{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XGPRP2XEUP6Z7HGF3GF2CFV6SP","short_pith_number":"pith:XGPRP2XE","canonical_record":{"source":{"id":"1707.03631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-12T10:25:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e1b9687c8aa34bb32595a942725ec4976673ed4a0d123af12d231a7862317ef2","abstract_canon_sha256":"1b5a41a1f3d848d624f5e6e184ba6a1167b65f70142cce26085862d9b71062cf"},"schema_version":"1.0"},"canonical_sha256":"b99f17eae4a3fd9f9cc5d98ba116be93ee63c94a9ff841fffe856d8776315d52","source":{"kind":"arxiv","id":"1707.03631","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03631","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03631v2","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03631","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"XGPRP2XEUP6Z","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XGPRP2XEUP6Z7HGF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XGPRP2XE","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XGPRP2XEUP6Z7HGF3GF2CFV6SP","target":"record","payload":{"canonical_record":{"source":{"id":"1707.03631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-12T10:25:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e1b9687c8aa34bb32595a942725ec4976673ed4a0d123af12d231a7862317ef2","abstract_canon_sha256":"1b5a41a1f3d848d624f5e6e184ba6a1167b65f70142cce26085862d9b71062cf"},"schema_version":"1.0"},"canonical_sha256":"b99f17eae4a3fd9f9cc5d98ba116be93ee63c94a9ff841fffe856d8776315d52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:03.810386Z","signature_b64":"W5c+cPOaMfObZiii17J3j4GWQSA6cXLonqxML+raULyTkokPznr3/0ckKAZuqVWMZam3QiH/tK8NZ4mX3TrHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b99f17eae4a3fd9f9cc5d98ba116be93ee63c94a9ff841fffe856d8776315d52","last_reissued_at":"2026-05-18T00:35:03.809580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:03.809580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.03631","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":"2026-05-18T00:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"94xGrIw2yladPxoPxyCww4yHwS9hk6rBbZ+1xfzt0cwJ2gchKap4c+FqjeRZjk2jSkWtn+4qlOYNrp80G/BODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:52:48.604823Z"},"content_sha256":"1074ea2d21fc192b04ff57427f27d936083530502e5aeb77d224249b7d482106","schema_version":"1.0","event_id":"sha256:1074ea2d21fc192b04ff57427f27d936083530502e5aeb77d224249b7d482106"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XGPRP2XEUP6Z7HGF3GF2CFV6SP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Dropout for Supervised and Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Il-Chul Moon, Jun-Keon Park, Su-Jin Shin, Sungrae Park","submitted_at":"2017-07-12T10:25:57Z","abstract_excerpt":"Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually biased inputs to enhance the generality, this paper introduces adversarial dropout, which is a minimal set of dropouts that maximize the divergence between the outputs from the network with the dropouts and the training supervisions. The identified adversarial dropout are used to reconfigure the neural network to train, and we demonstrated that training on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03631","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":"2026-05-18T00:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvRntiksbBUgwZ3juxf5K1ZpC2/GSeBS8jG2etG6XbgsozhtOCUTz0Z5bCfe04oAc+d89Y3ETpZ67r0JnW4ACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:52:48.605509Z"},"content_sha256":"6bd398bc23548c29366d579c406d9928b34e067c0402987b82168df80d9e628b","schema_version":"1.0","event_id":"sha256:6bd398bc23548c29366d579c406d9928b34e067c0402987b82168df80d9e628b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP/bundle.json","state_url":"https://pith.science/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP/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":"2026-05-25T16:52:48Z","links":{"resolver":"https://pith.science/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP","bundle":"https://pith.science/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP/bundle.json","state":"https://pith.science/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGPRP2XEUP6Z7HGF3GF2CFV6SP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XGPRP2XEUP6Z7HGF3GF2CFV6SP","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":"1b5a41a1f3d848d624f5e6e184ba6a1167b65f70142cce26085862d9b71062cf","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-12T10:25:57Z","title_canon_sha256":"e1b9687c8aa34bb32595a942725ec4976673ed4a0d123af12d231a7862317ef2"},"schema_version":"1.0","source":{"id":"1707.03631","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03631","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03631v2","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03631","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"XGPRP2XEUP6Z","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XGPRP2XEUP6Z7HGF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XGPRP2XE","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:6bd398bc23548c29366d579c406d9928b34e067c0402987b82168df80d9e628b","target":"graph","created_at":"2026-05-18T00:35:03Z","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"},"paper":{"abstract_excerpt":"Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually biased inputs to enhance the generality, this paper introduces adversarial dropout, which is a minimal set of dropouts that maximize the divergence between the outputs from the network with the dropouts and the training supervisions. The identified adversarial dropout are used to reconfigure the neural network to train, and we demonstrated that training on ","authors_text":"Il-Chul Moon, Jun-Keon Park, Su-Jin Shin, Sungrae Park","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-12T10:25:57Z","title":"Adversarial Dropout for Supervised and Semi-supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03631","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":"sha256:1074ea2d21fc192b04ff57427f27d936083530502e5aeb77d224249b7d482106","target":"record","created_at":"2026-05-18T00:35:03Z","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":"1b5a41a1f3d848d624f5e6e184ba6a1167b65f70142cce26085862d9b71062cf","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-12T10:25:57Z","title_canon_sha256":"e1b9687c8aa34bb32595a942725ec4976673ed4a0d123af12d231a7862317ef2"},"schema_version":"1.0","source":{"id":"1707.03631","kind":"arxiv","version":2}},"canonical_sha256":"b99f17eae4a3fd9f9cc5d98ba116be93ee63c94a9ff841fffe856d8776315d52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b99f17eae4a3fd9f9cc5d98ba116be93ee63c94a9ff841fffe856d8776315d52","first_computed_at":"2026-05-18T00:35:03.809580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:03.809580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W5c+cPOaMfObZiii17J3j4GWQSA6cXLonqxML+raULyTkokPznr3/0ckKAZuqVWMZam3QiH/tK8NZ4mX3TrHCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:03.810386Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03631","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1074ea2d21fc192b04ff57427f27d936083530502e5aeb77d224249b7d482106","sha256:6bd398bc23548c29366d579c406d9928b34e067c0402987b82168df80d9e628b"],"state_sha256":"64750ea7a61a58d92b6857c322795e37975b3f7f668bfaf8c5970b68f95f87dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bbo/QQKlid9pmV6J0jREK86MWsfrK2tGQ6Q77AHQtUzOEiqiHNulnnQzHzDYCND6nGlhZLtI5iqBlldU3tkwBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:52:48.609251Z","bundle_sha256":"01e1be209a29628dc8e1fb3dc30d10101288ccca0410e7cc549397967ce69915"}}