{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4IGY2NJV44JJMLIRWMHRATZBQG","short_pith_number":"pith:4IGY2NJV","canonical_record":{"source":{"id":"1809.06781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T18:59:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"66a6900f6f572a31458092ccf18e8b32b8c82dec988eff7115984671aa732299","abstract_canon_sha256":"c23c30c4427146b6b67d624bcae012c0ffa06e4f7534302b97854f2b049b6083"},"schema_version":"1.0"},"canonical_sha256":"e20d8d3535e712962d11b30f104f2181a141c0e62700b17fa9993463d8a4315f","source":{"kind":"arxiv","id":"1809.06781","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06781","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06781v2","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06781","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"4IGY2NJV44JJ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4IGY2NJV44JJMLIR","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4IGY2NJV","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4IGY2NJV44JJMLIRWMHRATZBQG","target":"record","payload":{"canonical_record":{"source":{"id":"1809.06781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T18:59:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"66a6900f6f572a31458092ccf18e8b32b8c82dec988eff7115984671aa732299","abstract_canon_sha256":"c23c30c4427146b6b67d624bcae012c0ffa06e4f7534302b97854f2b049b6083"},"schema_version":"1.0"},"canonical_sha256":"e20d8d3535e712962d11b30f104f2181a141c0e62700b17fa9993463d8a4315f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:39.037401Z","signature_b64":"RN4use1701gYwyCd0HGnzFkGK7jSW2aJgKk3Aao9VGEApRalICtSB9YCrDmkGasiXx1UFGVEzVxCO5laKLvTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e20d8d3535e712962d11b30f104f2181a141c0e62700b17fa9993463d8a4315f","last_reissued_at":"2026-05-18T00:04:39.036955Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:39.036955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.06781","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":"2026-05-18T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/gxQj/iMfYtugy6w6bYPaXwLJMS3y7JQQK5Nw575jxHM22qpj1VFj9oMKYZF7zQKoTZy3JjhC4Q5Avx7hOvVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T00:37:10.289162Z"},"content_sha256":"6eb3d4e5c1df9b4afa16390a7782734f130980df629f3c6100900910a5f1ec47","schema_version":"1.0","event_id":"sha256:6eb3d4e5c1df9b4afa16390a7782734f130980df629f3c6100900910a5f1ec47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4IGY2NJV44JJMLIRWMHRATZBQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Diagnostics for Deep Reinforcement Learning Policy Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"\\c{C}etin Kaya Ko\\c{c}, George Legrady, Jieliang Luo, Peter Feghali, Sam Green","submitted_at":"2018-09-14T18:59:12Z","abstract_excerpt":"Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like black-box functions, but this mindset is especially dangerous when used for control in safety-critical settings. In this paper, we present our extensions of CNN visualization algorithms to the domain of vision-based reinforcement learning. We use a simulated drone environment as an example scenario. These visualization algorithms are an important tool for behav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06781","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":"2026-05-18T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ikeG+C0mrfaBehyyruQWdx6vuNyoaQpXfXvCiIBIAfnBwlcTFR1MWWhQNWfjy0xcIBinUvtK7YgIUIE42q3PBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T00:37:10.289719Z"},"content_sha256":"1328b4ca3fba637f7ea471b712c28b3c7a6464f4e84fe8210b589d5068dd6fa4","schema_version":"1.0","event_id":"sha256:1328b4ca3fba637f7ea471b712c28b3c7a6464f4e84fe8210b589d5068dd6fa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IGY2NJV44JJMLIRWMHRATZBQG/bundle.json","state_url":"https://pith.science/pith/4IGY2NJV44JJMLIRWMHRATZBQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IGY2NJV44JJMLIRWMHRATZBQG/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":"2026-06-06T00:37:10Z","links":{"resolver":"https://pith.science/pith/4IGY2NJV44JJMLIRWMHRATZBQG","bundle":"https://pith.science/pith/4IGY2NJV44JJMLIRWMHRATZBQG/bundle.json","state":"https://pith.science/pith/4IGY2NJV44JJMLIRWMHRATZBQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IGY2NJV44JJMLIRWMHRATZBQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4IGY2NJV44JJMLIRWMHRATZBQG","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":"c23c30c4427146b6b67d624bcae012c0ffa06e4f7534302b97854f2b049b6083","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T18:59:12Z","title_canon_sha256":"66a6900f6f572a31458092ccf18e8b32b8c82dec988eff7115984671aa732299"},"schema_version":"1.0","source":{"id":"1809.06781","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06781","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06781v2","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06781","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"4IGY2NJV44JJ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4IGY2NJV44JJMLIR","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4IGY2NJV","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:1328b4ca3fba637f7ea471b712c28b3c7a6464f4e84fe8210b589d5068dd6fa4","target":"graph","created_at":"2026-05-18T00:04:39Z","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":"Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like black-box functions, but this mindset is especially dangerous when used for control in safety-critical settings. In this paper, we present our extensions of CNN visualization algorithms to the domain of vision-based reinforcement learning. We use a simulated drone environment as an example scenario. These visualization algorithms are an important tool for behav","authors_text":"\\c{C}etin Kaya Ko\\c{c}, George Legrady, Jieliang Luo, Peter Feghali, Sam Green","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T18:59:12Z","title":"Visual Diagnostics for Deep Reinforcement Learning Policy Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06781","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":"sha256:6eb3d4e5c1df9b4afa16390a7782734f130980df629f3c6100900910a5f1ec47","target":"record","created_at":"2026-05-18T00:04:39Z","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":"c23c30c4427146b6b67d624bcae012c0ffa06e4f7534302b97854f2b049b6083","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T18:59:12Z","title_canon_sha256":"66a6900f6f572a31458092ccf18e8b32b8c82dec988eff7115984671aa732299"},"schema_version":"1.0","source":{"id":"1809.06781","kind":"arxiv","version":2}},"canonical_sha256":"e20d8d3535e712962d11b30f104f2181a141c0e62700b17fa9993463d8a4315f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e20d8d3535e712962d11b30f104f2181a141c0e62700b17fa9993463d8a4315f","first_computed_at":"2026-05-18T00:04:39.036955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:39.036955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RN4use1701gYwyCd0HGnzFkGK7jSW2aJgKk3Aao9VGEApRalICtSB9YCrDmkGasiXx1UFGVEzVxCO5laKLvTCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:39.037401Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.06781","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eb3d4e5c1df9b4afa16390a7782734f130980df629f3c6100900910a5f1ec47","sha256:1328b4ca3fba637f7ea471b712c28b3c7a6464f4e84fe8210b589d5068dd6fa4"],"state_sha256":"c31d87f449e39109fd025fb1bf3b0d7480243c3b8dd247e73a15b49df41c7e5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CjHYqh+Qk9r/vLFXdng6YERhvZeGOhwhPnWCAr7/fG3FPB1lFi1Tlcmvk5rIH7JtPnDzZSb6orJcbDgW202jAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T00:37:10.292581Z","bundle_sha256":"81f7396abc47098434a1c376b3e1fe6cb2f6cacd9489aa975eeec18dac058673"}}