{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QMZO4XRSZ7SLHLBXKP4JBPPKPX","short_pith_number":"pith:QMZO4XRS","canonical_record":{"source":{"id":"1710.09767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T15:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"c09996fd77f0f69353c40639788ffc323a32999911ea6b3149f4f5d34382e1be","abstract_canon_sha256":"56bdf2cf57f49c95bfc717c40b5c85dafe9277481f56521ee0ffe8c86601522e"},"schema_version":"1.0"},"canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","source":{"kind":"arxiv","id":"1710.09767","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.09767","created_at":"2026-05-18T00:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.09767v1","created_at":"2026-05-18T00:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09767","created_at":"2026-05-18T00:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"QMZO4XRSZ7SL","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QMZO4XRSZ7SLHLBX","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QMZO4XRS","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QMZO4XRSZ7SLHLBXKP4JBPPKPX","target":"record","payload":{"canonical_record":{"source":{"id":"1710.09767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T15:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"c09996fd77f0f69353c40639788ffc323a32999911ea6b3149f4f5d34382e1be","abstract_canon_sha256":"56bdf2cf57f49c95bfc717c40b5c85dafe9277481f56521ee0ffe8c86601522e"},"schema_version":"1.0"},"canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:56.520259Z","signature_b64":"6t3CxxruJy6jAEKEVNrPM/TK8YNdd56LAi8CY1w9WDqvmRA2g0qd8OcMOD0JjmoM5V8kbGcOhFj1BSCFlodnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","last_reissued_at":"2026-05-18T00:31:56.519704Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:56.519704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.09767","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":"2026-05-18T00:31:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgOvDjg+bdJSrnxeXHimEWRskf6VPS4G+0tyLgbFRi5rJGBWIFgZjYyHpEB7D8XRrbbTeUZvxeF9EOsYUxy6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:05:35.043715Z"},"content_sha256":"f778fb30c7e43977c9bd487806701516a95dc7d9bf7f1b92218dd2fa51e53588","schema_version":"1.0","event_id":"sha256:f778fb30c7e43977c9bd487806701516a95dc7d9bf7f1b92218dd2fa51e53588"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QMZO4XRSZ7SLHLBXKP4JBPPKPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta Learning Shared Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"John Schulman, Jonathan Ho, Kevin Frans, Pieter Abbeel, Xi Chen","submitted_at":"2017-10-26T15:43:33Z","abstract_excerpt":"We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically, a set of primitives are shared within a distribution of tasks, and are switched between by task-specific policies. We provide a concrete metric for measuring the strength of such hierarchies, leading to an optimization problem for quickly reaching high reward on unseen tasks. We then present an algorithm to solve this problem end-to-end through the use of an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09767","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":""},"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":"2026-05-18T00:31:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1bVdS7NgaMm3cdHUoDeGz2SDLoZOB0c3HpOdCIKiphvksDM3VEXIxyotF8yjrAUlFSmvxkkPQZTLKpDi4OABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:05:35.044430Z"},"content_sha256":"25b0fb981644d3a89090b6357767d2a414720f239b942c7f601ac51ab2965d38","schema_version":"1.0","event_id":"sha256:25b0fb981644d3a89090b6357767d2a414720f239b942c7f601ac51ab2965d38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/bundle.json","state_url":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/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":"2026-05-23T19:05:35Z","links":{"resolver":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX","bundle":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/bundle.json","state":"https://pith.science/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMZO4XRSZ7SLHLBXKP4JBPPKPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QMZO4XRSZ7SLHLBXKP4JBPPKPX","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":"56bdf2cf57f49c95bfc717c40b5c85dafe9277481f56521ee0ffe8c86601522e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T15:43:33Z","title_canon_sha256":"c09996fd77f0f69353c40639788ffc323a32999911ea6b3149f4f5d34382e1be"},"schema_version":"1.0","source":{"id":"1710.09767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.09767","created_at":"2026-05-18T00:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.09767v1","created_at":"2026-05-18T00:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09767","created_at":"2026-05-18T00:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"QMZO4XRSZ7SL","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QMZO4XRSZ7SLHLBX","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QMZO4XRS","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:25b0fb981644d3a89090b6357767d2a414720f239b942c7f601ac51ab2965d38","target":"graph","created_at":"2026-05-18T00:31:56Z","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":"We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically, a set of primitives are shared within a distribution of tasks, and are switched between by task-specific policies. We provide a concrete metric for measuring the strength of such hierarchies, leading to an optimization problem for quickly reaching high reward on unseen tasks. We then present an algorithm to solve this problem end-to-end through the use of an","authors_text":"John Schulman, Jonathan Ho, Kevin Frans, Pieter Abbeel, Xi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T15:43:33Z","title":"Meta Learning Shared Hierarchies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09767","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:f778fb30c7e43977c9bd487806701516a95dc7d9bf7f1b92218dd2fa51e53588","target":"record","created_at":"2026-05-18T00:31:56Z","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":"56bdf2cf57f49c95bfc717c40b5c85dafe9277481f56521ee0ffe8c86601522e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T15:43:33Z","title_canon_sha256":"c09996fd77f0f69353c40639788ffc323a32999911ea6b3149f4f5d34382e1be"},"schema_version":"1.0","source":{"id":"1710.09767","kind":"arxiv","version":1}},"canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8332ee5e32cfe4b3ac3753f890bdea7df6e8a99a803306ec4b24490dafd15b92","first_computed_at":"2026-05-18T00:31:56.519704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:56.519704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6t3CxxruJy6jAEKEVNrPM/TK8YNdd56LAi8CY1w9WDqvmRA2g0qd8OcMOD0JjmoM5V8kbGcOhFj1BSCFlodnAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:56.520259Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.09767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f778fb30c7e43977c9bd487806701516a95dc7d9bf7f1b92218dd2fa51e53588","sha256:25b0fb981644d3a89090b6357767d2a414720f239b942c7f601ac51ab2965d38"],"state_sha256":"d304939a3597df1c890773e6faf3266686ba63c339328c6079d7db717817d891"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WUnsYHfLCX2SvsXNfTYML0AbNrdSuChBEm7VjW4TgVg7af1f6YWkSzerrbz0nXHNNRIO4cOb0IcEZL2v9WbBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T19:05:35.048541Z","bundle_sha256":"448af4b52dfe4f2f5cc5dfc943aeae995d00db3c7d730dafc382db492ea5054f"}}