{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:426XSYPVCRBQUL6HTLG5IP5XPI","short_pith_number":"pith:426XSYPV","canonical_record":{"source":{"id":"2412.03539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T18:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3522e011b807325e89ea8afeda4b4258758ceb78f5153ec510a49f57f70abd95","abstract_canon_sha256":"c71cfb295787b1090ca51357a76015088e05baa8e649d695d583b10ad6992764"},"schema_version":"1.0"},"canonical_sha256":"e6bd7961f514430a2fc79acdd43fb77a00dc53485bd13ebc8f33216f3c0d3d98","source":{"kind":"arxiv","id":"2412.03539","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03539","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03539v2","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03539","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"426XSYPVCRBQ","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"426XSYPVCRBQUL6H","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"426XSYPV","created_at":"2026-07-05T10:48:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:426XSYPVCRBQUL6HTLG5IP5XPI","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T18:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3522e011b807325e89ea8afeda4b4258758ceb78f5153ec510a49f57f70abd95","abstract_canon_sha256":"c71cfb295787b1090ca51357a76015088e05baa8e649d695d583b10ad6992764"},"schema_version":"1.0"},"canonical_sha256":"e6bd7961f514430a2fc79acdd43fb77a00dc53485bd13ebc8f33216f3c0d3d98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:22.225580Z","signature_b64":"SMbW9TK32T6TdiyiN+4+FA+t7RQdMZWuqXvABhPRVMXtrFJfBH3gWyOYXeiOvSbCbWVMNUSLcMqKLzbAwnvNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6bd7961f514430a2fc79acdd43fb77a00dc53485bd13ebc8f33216f3c0d3d98","last_reissued_at":"2026-07-05T10:48:22.225113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:22.225113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03539","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":"2026-07-05T10:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgYoCH5h0Do5eDlY6KJSGT/u2BGtlfKW6VEJmZahr5RhKya04vcjCdgxsdrSRSGPQTR8gJEvoVXMIRaSQdM8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:26:28.026272Z"},"content_sha256":"d71b0f44ab61128f1d7ae5d7d707a4ec6748e0edb94f091e0ec127e0723a104b","schema_version":"1.0","event_id":"sha256:d71b0f44ab61128f1d7ae5d7d707a4ec6748e0edb94f091e0ec127e0723a104b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:426XSYPVCRBQUL6HTLG5IP5XPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cuiyu He, Xinheng Xie, Yue Wu","submitted_at":"2024-12-04T18:36:09Z","abstract_excerpt":"Understanding adversarial examples is crucial for improving model robustness, as they introduce imperceptible perturbations to deceive models. Effective adversarial examples, therefore, offer the potential to train more robust models by eliminating model singularities. We propose NODE-AdvGAN, a novel approach that treats adversarial generation as a continuous process and employs a Neural Ordinary Differential Equation (NODE) to simulate generator dynamics. By mimicking the iterative nature of traditional gradient-based methods, NODE-AdvGAN generates smoother and more precise perturbations that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03539","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/2412.03539/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":"2026-07-05T10:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+uRURwc/o/LbvtKT+BOlSpkivvi/WY5L2yCJhinN9kSvR1lhCVwq+8mn5Etg9aiqFuZ+eqV7IcYTWCxlj4Z5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:26:28.026816Z"},"content_sha256":"d5a86c82d1bbf59e9642212da8de4b01b0627e465eb31276265c2628b46ed34f","schema_version":"1.0","event_id":"sha256:d5a86c82d1bbf59e9642212da8de4b01b0627e465eb31276265c2628b46ed34f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/426XSYPVCRBQUL6HTLG5IP5XPI/bundle.json","state_url":"https://pith.science/pith/426XSYPVCRBQUL6HTLG5IP5XPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/426XSYPVCRBQUL6HTLG5IP5XPI/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":"2026-08-22T09:26:28Z","links":{"resolver":"https://pith.science/pith/426XSYPVCRBQUL6HTLG5IP5XPI","bundle":"https://pith.science/pith/426XSYPVCRBQUL6HTLG5IP5XPI/bundle.json","state":"https://pith.science/pith/426XSYPVCRBQUL6HTLG5IP5XPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/426XSYPVCRBQUL6HTLG5IP5XPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:426XSYPVCRBQUL6HTLG5IP5XPI","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":"c71cfb295787b1090ca51357a76015088e05baa8e649d695d583b10ad6992764","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T18:36:09Z","title_canon_sha256":"3522e011b807325e89ea8afeda4b4258758ceb78f5153ec510a49f57f70abd95"},"schema_version":"1.0","source":{"id":"2412.03539","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03539","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03539v2","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03539","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"426XSYPVCRBQ","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"426XSYPVCRBQUL6H","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"426XSYPV","created_at":"2026-07-05T10:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:d5a86c82d1bbf59e9642212da8de4b01b0627e465eb31276265c2628b46ed34f","target":"graph","created_at":"2026-07-05T10:48:22Z","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/2412.03539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding adversarial examples is crucial for improving model robustness, as they introduce imperceptible perturbations to deceive models. Effective adversarial examples, therefore, offer the potential to train more robust models by eliminating model singularities. We propose NODE-AdvGAN, a novel approach that treats adversarial generation as a continuous process and employs a Neural Ordinary Differential Equation (NODE) to simulate generator dynamics. By mimicking the iterative nature of traditional gradient-based methods, NODE-AdvGAN generates smoother and more precise perturbations that","authors_text":"Cuiyu He, Xinheng Xie, Yue Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T18:36:09Z","title":"NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03539","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:d71b0f44ab61128f1d7ae5d7d707a4ec6748e0edb94f091e0ec127e0723a104b","target":"record","created_at":"2026-07-05T10:48:22Z","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":"c71cfb295787b1090ca51357a76015088e05baa8e649d695d583b10ad6992764","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T18:36:09Z","title_canon_sha256":"3522e011b807325e89ea8afeda4b4258758ceb78f5153ec510a49f57f70abd95"},"schema_version":"1.0","source":{"id":"2412.03539","kind":"arxiv","version":2}},"canonical_sha256":"e6bd7961f514430a2fc79acdd43fb77a00dc53485bd13ebc8f33216f3c0d3d98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6bd7961f514430a2fc79acdd43fb77a00dc53485bd13ebc8f33216f3c0d3d98","first_computed_at":"2026-07-05T10:48:22.225113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:22.225113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SMbW9TK32T6TdiyiN+4+FA+t7RQdMZWuqXvABhPRVMXtrFJfBH3gWyOYXeiOvSbCbWVMNUSLcMqKLzbAwnvNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:22.225580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03539","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d71b0f44ab61128f1d7ae5d7d707a4ec6748e0edb94f091e0ec127e0723a104b","sha256:d5a86c82d1bbf59e9642212da8de4b01b0627e465eb31276265c2628b46ed34f"],"state_sha256":"ead910945381b4483efd92e13e568e38db9c96dcc02d099615783bf26844fccc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvtcdCVtdjsIJ/AL8YtW4xxglJif3OndUicjQyxU8NzK5X0A1VslczFcVIFraomm+PgSLi8qBtJjMufPUAM9Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:26:28.031443Z","bundle_sha256":"8fa377ee9e7370143c0c1bc1a764a41cd600e29cb34e9e35554f254001001c3b"}}