{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P5THW6JFJAZYP6BX66R32S4XRC","short_pith_number":"pith:P5THW6JF","canonical_record":{"source":{"id":"2605.10240","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T09:14:51Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"634d16ccaf7ceb876b5d3a7a303c140f7e11f5ca96d5872315f25f97be100aad","abstract_canon_sha256":"5b6e6eba03ae07efca9aff9b82b453503465d7ab4cbfa0ad33418f6ea293d601"},"schema_version":"1.0"},"canonical_sha256":"7f667b7925483387f837f7a3bd4b97889c15704f2e3c11cfc565430740241090","source":{"kind":"arxiv","id":"2605.10240","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10240","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10240v2","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10240","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"P5THW6JFJAZY","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"P5THW6JFJAZYP6BX","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"P5THW6JF","created_at":"2026-06-23T03:13:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P5THW6JFJAZYP6BX66R32S4XRC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10240","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T09:14:51Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"634d16ccaf7ceb876b5d3a7a303c140f7e11f5ca96d5872315f25f97be100aad","abstract_canon_sha256":"5b6e6eba03ae07efca9aff9b82b453503465d7ab4cbfa0ad33418f6ea293d601"},"schema_version":"1.0"},"canonical_sha256":"7f667b7925483387f837f7a3bd4b97889c15704f2e3c11cfc565430740241090","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:57.898768Z","signature_b64":"88S1H0SV46S83QQ4XkbiMcAoNX68vo4gap9gTQouGByvu1ipPYmbrkpwZU/l0bC2SAHkxhkFnPezhIWUc4+pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f667b7925483387f837f7a3bd4b97889c15704f2e3c11cfc565430740241090","last_reissued_at":"2026-06-23T03:13:57.898350Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:57.898350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10240","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":"2026-06-23T03:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qxlt7nX5Rwdvdg2jtPQtx+l81SmQ2b69zo9WgqF8olMPjwN90kDHK5nmnnyT5E9UMoqDg1dtdTCxebwrF21MBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:31:26.227063Z"},"content_sha256":"a5d044be86706270eafdf96ff47c329df841e928d01e962958587fe53b5e6499","schema_version":"1.0","event_id":"sha256:a5d044be86706270eafdf96ff47c329df841e928d01e962958587fe53b5e6499"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P5THW6JFJAZYP6BX66R32S4XRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MARGIN corrects geometric distortions in hyperspherical embeddings to improve vulnerability detection on imbalanced datasets.","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SE","authors_text":"Huifang Ma, Jiahui Wei, Qingqing Li, Yafei Yang, Yuteng Zhang","submitted_at":"2026-05-11T09:14:51Z","abstract_excerpt":"Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulnerability datasets suffer from two severe challenges: frequency imbalance and difficulty imbalance. We reinterpret these challenges from an embedding geometry perspective, observing that such imbalances induce geometric distortions in hyperspherical representation space. To address this issue, we propose MARGIN, a metric-based framework that learns discriminative vulnerability representations through adaptive margin metric learning and hyperspher"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MARGIN consistently outperforms strong baselines, achieving notable improvements in classification and detection, especially on challenging, imbalanced datasets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed frequency and difficulty imbalances manifest primarily as geometric distortions in hyperspherical space and that aligning embedding distributions with Voronoi cells via von Mises-Fisher concentration will reliably improve downstream detection without introducing new failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MARGIN reduces geometric distortions in imbalanced vulnerability embeddings by dynamically regularizing margins with von Mises-Fisher concentration estimates and hyperspherical prototypes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MARGIN corrects geometric distortions in hyperspherical embeddings to improve vulnerability detection on imbalanced datasets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bce40fcb1d86eaa9c095c4ebd0b0e8f594a0aff94359584759974efe6c70ddb4"},"source":{"id":"2605.10240","kind":"arxiv","version":2},"verdict":{"id":"a561cc82-59d5-4b57-8b0b-63e8f77fbaa2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T05:22:44.897351Z","strongest_claim":"MARGIN consistently outperforms strong baselines, achieving notable improvements in classification and detection, especially on challenging, imbalanced datasets.","one_line_summary":"MARGIN reduces geometric distortions in imbalanced vulnerability embeddings by dynamically regularizing margins with von Mises-Fisher concentration estimates and hyperspherical prototypes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed frequency and difficulty imbalances manifest primarily as geometric distortions in hyperspherical space and that aligning embedding distributions with Voronoi cells via von Mises-Fisher concentration will reliably improve downstream detection without introducing new failure modes.","pith_extraction_headline":"MARGIN corrects geometric distortions in hyperspherical embeddings to improve vulnerability detection on imbalanced datasets."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10240/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.886947Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:38:03.600809Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.710470Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:33:05.502511Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"04894fcdb2d9ec2a61248ac21c53701828296fa7b13132227a9605082175420b"},"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":"a561cc82-59d5-4b57-8b0b-63e8f77fbaa2"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfDHnsJ9n33tnMZyQ9ed50c7tZ0HFGjz9hYr7+CDqwBpCf/YI8hY/vi/YLGBDtBe9bRf+jp7ZmTS8gYs8KbYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:31:26.227820Z"},"content_sha256":"9f720bbe99b304d9d8a47ef07204b1567bdceb9d0d323038e6918d3ed53d67c5","schema_version":"1.0","event_id":"sha256:9f720bbe99b304d9d8a47ef07204b1567bdceb9d0d323038e6918d3ed53d67c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5THW6JFJAZYP6BX66R32S4XRC/bundle.json","state_url":"https://pith.science/pith/P5THW6JFJAZYP6BX66R32S4XRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5THW6JFJAZYP6BX66R32S4XRC/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":"2026-08-04T03:31:26Z","links":{"resolver":"https://pith.science/pith/P5THW6JFJAZYP6BX66R32S4XRC","bundle":"https://pith.science/pith/P5THW6JFJAZYP6BX66R32S4XRC/bundle.json","state":"https://pith.science/pith/P5THW6JFJAZYP6BX66R32S4XRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5THW6JFJAZYP6BX66R32S4XRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P5THW6JFJAZYP6BX66R32S4XRC","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":"5b6e6eba03ae07efca9aff9b82b453503465d7ab4cbfa0ad33418f6ea293d601","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T09:14:51Z","title_canon_sha256":"634d16ccaf7ceb876b5d3a7a303c140f7e11f5ca96d5872315f25f97be100aad"},"schema_version":"1.0","source":{"id":"2605.10240","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10240","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10240v2","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10240","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"P5THW6JFJAZY","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"P5THW6JFJAZYP6BX","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"P5THW6JF","created_at":"2026-06-23T03:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:9f720bbe99b304d9d8a47ef07204b1567bdceb9d0d323038e6918d3ed53d67c5","target":"graph","created_at":"2026-06-23T03:13:57Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MARGIN consistently outperforms strong baselines, achieving notable improvements in classification and detection, especially on challenging, imbalanced datasets."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed frequency and difficulty imbalances manifest primarily as geometric distortions in hyperspherical space and that aligning embedding distributions with Voronoi cells via von Mises-Fisher concentration will reliably improve downstream detection without introducing new failure modes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MARGIN reduces geometric distortions in imbalanced vulnerability embeddings by dynamically regularizing margins with von Mises-Fisher concentration estimates and hyperspherical prototypes."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MARGIN corrects geometric distortions in hyperspherical embeddings to improve vulnerability detection on imbalanced datasets."}],"snapshot_sha256":"bce40fcb1d86eaa9c095c4ebd0b0e8f594a0aff94359584759974efe6c70ddb4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.886947Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:38:03.600809Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.710470Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:33:05.502511Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10240/integrity.json","findings":[],"snapshot_sha256":"04894fcdb2d9ec2a61248ac21c53701828296fa7b13132227a9605082175420b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulnerability datasets suffer from two severe challenges: frequency imbalance and difficulty imbalance. We reinterpret these challenges from an embedding geometry perspective, observing that such imbalances induce geometric distortions in hyperspherical representation space. To address this issue, we propose MARGIN, a metric-based framework that learns discriminative vulnerability representations through adaptive margin metric learning and hyperspher","authors_text":"Huifang Ma, Jiahui Wei, Qingqing Li, Yafei Yang, Yuteng Zhang","cross_cats":["cs.CR","cs.LG"],"headline":"MARGIN corrects geometric distortions in hyperspherical embeddings to improve vulnerability detection on imbalanced datasets.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T09:14:51Z","title":"MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10240","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T05:22:44.897351Z","id":"a561cc82-59d5-4b57-8b0b-63e8f77fbaa2","model_set":{"reader":"grok-4.3"},"one_line_summary":"MARGIN reduces geometric distortions in imbalanced vulnerability embeddings by dynamically regularizing margins with von Mises-Fisher concentration estimates and hyperspherical prototypes.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MARGIN corrects geometric distortions in hyperspherical embeddings to improve vulnerability detection on imbalanced datasets.","strongest_claim":"MARGIN consistently outperforms strong baselines, achieving notable improvements in classification and detection, especially on challenging, imbalanced datasets.","weakest_assumption":"That the observed frequency and difficulty imbalances manifest primarily as geometric distortions in hyperspherical space and that aligning embedding distributions with Voronoi cells via von Mises-Fisher concentration will reliably improve downstream detection without introducing new failure modes."}},"verdict_id":"a561cc82-59d5-4b57-8b0b-63e8f77fbaa2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a5d044be86706270eafdf96ff47c329df841e928d01e962958587fe53b5e6499","target":"record","created_at":"2026-06-23T03:13:57Z","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":"5b6e6eba03ae07efca9aff9b82b453503465d7ab4cbfa0ad33418f6ea293d601","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T09:14:51Z","title_canon_sha256":"634d16ccaf7ceb876b5d3a7a303c140f7e11f5ca96d5872315f25f97be100aad"},"schema_version":"1.0","source":{"id":"2605.10240","kind":"arxiv","version":2}},"canonical_sha256":"7f667b7925483387f837f7a3bd4b97889c15704f2e3c11cfc565430740241090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f667b7925483387f837f7a3bd4b97889c15704f2e3c11cfc565430740241090","first_computed_at":"2026-06-23T03:13:57.898350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:57.898350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"88S1H0SV46S83QQ4XkbiMcAoNX68vo4gap9gTQouGByvu1ipPYmbrkpwZU/l0bC2SAHkxhkFnPezhIWUc4+pAw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:57.898768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10240","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5d044be86706270eafdf96ff47c329df841e928d01e962958587fe53b5e6499","sha256:9f720bbe99b304d9d8a47ef07204b1567bdceb9d0d323038e6918d3ed53d67c5"],"state_sha256":"8da1dcd0de3c95dc462b77b3952fcfe0e65acfab827bb617a63ced09f874e66c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THS4pdNlGiEyWvfEYWUIuWBVYP/3iZwSAY2vMQ74/icQL9S+9Ou3ZRDJ3IyVgxePJAFI3rhhxKJ4Wat4vJGYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:31:26.232791Z","bundle_sha256":"4fca8ce9d3bd96109338914eef72cd99be396f3e60556bbbbfd361eb61174d3d"}}