{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:TL5KB2AEVXZBOSM27ZHRYWOLIX","short_pith_number":"pith:TL5KB2AE","canonical_record":{"source":{"id":"1708.01697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-05T01:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"c2a339cf6551a27a0bb4608a86ade4b107612910f039c6672829d5d3cc477c04","abstract_canon_sha256":"5643cce7d69b332f59ca250808ab5e03caaa1c411914d43ff8fc084174d6c2d5"},"schema_version":"1.0"},"canonical_sha256":"9afaa0e804adf217499afe4f1c59cb45fadc8f64c081b5e0a2072033677c3838","source":{"kind":"arxiv","id":"1708.01697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01697","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01697v1","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01697","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"TL5KB2AEVXZB","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TL5KB2AEVXZBOSM2","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TL5KB2AE","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:TL5KB2AEVXZBOSM27ZHRYWOLIX","target":"record","payload":{"canonical_record":{"source":{"id":"1708.01697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-05T01:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"c2a339cf6551a27a0bb4608a86ade4b107612910f039c6672829d5d3cc477c04","abstract_canon_sha256":"5643cce7d69b332f59ca250808ab5e03caaa1c411914d43ff8fc084174d6c2d5"},"schema_version":"1.0"},"canonical_sha256":"9afaa0e804adf217499afe4f1c59cb45fadc8f64c081b5e0a2072033677c3838","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:35.152797Z","signature_b64":"UpbXHN8qvWteW5S3XVH2gNMV9LgQCRsce5coUGJebkTlbkts1xz2vkFARcgocWqDFlC0VmosoAkVWJ6wvNIZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9afaa0e804adf217499afe4f1c59cb45fadc8f64c081b5e0a2072033677c3838","last_reissued_at":"2026-05-18T00:38:35.152351Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:35.152351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.01697","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dca1iYIivnnImnLrFMId0QwZq32Pk0G0xyS+u0PJv6Ov6+v6MpJPcCjTgWxQQ0ZdQrhnsKzp00oJc4KuyGzGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:32:37.073820Z"},"content_sha256":"e283b424724aceb6beec70dcd45fb96a5ba9d1e5e7df3fbce99aecc111299808","schema_version":"1.0","event_id":"sha256:e283b424724aceb6beec70dcd45fb96a5ba9d1e5e7df3fbce99aecc111299808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:TL5KB2AEVXZBOSM27ZHRYWOLIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Robustness: Softmax versus Openmax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andras Rozsa, Manuel G\\\"unther, Terrance E. Boult","submitted_at":"2017-08-05T01:44:52Z","abstract_excerpt":"Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications. However, it was discovered that machine learning models, including the best performing DNNs, suffer from a fundamental problem: they can unexpectedly and confidently misclassify examples formed by slightly perturbing otherwise correctly recognized inputs. Various approaches have been developed for efficiently generating these so-called adversarial examples, but those mostly rely on ascending the gradient of loss. In this paper, we introduce the novel logits optimized ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01697","kind":"arxiv","version":1},"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":"2026-05-18T00:38:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oR+5P7L3EFxcTMDozEEsby34ge0yc9ipwkbaNLVRkA82p6ZJDKoPw0k9e/bLnZHvFJP1Rx4kuEDM3gTiME2yCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:32:37.074479Z"},"content_sha256":"079ce6dc6d3195e9f3dd3273df33ede1b8d16f367f275643327701525cb9cc22","schema_version":"1.0","event_id":"sha256:079ce6dc6d3195e9f3dd3273df33ede1b8d16f367f275643327701525cb9cc22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX/bundle.json","state_url":"https://pith.science/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX/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":"2026-05-26T03:32:37Z","links":{"resolver":"https://pith.science/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX","bundle":"https://pith.science/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX/bundle.json","state":"https://pith.science/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TL5KB2AEVXZBOSM27ZHRYWOLIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TL5KB2AEVXZBOSM27ZHRYWOLIX","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":"5643cce7d69b332f59ca250808ab5e03caaa1c411914d43ff8fc084174d6c2d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-05T01:44:52Z","title_canon_sha256":"c2a339cf6551a27a0bb4608a86ade4b107612910f039c6672829d5d3cc477c04"},"schema_version":"1.0","source":{"id":"1708.01697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01697","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01697v1","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01697","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"TL5KB2AEVXZB","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TL5KB2AEVXZBOSM2","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TL5KB2AE","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:079ce6dc6d3195e9f3dd3273df33ede1b8d16f367f275643327701525cb9cc22","target":"graph","created_at":"2026-05-18T00:38:35Z","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 neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications. However, it was discovered that machine learning models, including the best performing DNNs, suffer from a fundamental problem: they can unexpectedly and confidently misclassify examples formed by slightly perturbing otherwise correctly recognized inputs. Various approaches have been developed for efficiently generating these so-called adversarial examples, but those mostly rely on ascending the gradient of loss. In this paper, we introduce the novel logits optimized ta","authors_text":"Andras Rozsa, Manuel G\\\"unther, Terrance E. Boult","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-05T01:44:52Z","title":"Adversarial Robustness: Softmax versus Openmax"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01697","kind":"arxiv","version":1},"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:e283b424724aceb6beec70dcd45fb96a5ba9d1e5e7df3fbce99aecc111299808","target":"record","created_at":"2026-05-18T00:38:35Z","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":"5643cce7d69b332f59ca250808ab5e03caaa1c411914d43ff8fc084174d6c2d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-05T01:44:52Z","title_canon_sha256":"c2a339cf6551a27a0bb4608a86ade4b107612910f039c6672829d5d3cc477c04"},"schema_version":"1.0","source":{"id":"1708.01697","kind":"arxiv","version":1}},"canonical_sha256":"9afaa0e804adf217499afe4f1c59cb45fadc8f64c081b5e0a2072033677c3838","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9afaa0e804adf217499afe4f1c59cb45fadc8f64c081b5e0a2072033677c3838","first_computed_at":"2026-05-18T00:38:35.152351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:35.152351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UpbXHN8qvWteW5S3XVH2gNMV9LgQCRsce5coUGJebkTlbkts1xz2vkFARcgocWqDFlC0VmosoAkVWJ6wvNIZBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:35.152797Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.01697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e283b424724aceb6beec70dcd45fb96a5ba9d1e5e7df3fbce99aecc111299808","sha256:079ce6dc6d3195e9f3dd3273df33ede1b8d16f367f275643327701525cb9cc22"],"state_sha256":"f2490b9e25613d979329816184593d0f44cdff73726e0792b4dd45a3f8b420b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ShcCCQBJ/oITGyRaL6mYNzg1n3FG3aXaNttv/wZtLC4t0npj8XdsUjqozCYvxXFBYk8LGFtXklPsmcg0DsS2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:32:37.078841Z","bundle_sha256":"723de295900e3e29b12f8487d21d47d8120a51bfcecd8851557df5a1682229bd"}}