{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZFPF3RVPPFN636UKPT6XH5RMT3","short_pith_number":"pith:ZFPF3RVP","canonical_record":{"source":{"id":"1805.11592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T17:19:36Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"bc4194e2c9cea053d4f994826b7ab6e0d56e209cfcf7b65401114f6251274cef","abstract_canon_sha256":"feba5f7adea23c33ce347dfff8aa10470c263263ba59ebbe88ea543327f41dbc"},"schema_version":"1.0"},"canonical_sha256":"c95e5dc6af795bedfa8a7cfd73f62c9ef708a69b2951f50e0ef6a47094b17abf","source":{"kind":"arxiv","id":"1805.11592","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11592","created_at":"2026-05-17T23:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11592v2","created_at":"2026-05-17T23:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11592","created_at":"2026-05-17T23:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZFPF3RVPPFN6","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZFPF3RVPPFN636UK","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZFPF3RVP","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZFPF3RVPPFN636UKPT6XH5RMT3","target":"record","payload":{"canonical_record":{"source":{"id":"1805.11592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T17:19:36Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"bc4194e2c9cea053d4f994826b7ab6e0d56e209cfcf7b65401114f6251274cef","abstract_canon_sha256":"feba5f7adea23c33ce347dfff8aa10470c263263ba59ebbe88ea543327f41dbc"},"schema_version":"1.0"},"canonical_sha256":"c95e5dc6af795bedfa8a7cfd73f62c9ef708a69b2951f50e0ef6a47094b17abf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:32.609063Z","signature_b64":"1dUjojpLSid3a36Musb8Kxzrn1GCpyWBx84IyafasqI8id/sgDFaG0iqv1L+WwLCHVuu/skLIUQdBTLb4RIJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c95e5dc6af795bedfa8a7cfd73f62c9ef708a69b2951f50e0ef6a47094b17abf","last_reissued_at":"2026-05-17T23:59:32.608446Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:32.608446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.11592","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":"2026-05-17T23:59:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxTCJKsoQEhhI5SV783vlBw7LOypAhHNxpLDARhfSVYZhRXAJLCt+3GxuX2zf16iJxDBODl4vHPnZ5BP9jdOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:17:46.270080Z"},"content_sha256":"37a93f209423ae246e3649df1d48f4168147551b6af0efd37be7a532051ff472","schema_version":"1.0","event_id":"sha256:37a93f209423ae246e3649df1d48f4168147551b6af0efd37be7a532051ff472"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZFPF3RVPPFN636UKPT6XH5RMT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Playing hard exploration games by watching YouTube","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Budden, Nando de Freitas, Tobias Pfaff, Tom Le Paine, Yusuf Aytar, Ziyu Wang","submitted_at":"2018-05-29T17:19:36Z","abstract_excerpt":"Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator. However, these demonstrations are typically collected under artificial conditions, i.e. with access to the agent's exact environment setup and the demonstrator's action and reward trajectories. Here we propose a two-stage method that overcomes these limitations by relying on noisy, unaligned footage without access to such data. First, we learn to map una"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11592","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":"2026-05-17T23:59:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I/lAAmjg0i9AVuOLlDV5AntSh2WkiYl/jZXlaWUi1FRUBVEDwcqu8ky7ouIwvKbZIWTcH8rO9kx9CKF6rD2OBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:17:46.270473Z"},"content_sha256":"c5580d98276b281587b5e6559fea8bada7652b4521f4864375392ac58981c6e3","schema_version":"1.0","event_id":"sha256:c5580d98276b281587b5e6559fea8bada7652b4521f4864375392ac58981c6e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFPF3RVPPFN636UKPT6XH5RMT3/bundle.json","state_url":"https://pith.science/pith/ZFPF3RVPPFN636UKPT6XH5RMT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFPF3RVPPFN636UKPT6XH5RMT3/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":"2026-05-30T21:17:46Z","links":{"resolver":"https://pith.science/pith/ZFPF3RVPPFN636UKPT6XH5RMT3","bundle":"https://pith.science/pith/ZFPF3RVPPFN636UKPT6XH5RMT3/bundle.json","state":"https://pith.science/pith/ZFPF3RVPPFN636UKPT6XH5RMT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFPF3RVPPFN636UKPT6XH5RMT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZFPF3RVPPFN636UKPT6XH5RMT3","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":"feba5f7adea23c33ce347dfff8aa10470c263263ba59ebbe88ea543327f41dbc","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T17:19:36Z","title_canon_sha256":"bc4194e2c9cea053d4f994826b7ab6e0d56e209cfcf7b65401114f6251274cef"},"schema_version":"1.0","source":{"id":"1805.11592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11592","created_at":"2026-05-17T23:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11592v2","created_at":"2026-05-17T23:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11592","created_at":"2026-05-17T23:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZFPF3RVPPFN6","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZFPF3RVPPFN636UK","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZFPF3RVP","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:c5580d98276b281587b5e6559fea8bada7652b4521f4864375392ac58981c6e3","target":"graph","created_at":"2026-05-17T23:59:32Z","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":"Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator. However, these demonstrations are typically collected under artificial conditions, i.e. with access to the agent's exact environment setup and the demonstrator's action and reward trajectories. Here we propose a two-stage method that overcomes these limitations by relying on noisy, unaligned footage without access to such data. First, we learn to map una","authors_text":"David Budden, Nando de Freitas, Tobias Pfaff, Tom Le Paine, Yusuf Aytar, Ziyu Wang","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T17:19:36Z","title":"Playing hard exploration games by watching YouTube"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11592","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":"sha256:37a93f209423ae246e3649df1d48f4168147551b6af0efd37be7a532051ff472","target":"record","created_at":"2026-05-17T23:59:32Z","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":"feba5f7adea23c33ce347dfff8aa10470c263263ba59ebbe88ea543327f41dbc","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T17:19:36Z","title_canon_sha256":"bc4194e2c9cea053d4f994826b7ab6e0d56e209cfcf7b65401114f6251274cef"},"schema_version":"1.0","source":{"id":"1805.11592","kind":"arxiv","version":2}},"canonical_sha256":"c95e5dc6af795bedfa8a7cfd73f62c9ef708a69b2951f50e0ef6a47094b17abf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c95e5dc6af795bedfa8a7cfd73f62c9ef708a69b2951f50e0ef6a47094b17abf","first_computed_at":"2026-05-17T23:59:32.608446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:32.608446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1dUjojpLSid3a36Musb8Kxzrn1GCpyWBx84IyafasqI8id/sgDFaG0iqv1L+WwLCHVuu/skLIUQdBTLb4RIJBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:32.609063Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37a93f209423ae246e3649df1d48f4168147551b6af0efd37be7a532051ff472","sha256:c5580d98276b281587b5e6559fea8bada7652b4521f4864375392ac58981c6e3"],"state_sha256":"a16e1b838e80d3bd727c7f85a4dd7056acbe06db522f4ec67a7833af0a5401a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TdOgf1rnFW+QoNAk/tHNl0+XV31pS34IHjNd4xUXJgn5hc9nM0ADwUgVQJil2Ze3pazcRptAhwTAVqZkd1sqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T21:17:46.273485Z","bundle_sha256":"8e035a1f99219887898bea4be7a35a9600042ec2a7f289c7cc76a6f7f643173a"}}