{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TCNJDQHS7CWQ64QRBQNADQ6WQ7","short_pith_number":"pith:TCNJDQHS","canonical_record":{"source":{"id":"1909.10618","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T21:11:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"609a3f77e8c2ae3412b9001753703a0613a557e18fc35d3b9ae8314dd9ca3128","abstract_canon_sha256":"3ac9d29e809abd18ee569453107580610cce872bc1bd1022893041e7972b3ef6"},"schema_version":"1.0"},"canonical_sha256":"989a91c0f2f8ad0f72110c1a01c3d687ed8cf104d341e5f2401770eebf3aae4d","source":{"kind":"arxiv","id":"1909.10618","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.10618","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"1909.10618v2","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10618","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"TCNJDQHS7CWQ","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"TCNJDQHS7CWQ64QR","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"TCNJDQHS","created_at":"2026-07-05T00:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TCNJDQHS7CWQ64QRBQNADQ6WQ7","target":"record","payload":{"canonical_record":{"source":{"id":"1909.10618","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T21:11:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"609a3f77e8c2ae3412b9001753703a0613a557e18fc35d3b9ae8314dd9ca3128","abstract_canon_sha256":"3ac9d29e809abd18ee569453107580610cce872bc1bd1022893041e7972b3ef6"},"schema_version":"1.0"},"canonical_sha256":"989a91c0f2f8ad0f72110c1a01c3d687ed8cf104d341e5f2401770eebf3aae4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:54.063802Z","signature_b64":"D/XULy4VD2/MP6Uya6c4cDzOD1FPDKl+nKewXb1xSJtW/4Qf7DVi6TjJGC43zEZQnbdDGSctVktimq3bFB3NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"989a91c0f2f8ad0f72110c1a01c3d687ed8cf104d341e5f2401770eebf3aae4d","last_reissued_at":"2026-07-05T00:28:54.063336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:54.063336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.10618","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5u+l1s/1Z5dod7+x688SdkLFNhE3dPYNANUncJHhXCx2evEfI3GdNjfWxOoPIcf5TPou9Ob06C/X4hl3Py+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:36:55.616439Z"},"content_sha256":"3b65d2652c3b852cbe4fcc3a90e128a5b7f660f2823150275dcafd63a8761a1c","schema_version":"1.0","event_id":"sha256:3b65d2652c3b852cbe4fcc3a90e128a5b7f660f2823150275dcafd63a8761a1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TCNJDQHS7CWQ64QRBQNADQ6WQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoran Tang, Honglak Lee, Ofir Nachum, Sergey Levine, Shixiang Gu, Xingyu Lu","submitted_at":"2019-09-23T21:11:30Z","abstract_excerpt":"Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended periods, and training and exploring in a more semantically meaningful action space, among others. However, in fully observed, Markovian settings, it is not immediately clear why hierarchical RL should provide benefits over standard \"shallow\" RL architectures. In this work, we iso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10618","kind":"arxiv","version":2},"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/1909.10618/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":"2026-07-05T00:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YXG7CYo0IqgGXRSFScBG3PFjf5WsiqnOB4/IVJ3ns/RHsHSO0TnKsRpRaWjt1xD5KCmPCbxt7zjzJ6kDJb3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:36:55.616969Z"},"content_sha256":"91aa58f435a700047f27cc8a6ec6c2f0d6e649b53399d7afdd32102c6adc341a","schema_version":"1.0","event_id":"sha256:91aa58f435a700047f27cc8a6ec6c2f0d6e649b53399d7afdd32102c6adc341a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7/bundle.json","state_url":"https://pith.science/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7/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":"2026-08-05T18:36:55Z","links":{"resolver":"https://pith.science/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7","bundle":"https://pith.science/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7/bundle.json","state":"https://pith.science/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCNJDQHS7CWQ64QRBQNADQ6WQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TCNJDQHS7CWQ64QRBQNADQ6WQ7","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":"3ac9d29e809abd18ee569453107580610cce872bc1bd1022893041e7972b3ef6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T21:11:30Z","title_canon_sha256":"609a3f77e8c2ae3412b9001753703a0613a557e18fc35d3b9ae8314dd9ca3128"},"schema_version":"1.0","source":{"id":"1909.10618","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.10618","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"1909.10618v2","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10618","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"TCNJDQHS7CWQ","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"TCNJDQHS7CWQ64QR","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"TCNJDQHS","created_at":"2026-07-05T00:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:91aa58f435a700047f27cc8a6ec6c2f0d6e649b53399d7afdd32102c6adc341a","target":"graph","created_at":"2026-07-05T00:28:54Z","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/1909.10618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended periods, and training and exploring in a more semantically meaningful action space, among others. However, in fully observed, Markovian settings, it is not immediately clear why hierarchical RL should provide benefits over standard \"shallow\" RL architectures. In this work, we iso","authors_text":"Haoran Tang, Honglak Lee, Ofir Nachum, Sergey Levine, Shixiang Gu, Xingyu Lu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T21:11:30Z","title":"Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10618","kind":"arxiv","version":2},"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":"sha256:3b65d2652c3b852cbe4fcc3a90e128a5b7f660f2823150275dcafd63a8761a1c","target":"record","created_at":"2026-07-05T00:28:54Z","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":"3ac9d29e809abd18ee569453107580610cce872bc1bd1022893041e7972b3ef6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T21:11:30Z","title_canon_sha256":"609a3f77e8c2ae3412b9001753703a0613a557e18fc35d3b9ae8314dd9ca3128"},"schema_version":"1.0","source":{"id":"1909.10618","kind":"arxiv","version":2}},"canonical_sha256":"989a91c0f2f8ad0f72110c1a01c3d687ed8cf104d341e5f2401770eebf3aae4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"989a91c0f2f8ad0f72110c1a01c3d687ed8cf104d341e5f2401770eebf3aae4d","first_computed_at":"2026-07-05T00:28:54.063336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:54.063336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D/XULy4VD2/MP6Uya6c4cDzOD1FPDKl+nKewXb1xSJtW/4Qf7DVi6TjJGC43zEZQnbdDGSctVktimq3bFB3NBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:54.063802Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.10618","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b65d2652c3b852cbe4fcc3a90e128a5b7f660f2823150275dcafd63a8761a1c","sha256:91aa58f435a700047f27cc8a6ec6c2f0d6e649b53399d7afdd32102c6adc341a"],"state_sha256":"a107b9302c1d26926061abfe7c3bf7475e082f78fe30d60917138f01d86f1ce1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2IE5YEV3j1B7HL4DBGp4lDwFKN+KVWF1jGNOjJBNlqdXx3SR0HeAh1TwXQqD9yhyYWqslMHsqoqB/ej/2BqVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:36:55.621320Z","bundle_sha256":"53b0489fd50d3d27297aa4ef3d23323dd92e4d1a2471fb2cb491bce5180d4526"}}