{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HDGPBU6XMJARSFC5ITIPQ2IJH2","short_pith_number":"pith:HDGPBU6X","canonical_record":{"source":{"id":"2507.06092","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:34:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"39921027df68bd47e5d7a6f20a1cf0f4508d17d58c5affa734efc2ee7ddc112c","abstract_canon_sha256":"93e870e31c2d54aadab132d6e3e3980cd3b17f17787be6cd6455f8067decd510"},"schema_version":"1.0"},"canonical_sha256":"38ccf0d3d7624119145d44d0f869093e9111029c4460a122e3518f0b8acceb56","source":{"kind":"arxiv","id":"2507.06092","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06092","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06092v4","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06092","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"HDGPBU6XMJAR","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"HDGPBU6XMJARSFC5","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"HDGPBU6X","created_at":"2026-05-29T02:05:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HDGPBU6XMJARSFC5ITIPQ2IJH2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06092","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:34:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"39921027df68bd47e5d7a6f20a1cf0f4508d17d58c5affa734efc2ee7ddc112c","abstract_canon_sha256":"93e870e31c2d54aadab132d6e3e3980cd3b17f17787be6cd6455f8067decd510"},"schema_version":"1.0"},"canonical_sha256":"38ccf0d3d7624119145d44d0f869093e9111029c4460a122e3518f0b8acceb56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:35.499449Z","signature_b64":"/HxyCt9I6+bYCX3FGzHYrbq5Ak7PRQI4jroRXzlCF1E439Pj6RtNH+ixRthEne+aPiHik1YF3v1cNyasFYU4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ccf0d3d7624119145d44d0f869093e9111029c4460a122e3518f0b8acceb56","last_reissued_at":"2026-05-29T02:05:35.498914Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:35.498914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06092","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wGKDQkliRdqPTLeOrVXRbIGSqKRnccPq1RbCa94Ey3vPAVErSqREpIcCTWTYxNDbBvJiv+EImM1J1QYKNetVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:47:38.803377Z"},"content_sha256":"a6baf71f4d40a2f6b55586d91d1824df9a8f9340c0179ed59118de484fa6dcc8","schema_version":"1.0","event_id":"sha256:a6baf71f4d40a2f6b55586d91d1824df9a8f9340c0179ed59118de484fa6dcc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HDGPBU6XMJARSFC5ITIPQ2IJH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taming Data Challenges in ML-based Security Tasks Using Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Aravind Cheruvu, Atul Prakash, Bimal Viswanath, Neal Mangaokar, Shirin Nilizadeh, Shravya Kanchi, Sifat Muhammad Abdullah","submitted_at":"2025-07-08T15:34:45Z","abstract_excerpt":"Machine learning-based supervised classifiers are widely used for security tasks, and their improvement has been largely focused on algorithmic advancements. We argue that data challenges that negatively impact the performance of these classifiers have received limited attention. We address the following research question: Can developments in Generative AI (GenAI) address these data challenges and improve classifier performance? We propose augmenting training datasets with synthetic data generated using GenAI techniques to improve classifier generalization. We evaluate this approach across 7 d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06092","kind":"arxiv","version":4},"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/2507.06092/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":"2026-05-29T02:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3gdmoxWNDpAarxh3ZogVngevBHYes3Mh8GsrI/io0fmtcbt9Pc4kZS8/5MMbU7tuTN89nCgG4lxxtxJWrYObAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:47:38.803801Z"},"content_sha256":"b4660482309519c2f96ecae51c9e843a434bcbf84b46afc1daadb997d9ad7223","schema_version":"1.0","event_id":"sha256:b4660482309519c2f96ecae51c9e843a434bcbf84b46afc1daadb997d9ad7223"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2/bundle.json","state_url":"https://pith.science/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2/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":"2026-05-31T01:47:38Z","links":{"resolver":"https://pith.science/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2","bundle":"https://pith.science/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2/bundle.json","state":"https://pith.science/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HDGPBU6XMJARSFC5ITIPQ2IJH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HDGPBU6XMJARSFC5ITIPQ2IJH2","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":"93e870e31c2d54aadab132d6e3e3980cd3b17f17787be6cd6455f8067decd510","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:34:45Z","title_canon_sha256":"39921027df68bd47e5d7a6f20a1cf0f4508d17d58c5affa734efc2ee7ddc112c"},"schema_version":"1.0","source":{"id":"2507.06092","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06092","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06092v4","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06092","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"HDGPBU6XMJAR","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"HDGPBU6XMJARSFC5","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"HDGPBU6X","created_at":"2026-05-29T02:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:b4660482309519c2f96ecae51c9e843a434bcbf84b46afc1daadb997d9ad7223","target":"graph","created_at":"2026-05-29T02:05:35Z","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/2507.06092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning-based supervised classifiers are widely used for security tasks, and their improvement has been largely focused on algorithmic advancements. We argue that data challenges that negatively impact the performance of these classifiers have received limited attention. We address the following research question: Can developments in Generative AI (GenAI) address these data challenges and improve classifier performance? We propose augmenting training datasets with synthetic data generated using GenAI techniques to improve classifier generalization. We evaluate this approach across 7 d","authors_text":"Aravind Cheruvu, Atul Prakash, Bimal Viswanath, Neal Mangaokar, Shirin Nilizadeh, Shravya Kanchi, Sifat Muhammad Abdullah","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:34:45Z","title":"Taming Data Challenges in ML-based Security Tasks Using Generative AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06092","kind":"arxiv","version":4},"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:a6baf71f4d40a2f6b55586d91d1824df9a8f9340c0179ed59118de484fa6dcc8","target":"record","created_at":"2026-05-29T02:05:35Z","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":"93e870e31c2d54aadab132d6e3e3980cd3b17f17787be6cd6455f8067decd510","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:34:45Z","title_canon_sha256":"39921027df68bd47e5d7a6f20a1cf0f4508d17d58c5affa734efc2ee7ddc112c"},"schema_version":"1.0","source":{"id":"2507.06092","kind":"arxiv","version":4}},"canonical_sha256":"38ccf0d3d7624119145d44d0f869093e9111029c4460a122e3518f0b8acceb56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38ccf0d3d7624119145d44d0f869093e9111029c4460a122e3518f0b8acceb56","first_computed_at":"2026-05-29T02:05:35.498914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:35.498914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HxyCt9I6+bYCX3FGzHYrbq5Ak7PRQI4jroRXzlCF1E439Pj6RtNH+ixRthEne+aPiHik1YF3v1cNyasFYU4Ag==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:35.499449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06092","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6baf71f4d40a2f6b55586d91d1824df9a8f9340c0179ed59118de484fa6dcc8","sha256:b4660482309519c2f96ecae51c9e843a434bcbf84b46afc1daadb997d9ad7223"],"state_sha256":"a730741da2595cb8ef3edd780fe5203f819e387f6b1bfc752e10db10a0273f14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RzbiyObrwOPE2XCYAyAmDuR6495vqYudVH3ppLa4PbNGRJH5pirM8rqyIoMd0Gq34gNzopQXyd0AfNjx2fzXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:47:38.806853Z","bundle_sha256":"8efe17bd9c63a9fde7f5c896255b64bca49333e29d6494acca5e4444cef14533"}}