{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:63FL7ZO2RB5GFTLXY4SJXUERYC","short_pith_number":"pith:63FL7ZO2","schema_version":"1.0","canonical_sha256":"f6cabfe5da887a62cd77c7249bd091c0a82dc6e481b621a3db80bfac8b3a350b","source":{"kind":"arxiv","id":"2606.02134","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Evaluation Paradigms in IBP-based Certified Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hadar Shavit, Holger H. Hoos, Konstantin Kaulen","submitted_at":"2026-06-01T12:00:15Z","abstract_excerpt":"Deep neural networks achieve strong performance on many supervised learning tasks but remain vulnerable to adversarial perturbations. Neural network verification provides mathematically rigorous robustness guarantees, yet at substantial computational cost. To mitigate this, certified training techniques optimise for verifiable robustness during training, typically inducing a trade-off between natural and certified accuracy controlled by method-specific hyperparameters. Because these metrics are inherently conflicting, the common practice of reporting a single configuration is problematic: it c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T12:00:15Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2fb3cfe4a5f7948b4aef700f4d0466f056ab4e6486aa34a095af5a185968d192","abstract_canon_sha256":"759dfd69920de39d310f68b237d51cda308651f60636050f6cca69450d0f6a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:07.418049Z","signature_b64":"p7GfqgSlyJ1cn3shJkFQpZEEdl0mTau+kGQQsEua7nEbimasjZifT6JEYViHb5U4cNzal8EmtFyu/TkoVIZMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6cabfe5da887a62cd77c7249bd091c0a82dc6e481b621a3db80bfac8b3a350b","last_reissued_at":"2026-06-02T02:05:07.417630Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:07.417630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Evaluation Paradigms in IBP-based Certified Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hadar Shavit, Holger H. Hoos, Konstantin Kaulen","submitted_at":"2026-06-01T12:00:15Z","abstract_excerpt":"Deep neural networks achieve strong performance on many supervised learning tasks but remain vulnerable to adversarial perturbations. Neural network verification provides mathematically rigorous robustness guarantees, yet at substantial computational cost. To mitigate this, certified training techniques optimise for verifiable robustness during training, typically inducing a trade-off between natural and certified accuracy controlled by method-specific hyperparameters. Because these metrics are inherently conflicting, the common practice of reporting a single configuration is problematic: it c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02134","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.02134/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02134","created_at":"2026-06-02T02:05:07.417696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02134v1","created_at":"2026-06-02T02:05:07.417696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02134","created_at":"2026-06-02T02:05:07.417696+00:00"},{"alias_kind":"pith_short_12","alias_value":"63FL7ZO2RB5G","created_at":"2026-06-02T02:05:07.417696+00:00"},{"alias_kind":"pith_short_16","alias_value":"63FL7ZO2RB5GFTLX","created_at":"2026-06-02T02:05:07.417696+00:00"},{"alias_kind":"pith_short_8","alias_value":"63FL7ZO2","created_at":"2026-06-02T02:05:07.417696+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC","json":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC.json","graph_json":"https://pith.science/api/pith-number/63FL7ZO2RB5GFTLXY4SJXUERYC/graph.json","events_json":"https://pith.science/api/pith-number/63FL7ZO2RB5GFTLXY4SJXUERYC/events.json","paper":"https://pith.science/paper/63FL7ZO2"},"agent_actions":{"view_html":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC","download_json":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC.json","view_paper":"https://pith.science/paper/63FL7ZO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02134&json=true","fetch_graph":"https://pith.science/api/pith-number/63FL7ZO2RB5GFTLXY4SJXUERYC/graph.json","fetch_events":"https://pith.science/api/pith-number/63FL7ZO2RB5GFTLXY4SJXUERYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC/action/storage_attestation","attest_author":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC/action/author_attestation","sign_citation":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC/action/citation_signature","submit_replication":"https://pith.science/pith/63FL7ZO2RB5GFTLXY4SJXUERYC/action/replication_record"}},"created_at":"2026-06-02T02:05:07.417696+00:00","updated_at":"2026-06-02T02:05:07.417696+00:00"}