0d98f7c3c0eae8e214e8d6550aac1eea54f088f931f1aabefe1b6f65"},"schema_version":"1.0"},"canonical_sha256":"2f8e99a5b474d43ffef46f41b4759b9379af5268a864fa7fc9da8b8c7ba4132e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:19.365114Z","signature_b64":"GkG8zk25NdqDpE26tB0K5RiJdSHyJ332F6Uk6ReMmOdY1uQNBmWIBqDaFE6ZPDFxTBoNF23w4UpHvihzzxqhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f8e99a5b474d43ffef46f41b4759b9379af5268a864fa7fc9da8b8c7ba4132e","last_reissued_at":"2026-07-05T05:43:19.364652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:19.364652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.11741","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":"2026-07-05T05:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2fPYDS2J2TExNPEqpo0uea1/PaJa2oF5/IPkEy4tIC2WgxdvkyEHSsaLnOvg7lLFvNGqnRvDN2CyTSFpN6bLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:43:39.455851Z"},"content_sha256":"d11f7b294506748fcdfe0de96e02867f5eda5434e89440b065a35a7afbcf8889","schema_version":"1.0","event_id":"sha256:d11f7b294506748fcdfe0de96e02867f5eda5434e89440b065a35a7afbcf8889"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F6HJTJNUOTKD77XUN5A3I5M3SN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daesol Cho, H. Jin Kim, Seungjae Lee","submitted_at":"2023-01-27T14:25:04Z","abstract_excerpt":"Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a sequence of surrogate tasks, shows reasonable results, most of the previous works still have difficulty in proposing curriculum due to the absence of a mechanism for obtaining calibrated guidance to the desired outcome state without any prior domain knowledge. To alleviate it, we propose an uncertainty & temporal distance-aware curriculum goal generation me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11741","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/2301.11741/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":"2026-07-05T05:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6e26ZJ3Xj66GL/M8HFBwtZsx0eImBJKG9VQ2q2LjTHRQvVD8UsxRLP74U6ztCkwCGDHGx87r1TmMK0A6hkzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:43:39.456740Z"},"content_sha256":"039df845925b69de23c6cc3ff6140a4f298c70e607620b2677ce47d4b6fc8094","schema_version":"1.0","event_id":"sha256:039df845925b69de23c6cc3ff6140a4f298c70e607620b2677ce47d4b6fc8094"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F6HJTJNUOTKD77XUN5A3I5M3SN/bundle.json","state_url":"https://pith.science/pith/F6HJTJNUOTKD77XUN5A3I5M3SN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F6HJTJNUOTKD77XUN5A3I5M3SN/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":"2026-08-21T01:43:39Z","links":{"resolver":"https://pith.science/pith/F6HJTJNUOTKD77XUN5A3I5M3SN","bundle":"https://pith.science/pith/F6HJTJNUOTKD77XUN5A3I5M3SN/bundle.json","state":"https://pith.science/pith/F6HJTJNUOTKD77XUN5A3I5M3SN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F6HJTJNUOTKD77XUN5A3I5M3SN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F6HJTJNUOTKD77XUN5A3I5M3SN","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":"5a7f6fef0d98f7c3c0eae8e214e8d6550aac1eea54f088f931f1aabefe1b6f65","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T14:25:04Z","title_canon_sha256":"f7c9a61ab5c424f6fd2ab92ca0cf62e0d11acb9186b567a2baf8c679e9ef036a"},"schema_version":"1.0","source":{"id":"2301.11741","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11741","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11741v3","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11741","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"F6HJTJNUOTKD","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"F6HJTJNUOTKD77XU","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"F6HJTJNU","created_at":"2026-07-05T05:43:19Z"}],"graph_snapshots":[{"event_id":"sha256:039df845925b69de23c6cc3ff6140a4f298c70e607620b2677ce47d4b6fc8094","target":"graph","created_at":"2026-07-05T05:43:19Z","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/2301.11741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a sequence of surrogate tasks, shows reasonable results, most of the previous works still have difficulty in proposing curriculum due to the absence of a mechanism for obtaining calibrated guidance to the desired outcome state without any prior domain knowledge. To alleviate it, we propose an uncertainty & temporal distance-aware curriculum goal generation me","authors_text":"Daesol Cho, H. Jin Kim, Seungjae Lee","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T14:25:04Z","title":"Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11741","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:d11f7b294506748fcdfe0de96e02867f5eda5434e89440b065a35a7afbcf8889","target":"record","created_at":"2026-07-05T05:43:19Z","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":"5a7f6fef0d98f7c3c0eae8e214e8d6550aac1eea54f088f931f1aabefe1b6f65","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T14:25:04Z","title_canon_sha256":"f7c9a61ab5c424f6fd2ab92ca0cf62e0d11acb9186b567a2baf8c679e9ef036a"},"schema_version":"1.0","source":{"id":"2301.11741","kind":"arxiv","version":3}},"canonical_sha256":"2f8e99a5b474d43ffef46f41b4759b9379af5268a864fa7fc9da8b8c7ba4132e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f8e99a5b474d43ffef46f41b4759b9379af5268a864fa7fc9da8b8c7ba4132e","first_computed_at":"2026-07-05T05:43:19.364652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:19.364652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkG8zk25NdqDpE26tB0K5RiJdSHyJ332F6Uk6ReMmOdY1uQNBmWIBqDaFE6ZPDFxTBoNF23w4UpHvihzzxqhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:19.365114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11741","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d11f7b294506748fcdfe0de96e02867f5eda5434e89440b065a35a7afbcf8889","sha256:039df845925b69de23c6cc3ff6140a4f298c70e607620b2677ce47d4b6fc8094"],"state_sha256":"21b2ba1f64926b3190cba59c5f8cbab32ee6aedc1176e01371019ef5a98df70c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cjVHZK5qvnnTtg/JgKcMX79Sj6F7zeg+1eLk4mwd/RYxnPF/44AcZTclTTw7+ImGZ6ntGWcusaGjqfUC32fdBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T01:43:39.461966Z","bundle_sha256":"02f5bb83433616c54abcd69414d1ff54fdd0af539a95aeb848b65f41275fedc6"}}