{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RXCW2X7ZVPMJVZOGO7GAW24LWF","short_pith_number":"pith:RXCW2X7Z","canonical_record":{"source":{"id":"1810.05017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T13:46:18Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"628ccceb3a2e49774dc63ab3c322616cb51488427573672ef45cc890586e2bb3","abstract_canon_sha256":"c44ab855f8367176e62d249d39e01353921166424c18f486ccb5a8cfdf1ae9df"},"schema_version":"1.0"},"canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","source":{"kind":"arxiv","id":"1810.05017","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05017","created_at":"2026-05-18T00:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05017v1","created_at":"2026-05-18T00:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05017","created_at":"2026-05-18T00:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"RXCW2X7ZVPMJ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RXCW2X7ZVPMJVZOG","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RXCW2X7Z","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RXCW2X7ZVPMJVZOGO7GAW24LWF","target":"record","payload":{"canonical_record":{"source":{"id":"1810.05017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T13:46:18Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"628ccceb3a2e49774dc63ab3c322616cb51488427573672ef45cc890586e2bb3","abstract_canon_sha256":"c44ab855f8367176e62d249d39e01353921166424c18f486ccb5a8cfdf1ae9df"},"schema_version":"1.0"},"canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:35.213614Z","signature_b64":"78Gw9mGShOS3tMnpWdy/y2JwzHMWF8TdDiLQhI7qMxZG4/hQV452+/xFR9QwCrlFK62jiri1xR24c/yvzhYtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","last_reissued_at":"2026-05-18T00:03:35.213127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:35.213127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.05017","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":"2026-05-18T00:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7yO1FuJvJs82WSup6Gxtd/5c6dNA/dqnfHWlv8xAlH6gIR6GWL8rPiLERF/cowjUMUq8BKbroUDq35AKrLSdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:57:24.956360Z"},"content_sha256":"4ec18730f6bae727443d66006f3d3b13acf10dcb30a60401ae83d6ae1add0dbc","schema_version":"1.0","event_id":"sha256:4ec18730f6bae727443d66006f3d3b13acf10dcb30a60401ae83d6ae1add0dbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RXCW2X7ZVPMJVZOGO7GAW24LWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"David Budden, Gabriel Barth-Maron, Matt W. Hoffman, Nando de Freitas, Scott Reed, Sergio G\\'omez Colmenarejo, Serkan Cabi, Tobias Pfaff, Tom Le Paine, Yusuf Aytar, Ziyu Wang","submitted_at":"2018-10-11T13:46:18Z","abstract_excerpt":"Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05017","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":"2026-05-18T00:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rBHuBVtW7KDzwIeRzeWLH75nlkFNCapxZcu5XAm381WRYytsE+EHRzzCSVxmOwNshpp8CGBBFLtAXiSyIIhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:57:24.956719Z"},"content_sha256":"d3317d2fc64cb4b6faba3735749f713df4595ee1ba24d3c7abba854649e6314a","schema_version":"1.0","event_id":"sha256:d3317d2fc64cb4b6faba3735749f713df4595ee1ba24d3c7abba854649e6314a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/bundle.json","state_url":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/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":"2026-05-19T11:57:24Z","links":{"resolver":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF","bundle":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/bundle.json","state":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RXCW2X7ZVPMJVZOGO7GAW24LWF","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":"c44ab855f8367176e62d249d39e01353921166424c18f486ccb5a8cfdf1ae9df","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T13:46:18Z","title_canon_sha256":"628ccceb3a2e49774dc63ab3c322616cb51488427573672ef45cc890586e2bb3"},"schema_version":"1.0","source":{"id":"1810.05017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05017","created_at":"2026-05-18T00:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05017v1","created_at":"2026-05-18T00:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05017","created_at":"2026-05-18T00:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"RXCW2X7ZVPMJ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RXCW2X7ZVPMJVZOG","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RXCW2X7Z","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:d3317d2fc64cb4b6faba3735749f713df4595ee1ba24d3c7abba854649e6314a","target":"graph","created_at":"2026-05-18T00:03:35Z","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":"Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing a","authors_text":"David Budden, Gabriel Barth-Maron, Matt W. Hoffman, Nando de Freitas, Scott Reed, Sergio G\\'omez Colmenarejo, Serkan Cabi, Tobias Pfaff, Tom Le Paine, Yusuf Aytar, Ziyu Wang","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T13:46:18Z","title":"One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05017","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":"sha256:4ec18730f6bae727443d66006f3d3b13acf10dcb30a60401ae83d6ae1add0dbc","target":"record","created_at":"2026-05-18T00:03:35Z","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":"c44ab855f8367176e62d249d39e01353921166424c18f486ccb5a8cfdf1ae9df","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T13:46:18Z","title_canon_sha256":"628ccceb3a2e49774dc63ab3c322616cb51488427573672ef45cc890586e2bb3"},"schema_version":"1.0","source":{"id":"1810.05017","kind":"arxiv","version":1}},"canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","first_computed_at":"2026-05-18T00:03:35.213127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:35.213127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"78Gw9mGShOS3tMnpWdy/y2JwzHMWF8TdDiLQhI7qMxZG4/hQV452+/xFR9QwCrlFK62jiri1xR24c/yvzhYtCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:35.213614Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.05017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ec18730f6bae727443d66006f3d3b13acf10dcb30a60401ae83d6ae1add0dbc","sha256:d3317d2fc64cb4b6faba3735749f713df4595ee1ba24d3c7abba854649e6314a"],"state_sha256":"4ccc5cf0507853d2cd45660a7af188f560f2cc2090379d8e0140c57b975c4441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3fMiJsFg75O1uyITiE47Z/yHNH2D6O0z+4YKt4HbLC6hsvdaSr0YXtPmBHBzPOvNfb72n5svU1c3fPIoDakAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T11:57:24.958347Z","bundle_sha256":"6736e47143e9b2aad2c15ba7f3a471a6f745dd647f2f93c5fb78dcd7e3ff4168"}}