{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3Z6WFULXNMESWKYDD3UXKGT5LA","short_pith_number":"pith:3Z6WFULX","schema_version":"1.0","canonical_sha256":"de7d62d1776b092b2b031ee9751a7d5821c7e31dc69f2cdc8e2395ec82513a62","source":{"kind":"arxiv","id":"2601.22952","version":2},"attestation_state":"computed","paper":{"title":"Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ting Zhang, Yunpeng Xiong","submitted_at":"2026-01-30T13:14:55Z","abstract_excerpt":"Static Application Security Testing (SAST) tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives (FPs), imposing a substantial manual triage burden on developers. Recent advances in Large Language Model (LLM) agents offer a promising direction by enabling iterative reasoning, tool use, and environment interaction to refine SAST alerts. However, the comparative effectiveness of different LLM-based agent architectures for FP filtering remains poorly understood. In this paper, we present a comparative study of three state-of-the-art "},"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":"2601.22952","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-01-30T13:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"1486226d0ca8b488fad020b844f500a496d2524cf660fefe9b05542b95a57b5a","abstract_canon_sha256":"e58f116d9f2c83ceeda881388dfe08e68998f1044791f99d359e05b9e1a3ca54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:28.016824Z","signature_b64":"mTMatQNZVLntiY//oMQ+6vR5hHqtv7qfQ7/CNQAURND5ePldAxEk2trYl/2+tmPwCHvdfv0RU4kzx5cV7KiPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de7d62d1776b092b2b031ee9751a7d5821c7e31dc69f2cdc8e2395ec82513a62","last_reissued_at":"2026-06-30T01:16:28.015762Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:28.015762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ting Zhang, Yunpeng Xiong","submitted_at":"2026-01-30T13:14:55Z","abstract_excerpt":"Static Application Security Testing (SAST) tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives (FPs), imposing a substantial manual triage burden on developers. Recent advances in Large Language Model (LLM) agents offer a promising direction by enabling iterative reasoning, tool use, and environment interaction to refine SAST alerts. However, the comparative effectiveness of different LLM-based agent architectures for FP filtering remains poorly understood. In this paper, we present a comparative study of three state-of-the-art "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22952","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/2601.22952/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":"2601.22952","created_at":"2026-06-30T01:16:28.015831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22952v2","created_at":"2026-06-30T01:16:28.015831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22952","created_at":"2026-06-30T01:16:28.015831+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Z6WFULXNMES","created_at":"2026-06-30T01:16:28.015831+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Z6WFULXNMESWKYD","created_at":"2026-06-30T01:16:28.015831+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Z6WFULX","created_at":"2026-06-30T01:16:28.015831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.23243","citing_title":"Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23243","citing_title":"Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19049","citing_title":"Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA","json":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA.json","graph_json":"https://pith.science/api/pith-number/3Z6WFULXNMESWKYDD3UXKGT5LA/graph.json","events_json":"https://pith.science/api/pith-number/3Z6WFULXNMESWKYDD3UXKGT5LA/events.json","paper":"https://pith.science/paper/3Z6WFULX"},"agent_actions":{"view_html":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA","download_json":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA.json","view_paper":"https://pith.science/paper/3Z6WFULX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22952&json=true","fetch_graph":"https://pith.science/api/pith-number/3Z6WFULXNMESWKYDD3UXKGT5LA/graph.json","fetch_events":"https://pith.science/api/pith-number/3Z6WFULXNMESWKYDD3UXKGT5LA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA/action/storage_attestation","attest_author":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA/action/author_attestation","sign_citation":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA/action/citation_signature","submit_replication":"https://pith.science/pith/3Z6WFULXNMESWKYDD3UXKGT5LA/action/replication_record"}},"created_at":"2026-06-30T01:16:28.015831+00:00","updated_at":"2026-06-30T01:16:28.015831+00:00"}