{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DQADHRI55LBMT4RXIAYBYU4SUC","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":"ac1fc6678e65c2717f63db818d8dd9a6b974d845e050eaef67f53be3f39177a4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-26T04:59:49Z","title_canon_sha256":"5000450cce3183688e0fad92f269882652b3a854af2db25d1dd446905d063a2e"},"schema_version":"1.0","source":{"id":"2605.26548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26548","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26548v1","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26548","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"DQADHRI55LBM","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"DQADHRI55LBMT4RX","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"DQADHRI5","created_at":"2026-05-27T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:fa07bd9e93e1ce70f32564cdb9793b198d688503528ffd262752232d4cd2b0f3","target":"graph","created_at":"2026-05-27T01:05:25Z","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/2605.26548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific descriptions, or vulnerability-reproduction tasks. We present SEC-bench Pro, a benchmark for measuring agent bug hunting on critical, high-complexity software systems. This work discloses reports with concrete PoC inputs and links fixes into reproducible tasks through a three-phase pipeline for vulnerabili","authors_text":"Chunqiu Steven Xia, Dongjun Kim, Hwiwon Lee, Jiawei Liu, Lingming Zhang, Ziqi Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-26T04:59:49Z","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26548","kind":"arxiv","version":1},"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":"sha256:59522ea393a16b5f1742882842f1774e6c087920a3ae1bb6992b432e473d3ea4","target":"record","created_at":"2026-05-27T01:05:25Z","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":"ac1fc6678e65c2717f63db818d8dd9a6b974d845e050eaef67f53be3f39177a4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-26T04:59:49Z","title_canon_sha256":"5000450cce3183688e0fad92f269882652b3a854af2db25d1dd446905d063a2e"},"schema_version":"1.0","source":{"id":"2605.26548","kind":"arxiv","version":1}},"canonical_sha256":"1c0033c51deac2c9f23740301c5392a0a631eeebd8342374371a758fe353d88d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c0033c51deac2c9f23740301c5392a0a631eeebd8342374371a758fe353d88d","first_computed_at":"2026-05-27T01:05:25.898787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:25.898787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z/dn0s28pY0jI8z+lMXqwE0Y58pxoUXycJ0JYdHggcy8yPqHN26fl7yFArurZZVR1dKhrjrmEsSw7NK/lD+HDg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:25.899337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59522ea393a16b5f1742882842f1774e6c087920a3ae1bb6992b432e473d3ea4","sha256:fa07bd9e93e1ce70f32564cdb9793b198d688503528ffd262752232d4cd2b0f3"],"state_sha256":"88ef78060d878734e895851ce05e545ed88a2f11b0c0eb3fc3f3d2585756c7ef"}