{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZSY752PYBAB7BKQBGYS4L3VHOE","short_pith_number":"pith:ZSY752PY","canonical_record":{"source":{"id":"2210.06964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T12:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"e6211959d04ec3efcf3d2c4a117d365967dbe8ec20e82d1c5618074f25196e7a","abstract_canon_sha256":"97d4daede188853f8183c6b779ae8cf7e284e41e627ae003de9eec1c37647aad"},"schema_version":"1.0"},"canonical_sha256":"ccb1fee9f80803f0aa013625c5eea771043f212e837c0a2efb1f027fd3f2f818","source":{"kind":"arxiv","id":"2210.06964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06964","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06964v1","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06964","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZSY752PYBAB7","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZSY752PYBAB7BKQB","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZSY752PY","created_at":"2026-07-05T05:06:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZSY752PYBAB7BKQBGYS4L3VHOE","target":"record","payload":{"canonical_record":{"source":{"id":"2210.06964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T12:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"e6211959d04ec3efcf3d2c4a117d365967dbe8ec20e82d1c5618074f25196e7a","abstract_canon_sha256":"97d4daede188853f8183c6b779ae8cf7e284e41e627ae003de9eec1c37647aad"},"schema_version":"1.0"},"canonical_sha256":"ccb1fee9f80803f0aa013625c5eea771043f212e837c0a2efb1f027fd3f2f818","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:22.973876Z","signature_b64":"tvbXvQBRm7Eqm6H0XX99JOi0UzJGca6CX3EIKl96HCI3zMxGRcxqsnLe3kID7jmuQwrkdh03rf1zJItZ2/pUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccb1fee9f80803f0aa013625c5eea771043f212e837c0a2efb1f027fd3f2f818","last_reissued_at":"2026-07-05T05:06:22.973485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:22.973485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.06964","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":"2026-07-05T05:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+dGK96hpT/geNGby2GTYhDPz6BHjymWdm3BZjhK+rI7lvJhSYvduFoztEBqQQxxfeRVt1EBFOd6FY217Sa19BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:38.441609Z"},"content_sha256":"ed67dbb693ae0f6bbfa3e2e0131449b289b42f7aab4f7323f0429877a30aefa6","schema_version":"1.0","event_id":"sha256:ed67dbb693ae0f6bbfa3e2e0131449b289b42f7aab4f7323f0429877a30aefa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZSY752PYBAB7BKQBGYS4L3VHOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaming Guo, Ke Tang, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Xishan Zhang, Yunji Chen, Zidong Du","submitted_at":"2022-10-13T12:42:48Z","abstract_excerpt":"Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e.g., subgoals or options). However, how to automatically discover high-quality hierarchical structures is still a great challenge. Previous HRL methods can hardly discover the hierarchical structures in complex environments due to the low exploration efficiency by exploiting the randomness-driven exploration paradigm. To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06964","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/2210.06964/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":"2026-07-05T05:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGJw+6lw8EXM09ft/rQnxkCAV9m4vHiK2A9vZ42tGltTcgb9pqb+vOhiDKcN/va3K768WC+o1KKcPtQ9by4bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:38.441993Z"},"content_sha256":"ce45e8e889aecda1a0ab0a8288fb09a46c0ae3152afad264d962dd4b187c1b74","schema_version":"1.0","event_id":"sha256:ce45e8e889aecda1a0ab0a8288fb09a46c0ae3152afad264d962dd4b187c1b74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSY752PYBAB7BKQBGYS4L3VHOE/bundle.json","state_url":"https://pith.science/pith/ZSY752PYBAB7BKQBGYS4L3VHOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSY752PYBAB7BKQBGYS4L3VHOE/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":"2026-07-07T06:39:38Z","links":{"resolver":"https://pith.science/pith/ZSY752PYBAB7BKQBGYS4L3VHOE","bundle":"https://pith.science/pith/ZSY752PYBAB7BKQBGYS4L3VHOE/bundle.json","state":"https://pith.science/pith/ZSY752PYBAB7BKQBGYS4L3VHOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSY752PYBAB7BKQBGYS4L3VHOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZSY752PYBAB7BKQBGYS4L3VHOE","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":"97d4daede188853f8183c6b779ae8cf7e284e41e627ae003de9eec1c37647aad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T12:42:48Z","title_canon_sha256":"e6211959d04ec3efcf3d2c4a117d365967dbe8ec20e82d1c5618074f25196e7a"},"schema_version":"1.0","source":{"id":"2210.06964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06964","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06964v1","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06964","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZSY752PYBAB7","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZSY752PYBAB7BKQB","created_at":"2026-07-05T05:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZSY752PY","created_at":"2026-07-05T05:06:22Z"}],"graph_snapshots":[{"event_id":"sha256:ce45e8e889aecda1a0ab0a8288fb09a46c0ae3152afad264d962dd4b187c1b74","target":"graph","created_at":"2026-07-05T05:06:22Z","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/2210.06964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e.g., subgoals or options). However, how to automatically discover high-quality hierarchical structures is still a great challenge. Previous HRL methods can hardly discover the hierarchical structures in complex environments due to the low exploration efficiency by exploiting the randomness-driven exploration paradigm. To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning fram","authors_text":"Jiaming Guo, Ke Tang, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Xishan Zhang, Yunji Chen, Zidong Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T12:42:48Z","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06964","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:ed67dbb693ae0f6bbfa3e2e0131449b289b42f7aab4f7323f0429877a30aefa6","target":"record","created_at":"2026-07-05T05:06:22Z","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":"97d4daede188853f8183c6b779ae8cf7e284e41e627ae003de9eec1c37647aad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T12:42:48Z","title_canon_sha256":"e6211959d04ec3efcf3d2c4a117d365967dbe8ec20e82d1c5618074f25196e7a"},"schema_version":"1.0","source":{"id":"2210.06964","kind":"arxiv","version":1}},"canonical_sha256":"ccb1fee9f80803f0aa013625c5eea771043f212e837c0a2efb1f027fd3f2f818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb1fee9f80803f0aa013625c5eea771043f212e837c0a2efb1f027fd3f2f818","first_computed_at":"2026-07-05T05:06:22.973485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:22.973485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvbXvQBRm7Eqm6H0XX99JOi0UzJGca6CX3EIKl96HCI3zMxGRcxqsnLe3kID7jmuQwrkdh03rf1zJItZ2/pUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:22.973876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed67dbb693ae0f6bbfa3e2e0131449b289b42f7aab4f7323f0429877a30aefa6","sha256:ce45e8e889aecda1a0ab0a8288fb09a46c0ae3152afad264d962dd4b187c1b74"],"state_sha256":"05883680759191ce1ada5fe86b80fbf1ba47b61a0d8ad690760c5ae5be460161"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJsizumlpbJBaRPxzr+70hVBafq25riIo7tieBLGTG9knrIZKqoNXbj8ducFVr44UH74NqaUvCbSaRfOK9WTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:39:38.444126Z","bundle_sha256":"0868255b9baf005f23cbb3a26b881817391d1e50cb62aa3ae1f61417388dbb62"}}