{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZVPM4VFTGEI2FLKBMEPPSPWBSA","short_pith_number":"pith:ZVPM4VFT","canonical_record":{"source":{"id":"1905.01537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T18:22:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"423b504c979561afb4a5db7fb435cda3d6e7db2d9e5eda6998a9a059796bf32f","abstract_canon_sha256":"696d2e1eb5bd8ec7febc294be38d67abfa1d717907942cf1c8a72eff4c40399a"},"schema_version":"1.0"},"canonical_sha256":"cd5ece54b33111a2ad41611ef93ec1900a9a722a202abd8ca5d37dcf7c4f8613","source":{"kind":"arxiv","id":"1905.01537","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01537","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01537v2","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01537","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZVPM4VFTGEI2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZVPM4VFTGEI2FLKB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZVPM4VFT","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZVPM4VFTGEI2FLKBMEPPSPWBSA","target":"record","payload":{"canonical_record":{"source":{"id":"1905.01537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T18:22:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"423b504c979561afb4a5db7fb435cda3d6e7db2d9e5eda6998a9a059796bf32f","abstract_canon_sha256":"696d2e1eb5bd8ec7febc294be38d67abfa1d717907942cf1c8a72eff4c40399a"},"schema_version":"1.0"},"canonical_sha256":"cd5ece54b33111a2ad41611ef93ec1900a9a722a202abd8ca5d37dcf7c4f8613","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:15.107346Z","signature_b64":"UlCu6QDYk5GgK14jKaIyFKr9XMgdiI6aiNVzYplTS3ZBQkmK/yAZtNnJ5dF4LX8c0i1B4IHlPAzh116J1PegCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd5ece54b33111a2ad41611ef93ec1900a9a722a202abd8ca5d37dcf7c4f8613","last_reissued_at":"2026-05-17T23:42:15.106687Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:15.106687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.01537","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":"2026-05-17T23:42:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuX8Q8vUND8GQSGk9pkNoPWPHaMaeNg0cABR34QgEE7PMmMCK3f8zxoVFfoponBDeP9qhAhSmR6N2xtaF8n5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:48:10.967746Z"},"content_sha256":"11d058befd9a935e90605c42fc5361d09f2acc26755439d209fc9be2e4be154f","schema_version":"1.0","event_id":"sha256:11d058befd9a935e90605c42fc5361d09f2acc26755439d209fc9be2e4be154f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZVPM4VFTGEI2FLKBMEPPSPWBSA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Policy Learning is Sensitive to Goal Space Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arjun K. Bansal, Madhavun Candadai, Mariano Phielipp, Zach Dwiel","submitted_at":"2019-05-04T18:22:32Z","abstract_excerpt":"Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transferability of sub-policies to tasks outside the training distribution. It is often implemented as a master policy providing goals to a sub-policy. Ideally, we would like the goal-spaces to be learned, however, properties of optimal goal spaces still remain unknown and consequently there is no method yet to learn optimal goal spaces. Motivated by this, we systematically analyze how various modifications to the ground-trut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01537","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":""},"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":"2026-05-17T23:42:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cRB2PjwnZo82ossSQ0OHpJdYgQrnnE0sDJwAqUw0IPX48W3DxEg60CuwkTbgZ1jzS7ncuj6s06Rmx8xRycfZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:48:10.968213Z"},"content_sha256":"7ffb49520d55654e1c846406222e05a820906073f5c84d1861cd3a76b6f63f85","schema_version":"1.0","event_id":"sha256:7ffb49520d55654e1c846406222e05a820906073f5c84d1861cd3a76b6f63f85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA/bundle.json","state_url":"https://pith.science/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA/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":"2026-05-29T21:48:10Z","links":{"resolver":"https://pith.science/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA","bundle":"https://pith.science/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA/bundle.json","state":"https://pith.science/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVPM4VFTGEI2FLKBMEPPSPWBSA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZVPM4VFTGEI2FLKBMEPPSPWBSA","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":"696d2e1eb5bd8ec7febc294be38d67abfa1d717907942cf1c8a72eff4c40399a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T18:22:32Z","title_canon_sha256":"423b504c979561afb4a5db7fb435cda3d6e7db2d9e5eda6998a9a059796bf32f"},"schema_version":"1.0","source":{"id":"1905.01537","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01537","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01537v2","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01537","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZVPM4VFTGEI2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZVPM4VFTGEI2FLKB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZVPM4VFT","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:7ffb49520d55654e1c846406222e05a820906073f5c84d1861cd3a76b6f63f85","target":"graph","created_at":"2026-05-17T23:42:15Z","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"},"paper":{"abstract_excerpt":"Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transferability of sub-policies to tasks outside the training distribution. It is often implemented as a master policy providing goals to a sub-policy. Ideally, we would like the goal-spaces to be learned, however, properties of optimal goal spaces still remain unknown and consequently there is no method yet to learn optimal goal spaces. Motivated by this, we systematically analyze how various modifications to the ground-trut","authors_text":"Arjun K. Bansal, Madhavun Candadai, Mariano Phielipp, Zach Dwiel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T18:22:32Z","title":"Hierarchical Policy Learning is Sensitive to Goal Space Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01537","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":"sha256:11d058befd9a935e90605c42fc5361d09f2acc26755439d209fc9be2e4be154f","target":"record","created_at":"2026-05-17T23:42:15Z","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":"696d2e1eb5bd8ec7febc294be38d67abfa1d717907942cf1c8a72eff4c40399a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T18:22:32Z","title_canon_sha256":"423b504c979561afb4a5db7fb435cda3d6e7db2d9e5eda6998a9a059796bf32f"},"schema_version":"1.0","source":{"id":"1905.01537","kind":"arxiv","version":2}},"canonical_sha256":"cd5ece54b33111a2ad41611ef93ec1900a9a722a202abd8ca5d37dcf7c4f8613","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd5ece54b33111a2ad41611ef93ec1900a9a722a202abd8ca5d37dcf7c4f8613","first_computed_at":"2026-05-17T23:42:15.106687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:15.106687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UlCu6QDYk5GgK14jKaIyFKr9XMgdiI6aiNVzYplTS3ZBQkmK/yAZtNnJ5dF4LX8c0i1B4IHlPAzh116J1PegCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:15.107346Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01537","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11d058befd9a935e90605c42fc5361d09f2acc26755439d209fc9be2e4be154f","sha256:7ffb49520d55654e1c846406222e05a820906073f5c84d1861cd3a76b6f63f85"],"state_sha256":"501831a520d997aea32188ae2c3efc28357aa94bd51407342487da5ded322368"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QbGxP2+Nr94pIIPafZgbfvAHXFH8/SKaGrg1mV0ji0QIx2dKuJ6YUZKbDu21sMPS/d9LubatYLwUFK0TUqR7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:48:10.971764Z","bundle_sha256":"c585986978b3869927f8e170ae21ad85f8b59f4a85956972df5451ced2b71b72"}}