{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TCSTBGEATDEO5KDFAUENOEMX7P","short_pith_number":"pith:TCSTBGEA","canonical_record":{"source":{"id":"2408.10204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:58:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"25414fd22289307ca795d95da3cf63bbd15aaa4d714bd36a2920876a04efeadf","abstract_canon_sha256":"7f35ed35be967bd13fede7ccc8d0bf8ead79ee7f0898d5ff1664494c5919aac1"},"schema_version":"1.0"},"canonical_sha256":"98a530988098c8eea8650508d71197fbeacd9a35b84bead4f14c37901d151ecb","source":{"kind":"arxiv","id":"2408.10204","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10204","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10204v3","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10204","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"TCSTBGEATDEO","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"TCSTBGEATDEO5KDF","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"TCSTBGEA","created_at":"2026-07-05T09:53:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TCSTBGEATDEO5KDFAUENOEMX7P","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:58:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"25414fd22289307ca795d95da3cf63bbd15aaa4d714bd36a2920876a04efeadf","abstract_canon_sha256":"7f35ed35be967bd13fede7ccc8d0bf8ead79ee7f0898d5ff1664494c5919aac1"},"schema_version":"1.0"},"canonical_sha256":"98a530988098c8eea8650508d71197fbeacd9a35b84bead4f14c37901d151ecb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:28.556952Z","signature_b64":"RXs2Zebt1ahxKMouU4dZYtsE9N60Xgu2LlxlRqEieUdjwdtZbqfuAUg8cOMF6y91uZgJnPVupjbhhxfU0gVrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98a530988098c8eea8650508d71197fbeacd9a35b84bead4f14c37901d151ecb","last_reissued_at":"2026-07-05T09:53:28.556489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:28.556489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10204","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UKDIpxhaATOq2sf8vKRF4eH6EU+DCa/ueoxnwvbmgtAJwosTarQbUQOxQecuNy2mo1lfik6lUEjW9J0CojX5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:31.930350Z"},"content_sha256":"98ad5455313c9e3d054269a41bab683789d447d756611d619f6cc259a9b1d963","schema_version":"1.0","event_id":"sha256:98ad5455313c9e3d054269a41bab683789d447d756611d619f6cc259a9b1d963"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TCSTBGEATDEO5KDFAUENOEMX7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bhavna Gopal, Huanrui Yang, Jingyang Zhang, Mark Horton, Yiran Chen","submitted_at":"2024-08-19T17:58:03Z","abstract_excerpt":"Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by introducing parameter efficiency into the adversarial training process, improving both clean accuracy and adversarial robustness. Instead of tuning the entire model, CLAT identifies and fine-tunes robustness-critical layers - those predominantly learning non-robust features - while freezing the remaining model to enhance robustness. It employs dynamic critical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10204","kind":"arxiv","version":3},"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/2408.10204/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":"2026-07-05T09:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3nazg30XlE5tpGrzqmZUfb1rrwaCg1HyII/YSlEBb8n1GaiyyauL8PZ93DTkjy69NLPdOIiIojYtw9kJSSaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:31.930726Z"},"content_sha256":"68d38b87f65d53ad97be0b214e13c59392fd766189dd1c6550d63cf7d56d753d","schema_version":"1.0","event_id":"sha256:68d38b87f65d53ad97be0b214e13c59392fd766189dd1c6550d63cf7d56d753d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCSTBGEATDEO5KDFAUENOEMX7P/bundle.json","state_url":"https://pith.science/pith/TCSTBGEATDEO5KDFAUENOEMX7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCSTBGEATDEO5KDFAUENOEMX7P/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":"2026-07-09T05:01:31Z","links":{"resolver":"https://pith.science/pith/TCSTBGEATDEO5KDFAUENOEMX7P","bundle":"https://pith.science/pith/TCSTBGEATDEO5KDFAUENOEMX7P/bundle.json","state":"https://pith.science/pith/TCSTBGEATDEO5KDFAUENOEMX7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCSTBGEATDEO5KDFAUENOEMX7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TCSTBGEATDEO5KDFAUENOEMX7P","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":"7f35ed35be967bd13fede7ccc8d0bf8ead79ee7f0898d5ff1664494c5919aac1","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:58:03Z","title_canon_sha256":"25414fd22289307ca795d95da3cf63bbd15aaa4d714bd36a2920876a04efeadf"},"schema_version":"1.0","source":{"id":"2408.10204","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10204","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10204v3","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10204","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"TCSTBGEATDEO","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"TCSTBGEATDEO5KDF","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"TCSTBGEA","created_at":"2026-07-05T09:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:68d38b87f65d53ad97be0b214e13c59392fd766189dd1c6550d63cf7d56d753d","target":"graph","created_at":"2026-07-05T09:53:28Z","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/2408.10204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by introducing parameter efficiency into the adversarial training process, improving both clean accuracy and adversarial robustness. Instead of tuning the entire model, CLAT identifies and fine-tunes robustness-critical layers - those predominantly learning non-robust features - while freezing the remaining model to enhance robustness. It employs dynamic critical","authors_text":"Bhavna Gopal, Huanrui Yang, Jingyang Zhang, Mark Horton, Yiran Chen","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:58:03Z","title":"Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10204","kind":"arxiv","version":3},"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":"sha256:98ad5455313c9e3d054269a41bab683789d447d756611d619f6cc259a9b1d963","target":"record","created_at":"2026-07-05T09:53:28Z","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":"7f35ed35be967bd13fede7ccc8d0bf8ead79ee7f0898d5ff1664494c5919aac1","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:58:03Z","title_canon_sha256":"25414fd22289307ca795d95da3cf63bbd15aaa4d714bd36a2920876a04efeadf"},"schema_version":"1.0","source":{"id":"2408.10204","kind":"arxiv","version":3}},"canonical_sha256":"98a530988098c8eea8650508d71197fbeacd9a35b84bead4f14c37901d151ecb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98a530988098c8eea8650508d71197fbeacd9a35b84bead4f14c37901d151ecb","first_computed_at":"2026-07-05T09:53:28.556489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:28.556489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXs2Zebt1ahxKMouU4dZYtsE9N60Xgu2LlxlRqEieUdjwdtZbqfuAUg8cOMF6y91uZgJnPVupjbhhxfU0gVrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:28.556952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10204","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98ad5455313c9e3d054269a41bab683789d447d756611d619f6cc259a9b1d963","sha256:68d38b87f65d53ad97be0b214e13c59392fd766189dd1c6550d63cf7d56d753d"],"state_sha256":"a5ea69b0c7d1cdae77f191b6783efa123485a4c09b0cafb9cf19ea08c2404cd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZBubBHCw4etmqYm4BGtKap+3NCaDdF0LNMeZdHbXAkqLvA91hi8Ql7Vt8ojve7uNCzz8Vp7cz4XKcs+PlK6CBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:01:31.932747Z","bundle_sha256":"f2100a806363f85989fe549bb37e6fedba193e5b489734f8255baf6dca9afbde"}}