{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OTMW4C5CHOJB2GH6LGW2YF75UH","short_pith_number":"pith:OTMW4C5C","canonical_record":{"source":{"id":"1709.04083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T23:17:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"352e79d8a3e4c78721f51b4387f10ade41aa8939b1dfc70e060a6de949536043","abstract_canon_sha256":"e2b9cc1da42aa517a3d1ceb73c9f93ef0abbfe23b12308739899fe5e2355c9c9"},"schema_version":"1.0"},"canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","source":{"kind":"arxiv","id":"1709.04083","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04083","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04083v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04083","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"OTMW4C5CHOJB","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OTMW4C5CHOJB2GH6","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OTMW4C5C","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OTMW4C5CHOJB2GH6LGW2YF75UH","target":"record","payload":{"canonical_record":{"source":{"id":"1709.04083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T23:17:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"352e79d8a3e4c78721f51b4387f10ade41aa8939b1dfc70e060a6de949536043","abstract_canon_sha256":"e2b9cc1da42aa517a3d1ceb73c9f93ef0abbfe23b12308739899fe5e2355c9c9"},"schema_version":"1.0"},"canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.962185Z","signature_b64":"pBsyVeopUh+gE47ty1PsUlXPEho+IPeSQN5Dr0wwUj5NKw8+vOzTAk2Sc4gW5ct9VbS0gfZvZgAMBKrdXy0pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","last_reissued_at":"2026-05-17T23:49:17.961708Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.961708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.04083","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":"2026-05-17T23:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ulGSC/5OgP+S/m70m5CncRfXHLBL6HPztoCagasjVmWTTAVRJGeP06jq7be2C+cS7YV4gZEveX80HTqdpHbwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:59:07.129278Z"},"content_sha256":"05d8c4bdb1c2289865aa2058ba167bdc57a0d26d2a6242da2d518ce6fe7f7177","schema_version":"1.0","event_id":"sha256:05d8c4bdb1c2289865aa2058ba167bdc57a0d26d2a6242da2d518ce6fe7f7177"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OTMW4C5CHOJB2GH6LGW2YF75UH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gabriel V. de la Cruz Jr, Matthew E. Taylor, Yunshu Du","submitted_at":"2017-09-12T23:17:45Z","abstract_excerpt":"Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from the raw images in addition to learning a policy. As a result, deep RL can require a prohibitively large amount of training time and data to reach reasonable performance, making it difficult to use deep RL in real-world applications, especially when data is expensive. In this work, we speed up training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04083","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":"2026-05-17T23:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pxxzRqyPGTDaTAeLXzu7TQoRe3wFtpkhbqOJnN0n7sWsvUzjMI8244WU0SHmFaQ0sjaOrfR2r9i0Zrosqo7sDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:59:07.129782Z"},"content_sha256":"2fd792e25099799ccdd74c63090acfa1911dbf0005fb7ccbb787a5192999c9e0","schema_version":"1.0","event_id":"sha256:2fd792e25099799ccdd74c63090acfa1911dbf0005fb7ccbb787a5192999c9e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/bundle.json","state_url":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/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":"2026-05-31T12:59:07Z","links":{"resolver":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH","bundle":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/bundle.json","state":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OTMW4C5CHOJB2GH6LGW2YF75UH","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":"e2b9cc1da42aa517a3d1ceb73c9f93ef0abbfe23b12308739899fe5e2355c9c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T23:17:45Z","title_canon_sha256":"352e79d8a3e4c78721f51b4387f10ade41aa8939b1dfc70e060a6de949536043"},"schema_version":"1.0","source":{"id":"1709.04083","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04083","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04083v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04083","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"OTMW4C5CHOJB","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OTMW4C5CHOJB2GH6","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OTMW4C5C","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:2fd792e25099799ccdd74c63090acfa1911dbf0005fb7ccbb787a5192999c9e0","target":"graph","created_at":"2026-05-17T23:49:17Z","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 (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from the raw images in addition to learning a policy. As a result, deep RL can require a prohibitively large amount of training time and data to reach reasonable performance, making it difficult to use deep RL in real-world applications, especially when data is expensive. In this work, we speed up training","authors_text":"Gabriel V. de la Cruz Jr, Matthew E. Taylor, Yunshu Du","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T23:17:45Z","title":"Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04083","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":"sha256:05d8c4bdb1c2289865aa2058ba167bdc57a0d26d2a6242da2d518ce6fe7f7177","target":"record","created_at":"2026-05-17T23:49:17Z","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":"e2b9cc1da42aa517a3d1ceb73c9f93ef0abbfe23b12308739899fe5e2355c9c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T23:17:45Z","title_canon_sha256":"352e79d8a3e4c78721f51b4387f10ade41aa8939b1dfc70e060a6de949536043"},"schema_version":"1.0","source":{"id":"1709.04083","kind":"arxiv","version":2}},"canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","first_computed_at":"2026-05-17T23:49:17.961708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:17.961708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pBsyVeopUh+gE47ty1PsUlXPEho+IPeSQN5Dr0wwUj5NKw8+vOzTAk2Sc4gW5ct9VbS0gfZvZgAMBKrdXy0pAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:17.962185Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.04083","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05d8c4bdb1c2289865aa2058ba167bdc57a0d26d2a6242da2d518ce6fe7f7177","sha256:2fd792e25099799ccdd74c63090acfa1911dbf0005fb7ccbb787a5192999c9e0"],"state_sha256":"088072869ebfd20df859bb391ad32d348b76825311f18b2ed92a1684c31a152e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0o/dt/ero/Yge3lZ6NDz9lgohyD/yH4UF98F4NqUQV4gRqtoRWyS1t9o6gQTi6j+NwurV6qdJYwGQaNLGeivBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T12:59:07.133416Z","bundle_sha256":"0682c2f4b59348217b953b3d9c9476c067cb97a7ed93f3b2cef7f79cc7771728"}}