{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FJ5UL4N33KK4AWUL6Y6FRWG2WE","short_pith_number":"pith:FJ5UL4N3","canonical_record":{"source":{"id":"1703.07326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-21T17:22:29Z","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"8d25935a0f80329d326982660863a3151a905fd6b34d1b31dcc6343b58b4e4ac","abstract_canon_sha256":"51a8136eea5287ab748f888675d6f03e4d423ba90d8acdbe37b7c487d30c777b"},"schema_version":"1.0"},"canonical_sha256":"2a7b45f1bbda95c05a8bf63c58d8dab10e951830b61436c87b6e1a4517453724","source":{"kind":"arxiv","id":"1703.07326","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07326","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07326v3","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07326","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"FJ5UL4N33KK4","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJ5UL4N33KK4AWUL","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJ5UL4N3","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FJ5UL4N33KK4AWUL6Y6FRWG2WE","target":"record","payload":{"canonical_record":{"source":{"id":"1703.07326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-21T17:22:29Z","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"8d25935a0f80329d326982660863a3151a905fd6b34d1b31dcc6343b58b4e4ac","abstract_canon_sha256":"51a8136eea5287ab748f888675d6f03e4d423ba90d8acdbe37b7c487d30c777b"},"schema_version":"1.0"},"canonical_sha256":"2a7b45f1bbda95c05a8bf63c58d8dab10e951830b61436c87b6e1a4517453724","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:56.197094Z","signature_b64":"AryDrdttsw+btDMKwjWKMx2S4Z4h26tRCa6KKIWx8qwryVdWtqHj9z7HnsUGgz6qVYnY2FLf2p2zcXcmu2tYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a7b45f1bbda95c05a8bf63c58d8dab10e951830b61436c87b6e1a4517453724","last_reissued_at":"2026-05-18T00:28:56.196552Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:56.196552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.07326","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5HXxCp2pjRG5ifghP0Q8E5FUo8vHrbEjYa3yPcoJgFdsmDoBtbA2PYZ9fJCl1behLUfob4B1ryaHo1u0WqnqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:13:06.184239Z"},"content_sha256":"8e6c86f7753f58b18e6712c617b8da39a51a20301781f6281108ba129136f498","schema_version":"1.0","event_id":"sha256:8e6c86f7753f58b18e6712c617b8da39a51a20301781f6281108ba129136f498"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FJ5UL4N33KK4AWUL6Y6FRWG2WE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One-Shot Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.AI","authors_text":"Bradly C. Stadie, Ilya Sutskever, Jonas Schneider, Jonathan Ho, Marcin Andrychowicz, Pieter Abbeel, Wojciech Zaremba, Yan Duan","submitted_at":"2017-03-21T17:22:29Z","abstract_excerpt":"Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we call one-shot imitation learning.\n  Specifically, we consider the setting where there is a very large s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07326","kind":"arxiv","version":3},"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":"2026-05-18T00:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3KvLHbk6TMMsDI4p0TB86h/riNzfoL6OAClyGldbH8VAZpUNFOoe2E2Y0sbc/TufTQ6c/WCwWKiglQKW3/Q/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:13:06.184940Z"},"content_sha256":"5213cde3376e1287a4d93390492d1ea0f4f62e27a0e0eda1d325f11382199256","schema_version":"1.0","event_id":"sha256:5213cde3376e1287a4d93390492d1ea0f4f62e27a0e0eda1d325f11382199256"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE/bundle.json","state_url":"https://pith.science/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE/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":"2026-05-27T09:13:06Z","links":{"resolver":"https://pith.science/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE","bundle":"https://pith.science/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE/bundle.json","state":"https://pith.science/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJ5UL4N33KK4AWUL6Y6FRWG2WE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FJ5UL4N33KK4AWUL6Y6FRWG2WE","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":"51a8136eea5287ab748f888675d6f03e4d423ba90d8acdbe37b7c487d30c777b","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-21T17:22:29Z","title_canon_sha256":"8d25935a0f80329d326982660863a3151a905fd6b34d1b31dcc6343b58b4e4ac"},"schema_version":"1.0","source":{"id":"1703.07326","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07326","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07326v3","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07326","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"FJ5UL4N33KK4","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJ5UL4N33KK4AWUL","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJ5UL4N3","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:5213cde3376e1287a4d93390492d1ea0f4f62e27a0e0eda1d325f11382199256","target":"graph","created_at":"2026-05-18T00:28:56Z","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":"Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we call one-shot imitation learning.\n  Specifically, we consider the setting where there is a very large s","authors_text":"Bradly C. Stadie, Ilya Sutskever, Jonas Schneider, Jonathan Ho, Marcin Andrychowicz, Pieter Abbeel, Wojciech Zaremba, Yan Duan","cross_cats":["cs.LG","cs.NE","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-21T17:22:29Z","title":"One-Shot Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07326","kind":"arxiv","version":3},"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":"sha256:8e6c86f7753f58b18e6712c617b8da39a51a20301781f6281108ba129136f498","target":"record","created_at":"2026-05-18T00:28:56Z","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":"51a8136eea5287ab748f888675d6f03e4d423ba90d8acdbe37b7c487d30c777b","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-21T17:22:29Z","title_canon_sha256":"8d25935a0f80329d326982660863a3151a905fd6b34d1b31dcc6343b58b4e4ac"},"schema_version":"1.0","source":{"id":"1703.07326","kind":"arxiv","version":3}},"canonical_sha256":"2a7b45f1bbda95c05a8bf63c58d8dab10e951830b61436c87b6e1a4517453724","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a7b45f1bbda95c05a8bf63c58d8dab10e951830b61436c87b6e1a4517453724","first_computed_at":"2026-05-18T00:28:56.196552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:56.196552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AryDrdttsw+btDMKwjWKMx2S4Z4h26tRCa6KKIWx8qwryVdWtqHj9z7HnsUGgz6qVYnY2FLf2p2zcXcmu2tYDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:56.197094Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.07326","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e6c86f7753f58b18e6712c617b8da39a51a20301781f6281108ba129136f498","sha256:5213cde3376e1287a4d93390492d1ea0f4f62e27a0e0eda1d325f11382199256"],"state_sha256":"7be6d1854f5327b98ea4fb8fc853707405f49ce58aceb64b45d5911c9760b9af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I4iSd8OeNfFRJHmXcReRKLCeFVRlYp41ksVGHT7DDEkilwdOtS/qw97IoD0QUc7aay0pCFew5kfK7lZISZEfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T09:13:06.188624Z","bundle_sha256":"b6a083d7911ebe1424c1d5c59c5fc6ce2e307a57c0b4ac4fd3b75aef43f253ed"}}