{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RYDPIK2TJJXFQTBSWW2STCK5HD","short_pith_number":"pith:RYDPIK2T","canonical_record":{"source":{"id":"2210.05938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T06:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"dd646ae48a33e14bbeb27da966eb00c59d9dec93a0f2fa0bd925864b78d54dfb","abstract_canon_sha256":"c159eca4e53f849f147d982881fb7484e679348761265515db09bdb6a1617b5b"},"schema_version":"1.0"},"canonical_sha256":"8e06f42b534a6e584c32b5b529895d38f2edd78ea7549e0f2a715b525ed46535","source":{"kind":"arxiv","id":"2210.05938","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05938","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05938v2","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05938","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"RYDPIK2TJJXF","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"RYDPIK2TJJXFQTBS","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"RYDPIK2T","created_at":"2026-07-05T05:22:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RYDPIK2TJJXFQTBSWW2STCK5HD","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T06:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"dd646ae48a33e14bbeb27da966eb00c59d9dec93a0f2fa0bd925864b78d54dfb","abstract_canon_sha256":"c159eca4e53f849f147d982881fb7484e679348761265515db09bdb6a1617b5b"},"schema_version":"1.0"},"canonical_sha256":"8e06f42b534a6e584c32b5b529895d38f2edd78ea7549e0f2a715b525ed46535","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:30.679610Z","signature_b64":"5ksIBy4J30ykRurTV6XZ1p9WxVP+uUi7aLsEKYM9UFNtCGXTw3eQ4LBo7swz8BXtx1LWrwTG8MKCYaspeaGEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e06f42b534a6e584c32b5b529895d38f2edd78ea7549e0f2a715b525ed46535","last_reissued_at":"2026-07-05T05:22:30.679157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:30.679157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05938","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":"2026-07-05T05:22:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CB2LXCV6VHa8w1SZQgMgdGDlPZ+l4N6xpgf6spG5kkHicYNJaENNu1z8xvm7Dda/DPe1nOJPM92sHfL8gr60CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:53:41.170437Z"},"content_sha256":"bb17179397057661273a68ef9217666d91ebd6adaad948991061720419bca26c","schema_version":"1.0","event_id":"sha256:bb17179397057661273a68ef9217666d91ebd6adaad948991061720419bca26c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RYDPIK2TJJXFQTBSWW2STCK5HD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Models are less Over-Confident","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Janis Keuper, Julia Grabinski, Margret Keuper, Paul Gavrikov","submitted_at":"2022-10-12T06:14:55Z","abstract_excerpt":"Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack of robustness, unveiled by the striking effectiveness of adversarial attacks. Current attack methods are able to manipulate the network's prediction by adding specific but small amounts of noise to the input. In turn, adversarial training (AT) aims to achieve robustness against such attacks and ideally a better model generalization ability by including advers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05938","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.05938/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:22:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WhFGhvGBysKU1UU+6zKRfT9mgnNkVq7BCVhQtTnXdLmG9Esi3aWPOMpLFEbkWekgHdyk17i3LvPPvqAS60aRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:53:41.170942Z"},"content_sha256":"ae6ad4d55ed44393b7d626963e8d635191d32926c7faf9dae854285077305880","schema_version":"1.0","event_id":"sha256:ae6ad4d55ed44393b7d626963e8d635191d32926c7faf9dae854285077305880"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RYDPIK2TJJXFQTBSWW2STCK5HD/bundle.json","state_url":"https://pith.science/pith/RYDPIK2TJJXFQTBSWW2STCK5HD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RYDPIK2TJJXFQTBSWW2STCK5HD/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":"2026-08-05T04:53:41Z","links":{"resolver":"https://pith.science/pith/RYDPIK2TJJXFQTBSWW2STCK5HD","bundle":"https://pith.science/pith/RYDPIK2TJJXFQTBSWW2STCK5HD/bundle.json","state":"https://pith.science/pith/RYDPIK2TJJXFQTBSWW2STCK5HD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RYDPIK2TJJXFQTBSWW2STCK5HD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RYDPIK2TJJXFQTBSWW2STCK5HD","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":"c159eca4e53f849f147d982881fb7484e679348761265515db09bdb6a1617b5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T06:14:55Z","title_canon_sha256":"dd646ae48a33e14bbeb27da966eb00c59d9dec93a0f2fa0bd925864b78d54dfb"},"schema_version":"1.0","source":{"id":"2210.05938","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05938","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05938v2","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05938","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"RYDPIK2TJJXF","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"RYDPIK2TJJXFQTBS","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"RYDPIK2T","created_at":"2026-07-05T05:22:30Z"}],"graph_snapshots":[{"event_id":"sha256:ae6ad4d55ed44393b7d626963e8d635191d32926c7faf9dae854285077305880","target":"graph","created_at":"2026-07-05T05:22:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.05938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack of robustness, unveiled by the striking effectiveness of adversarial attacks. Current attack methods are able to manipulate the network's prediction by adding specific but small amounts of noise to the input. In turn, adversarial training (AT) aims to achieve robustness against such attacks and ideally a better model generalization ability by including advers","authors_text":"Janis Keuper, Julia Grabinski, Margret Keuper, Paul Gavrikov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T06:14:55Z","title":"Robust Models are less Over-Confident"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05938","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:bb17179397057661273a68ef9217666d91ebd6adaad948991061720419bca26c","target":"record","created_at":"2026-07-05T05:22:30Z","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":"c159eca4e53f849f147d982881fb7484e679348761265515db09bdb6a1617b5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T06:14:55Z","title_canon_sha256":"dd646ae48a33e14bbeb27da966eb00c59d9dec93a0f2fa0bd925864b78d54dfb"},"schema_version":"1.0","source":{"id":"2210.05938","kind":"arxiv","version":2}},"canonical_sha256":"8e06f42b534a6e584c32b5b529895d38f2edd78ea7549e0f2a715b525ed46535","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e06f42b534a6e584c32b5b529895d38f2edd78ea7549e0f2a715b525ed46535","first_computed_at":"2026-07-05T05:22:30.679157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:30.679157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5ksIBy4J30ykRurTV6XZ1p9WxVP+uUi7aLsEKYM9UFNtCGXTw3eQ4LBo7swz8BXtx1LWrwTG8MKCYaspeaGEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:30.679610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05938","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb17179397057661273a68ef9217666d91ebd6adaad948991061720419bca26c","sha256:ae6ad4d55ed44393b7d626963e8d635191d32926c7faf9dae854285077305880"],"state_sha256":"b1557cac11425a53300838e4099e51939f284abe2afb22f9770ea6cad1796927"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AogXj52dYGnMITovYMZyEw8QE28oCf9Wr+G/cQhY2uM/i2nlIEFYccRui8fKqC+Yjv/P65e+Qinei3INaORDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:53:41.176011Z","bundle_sha256":"d14fbb59ce3db373af6875a3a524c599f1209a205e331e763c0407985b58006a"}}