{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LZPJNWLVL7KOUCTGTBB74KXLJA","short_pith_number":"pith:LZPJNWLV","canonical_record":{"source":{"id":"2404.10588","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T14:13:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"45dfe82b30a3524649fde17fc948c9602269231a75f2bb3041ca48d8919d76e2","abstract_canon_sha256":"3eecd68c3a9fb4e9ab0401ed20e0d9ad140cd57080507859ced4f54ac5cd2916"},"schema_version":"1.0"},"canonical_sha256":"5e5e96d9755fd4ea0a669843fe2aeb48287526a30c6fd045138aed0797707f37","source":{"kind":"arxiv","id":"2404.10588","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10588","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10588v2","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10588","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"LZPJNWLVL7KO","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"LZPJNWLVL7KOUCTG","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"LZPJNWLV","created_at":"2026-07-05T08:08:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LZPJNWLVL7KOUCTGTBB74KXLJA","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10588","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T14:13:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"45dfe82b30a3524649fde17fc948c9602269231a75f2bb3041ca48d8919d76e2","abstract_canon_sha256":"3eecd68c3a9fb4e9ab0401ed20e0d9ad140cd57080507859ced4f54ac5cd2916"},"schema_version":"1.0"},"canonical_sha256":"5e5e96d9755fd4ea0a669843fe2aeb48287526a30c6fd045138aed0797707f37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:58.410109Z","signature_b64":"Li8jjcc7X6xpTvdc69v+ikoebVH1mXIrUCGV3TVUsGo4w9GN6QU4/lOmRL679Z9Ms7y8oKvwy8+teQKOOMvmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e5e96d9755fd4ea0a669843fe2aeb48287526a30c6fd045138aed0797707f37","last_reissued_at":"2026-07-05T08:08:58.409634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:58.409634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10588","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":"2026-07-05T08:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jnjTve85oljd0Bq4Q11CuoDX8AHy/P6K3XJIVODd5Wz30pUand7Bi2AvLS5L3aacctubqkg8Kqg4KDSwkkT4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-29T10:13:12.926857Z"},"content_sha256":"1519e7f948af1c9748a86d1adb8912cbdd11199c90b72810a9daea0283739828","schema_version":"1.0","event_id":"sha256:1519e7f948af1c9748a86d1adb8912cbdd11199c90b72810a9daea0283739828"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LZPJNWLVL7KOUCTGTBB74KXLJA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Counterfactual Examples Complicate Adversarial Training?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cameron Darwin, Eduardo Ortega, Eric Yeats, Frank Liu, Hai Li","submitted_at":"2024-04-16T14:13:44Z","abstract_excerpt":"We leverage diffusion models to study the robustness-performance tradeoff of robust classifiers. Our approach introduces a simple, pretrained diffusion method to generate low-norm counterfactual examples (CEs): semantically altered data which results in different true class membership. We report that the confidence and accuracy of robust models on their clean training data are associated with the proximity of the data to their CEs. Moreover, robust models perform very poorly when evaluated on the CEs directly, as they become increasingly invariant to the low-norm, semantic changes brought by C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10588","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/2404.10588/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":"2026-07-05T08:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DkEiVjny/+i/gH2EHg+pefFHTV05qQmEEIm23P1jJKVjzdLVJF/A6rSiiVf2P0e6RhgX7ETwOt/qj6suwPf1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-29T10:13:12.927240Z"},"content_sha256":"e9995b5f69c469046cb61480a3b1910d5a8d7f531c22b7f501ce26ab50aba6c8","schema_version":"1.0","event_id":"sha256:e9995b5f69c469046cb61480a3b1910d5a8d7f531c22b7f501ce26ab50aba6c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZPJNWLVL7KOUCTGTBB74KXLJA/bundle.json","state_url":"https://pith.science/pith/LZPJNWLVL7KOUCTGTBB74KXLJA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZPJNWLVL7KOUCTGTBB74KXLJA/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":"2026-07-29T10:13:12Z","links":{"resolver":"https://pith.science/pith/LZPJNWLVL7KOUCTGTBB74KXLJA","bundle":"https://pith.science/pith/LZPJNWLVL7KOUCTGTBB74KXLJA/bundle.json","state":"https://pith.science/pith/LZPJNWLVL7KOUCTGTBB74KXLJA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZPJNWLVL7KOUCTGTBB74KXLJA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZPJNWLVL7KOUCTGTBB74KXLJA","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":"3eecd68c3a9fb4e9ab0401ed20e0d9ad140cd57080507859ced4f54ac5cd2916","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T14:13:44Z","title_canon_sha256":"45dfe82b30a3524649fde17fc948c9602269231a75f2bb3041ca48d8919d76e2"},"schema_version":"1.0","source":{"id":"2404.10588","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10588","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10588v2","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10588","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"LZPJNWLVL7KO","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"LZPJNWLVL7KOUCTG","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"LZPJNWLV","created_at":"2026-07-05T08:08:58Z"}],"graph_snapshots":[{"event_id":"sha256:e9995b5f69c469046cb61480a3b1910d5a8d7f531c22b7f501ce26ab50aba6c8","target":"graph","created_at":"2026-07-05T08:08:58Z","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/2404.10588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We leverage diffusion models to study the robustness-performance tradeoff of robust classifiers. Our approach introduces a simple, pretrained diffusion method to generate low-norm counterfactual examples (CEs): semantically altered data which results in different true class membership. We report that the confidence and accuracy of robust models on their clean training data are associated with the proximity of the data to their CEs. Moreover, robust models perform very poorly when evaluated on the CEs directly, as they become increasingly invariant to the low-norm, semantic changes brought by C","authors_text":"Cameron Darwin, Eduardo Ortega, Eric Yeats, Frank Liu, Hai Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T14:13:44Z","title":"Do Counterfactual Examples Complicate Adversarial Training?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10588","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":"sha256:1519e7f948af1c9748a86d1adb8912cbdd11199c90b72810a9daea0283739828","target":"record","created_at":"2026-07-05T08:08:58Z","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":"3eecd68c3a9fb4e9ab0401ed20e0d9ad140cd57080507859ced4f54ac5cd2916","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T14:13:44Z","title_canon_sha256":"45dfe82b30a3524649fde17fc948c9602269231a75f2bb3041ca48d8919d76e2"},"schema_version":"1.0","source":{"id":"2404.10588","kind":"arxiv","version":2}},"canonical_sha256":"5e5e96d9755fd4ea0a669843fe2aeb48287526a30c6fd045138aed0797707f37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e5e96d9755fd4ea0a669843fe2aeb48287526a30c6fd045138aed0797707f37","first_computed_at":"2026-07-05T08:08:58.409634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:58.409634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Li8jjcc7X6xpTvdc69v+ikoebVH1mXIrUCGV3TVUsGo4w9GN6QU4/lOmRL679Z9Ms7y8oKvwy8+teQKOOMvmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:58.410109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10588","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1519e7f948af1c9748a86d1adb8912cbdd11199c90b72810a9daea0283739828","sha256:e9995b5f69c469046cb61480a3b1910d5a8d7f531c22b7f501ce26ab50aba6c8"],"state_sha256":"9a907cf194a866f7267485ef4bdf286a271ecc1c7d4ae0a9db27f966dec4ba8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"26b51PGIPvs4Jiw192+4tUpctP0KGqCphDcB4GTAYG/lIRtn85Nlb6aETJKw6W05K1oqyzLW4lCy2hV/tjyeAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-29T10:13:12.929927Z","bundle_sha256":"59d53862a8e5706b1fe49bf1c52e8e5e387795fe7549cb8bd900ce5a9b37984b"}}