{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FQJ4SE5NLLS3VUF5SKKQROORF4","short_pith_number":"pith:FQJ4SE5N","canonical_record":{"source":{"id":"1703.01703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-06T02:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"58f1fc5e38153b76dacf46caea1d38ef3de9bf09a544a976ce80457b0d122d2a","abstract_canon_sha256":"3db0eaabd5ad4b141d2e0fed1d8fd3a81d22dcb69fde467d007ed918b91762e1"},"schema_version":"1.0"},"canonical_sha256":"2c13c913ad5ae5bad0bd929508b9d12f13c0ad0dd3433876e6474e3b92dcab5b","source":{"kind":"arxiv","id":"1703.01703","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01703","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01703v2","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01703","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"FQJ4SE5NLLS3","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"FQJ4SE5NLLS3VUF5","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"FQJ4SE5N","created_at":"2026-07-05T00:06:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FQJ4SE5NLLS3VUF5SKKQROORF4","target":"record","payload":{"canonical_record":{"source":{"id":"1703.01703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-06T02:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"58f1fc5e38153b76dacf46caea1d38ef3de9bf09a544a976ce80457b0d122d2a","abstract_canon_sha256":"3db0eaabd5ad4b141d2e0fed1d8fd3a81d22dcb69fde467d007ed918b91762e1"},"schema_version":"1.0"},"canonical_sha256":"2c13c913ad5ae5bad0bd929508b9d12f13c0ad0dd3433876e6474e3b92dcab5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:03.312762Z","signature_b64":"CWM7t22aw9dy/pnEGd8ftdcdFLWdrL9rAi21V3dZA257d7IRzTTFQXsHNGBWCjOirZDLAB6cPih1wcmHl4SzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c13c913ad5ae5bad0bd929508b9d12f13c0ad0dd3433876e6474e3b92dcab5b","last_reissued_at":"2026-07-05T00:06:03.312336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:03.312336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.01703","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":"2026-07-05T00:06:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"goR6WkfGQH0eefhJdxwoFSjQlNXQS/fCfn0mXK/2syK75GxZPsPOD2P/rQ3N59OksdWPtyadxKPW6APH/1bgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:00:39.022409Z"},"content_sha256":"55c098df2fe8fe905aa98edaa65e51e7997a4517131054ec56c5592aa5880268","schema_version":"1.0","event_id":"sha256:55c098df2fe8fe905aa98edaa65e51e7997a4517131054ec56c5592aa5880268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FQJ4SE5NLLS3VUF5SKKQROORF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Third-Person Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bradly C. Stadie, Ilya Sutskever, Pieter Abbeel","submitted_at":"2017-03-06T02:02:34Z","abstract_excerpt":"Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to optimize. Traditionally, imitation learning in RL has been used to overcome this problem. Unfortunately, hitherto imitation learning methods tend to require that demonstrations are supplied in the first-person: the agent is provided with a sequence of states and a specification of the actions that it should have taken. While powerful, this kind of imitation learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01703","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/1703.01703/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":"2026-07-05T00:06:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnFZ/o5JwuHVig9PBeRV9+pecVVrHmgP+l04OAB/Bz5xpF4oeADx8/3rS5ZNJxC0QkaYW9MwNebx85xoBREcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:00:39.022923Z"},"content_sha256":"91a5327bb6e1c6904444717f6d122c12a118e5e8842aec483d755ebadfc5de62","schema_version":"1.0","event_id":"sha256:91a5327bb6e1c6904444717f6d122c12a118e5e8842aec483d755ebadfc5de62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQJ4SE5NLLS3VUF5SKKQROORF4/bundle.json","state_url":"https://pith.science/pith/FQJ4SE5NLLS3VUF5SKKQROORF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQJ4SE5NLLS3VUF5SKKQROORF4/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":"2026-08-08T19:00:39Z","links":{"resolver":"https://pith.science/pith/FQJ4SE5NLLS3VUF5SKKQROORF4","bundle":"https://pith.science/pith/FQJ4SE5NLLS3VUF5SKKQROORF4/bundle.json","state":"https://pith.science/pith/FQJ4SE5NLLS3VUF5SKKQROORF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQJ4SE5NLLS3VUF5SKKQROORF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FQJ4SE5NLLS3VUF5SKKQROORF4","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":"3db0eaabd5ad4b141d2e0fed1d8fd3a81d22dcb69fde467d007ed918b91762e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-06T02:02:34Z","title_canon_sha256":"58f1fc5e38153b76dacf46caea1d38ef3de9bf09a544a976ce80457b0d122d2a"},"schema_version":"1.0","source":{"id":"1703.01703","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01703","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01703v2","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01703","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"FQJ4SE5NLLS3","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"FQJ4SE5NLLS3VUF5","created_at":"2026-07-05T00:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"FQJ4SE5N","created_at":"2026-07-05T00:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:91a5327bb6e1c6904444717f6d122c12a118e5e8842aec483d755ebadfc5de62","target":"graph","created_at":"2026-07-05T00:06:03Z","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/1703.01703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to optimize. Traditionally, imitation learning in RL has been used to overcome this problem. Unfortunately, hitherto imitation learning methods tend to require that demonstrations are supplied in the first-person: the agent is provided with a sequence of states and a specification of the actions that it should have taken. While powerful, this kind of imitation learni","authors_text":"Bradly C. Stadie, Ilya Sutskever, Pieter Abbeel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-06T02:02:34Z","title":"Third-Person Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01703","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":"sha256:55c098df2fe8fe905aa98edaa65e51e7997a4517131054ec56c5592aa5880268","target":"record","created_at":"2026-07-05T00:06:03Z","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":"3db0eaabd5ad4b141d2e0fed1d8fd3a81d22dcb69fde467d007ed918b91762e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-06T02:02:34Z","title_canon_sha256":"58f1fc5e38153b76dacf46caea1d38ef3de9bf09a544a976ce80457b0d122d2a"},"schema_version":"1.0","source":{"id":"1703.01703","kind":"arxiv","version":2}},"canonical_sha256":"2c13c913ad5ae5bad0bd929508b9d12f13c0ad0dd3433876e6474e3b92dcab5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c13c913ad5ae5bad0bd929508b9d12f13c0ad0dd3433876e6474e3b92dcab5b","first_computed_at":"2026-07-05T00:06:03.312336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:06:03.312336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWM7t22aw9dy/pnEGd8ftdcdFLWdrL9rAi21V3dZA257d7IRzTTFQXsHNGBWCjOirZDLAB6cPih1wcmHl4SzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:06:03.312762Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01703","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55c098df2fe8fe905aa98edaa65e51e7997a4517131054ec56c5592aa5880268","sha256:91a5327bb6e1c6904444717f6d122c12a118e5e8842aec483d755ebadfc5de62"],"state_sha256":"e2219292849d63454ac4bd236df12df695c817edc742a002d042086f1b6c18ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sENN9aGIFbo44b/HawW96a5NKGpDb3WBaWP+A2nF4KpI+8rmOwijwTQebaE8PjgtFY+cZW/ERYbLMpGHFaNXCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:00:39.027697Z","bundle_sha256":"5ad37624185e45a84a58710fa7a6b412513adfd7e650ab7a8190704d32ca74ce"}}