{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:STH5XJ7XSQOD3OBMDLPVBSEAU6","short_pith_number":"pith:STH5XJ7X","schema_version":"1.0","canonical_sha256":"94cfdba7f7941c3db82c1adf50c880a7b4a7727c96dd3489defd695a1cf20f3e","source":{"kind":"arxiv","id":"2602.24009","version":4},"attestation_state":"computed","paper":{"title":"Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Chenxu Fu, Jingjie Zheng, Wei Xu, Zhicheng Fang","submitted_at":"2026-02-27T13:32:53Z","abstract_excerpt":"Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK FOUNDRY (JBF), a system that addresses this gap via a multi-agent workflow to translate jailbreak papers into executable modules for immediate evaluation within a unified harness. JBF features three core components: (i) JBF-LIB for shared contracts and reusable utilities; (ii) JBF-FORGE for the multi-agent paper-to-module translation; and (iii) JBF-EVAL for"},"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":"2602.24009","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-02-27T13:32:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"147ca9af542252af2b1203887f5d083817a4559386fa5e2460155df9bec1a1d4","abstract_canon_sha256":"45fb5ee8ee8160c477b8ca3d16b9e261ea02c8b3c74eea5f3c04fff4c7da57ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:18:28.024490Z","signature_b64":"5lEGzj/F3ZljZ0UE6Dtyt/fs/CuZCRMb8LJTvOBBS/XS0ctiJMYcjrqnHAblHha/r0IOqOLYO8Zq2sgdWsz3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94cfdba7f7941c3db82c1adf50c880a7b4a7727c96dd3489defd695a1cf20f3e","last_reissued_at":"2026-07-20T01:18:28.023545Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:18:28.023545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Chenxu Fu, Jingjie Zheng, Wei Xu, Zhicheng Fang","submitted_at":"2026-02-27T13:32:53Z","abstract_excerpt":"Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK FOUNDRY (JBF), a system that addresses this gap via a multi-agent workflow to translate jailbreak papers into executable modules for immediate evaluation within a unified harness. JBF features three core components: (i) JBF-LIB for shared contracts and reusable utilities; (ii) JBF-FORGE for the multi-agent paper-to-module translation; and (iii) JBF-EVAL for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.24009","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/2602.24009/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":"2602.24009","created_at":"2026-07-20T01:18:28.023983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.24009v4","created_at":"2026-07-20T01:18:28.023983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.24009","created_at":"2026-07-20T01:18:28.023983+00:00"},{"alias_kind":"pith_short_12","alias_value":"STH5XJ7XSQOD","created_at":"2026-07-20T01:18:28.023983+00:00"},{"alias_kind":"pith_short_16","alias_value":"STH5XJ7XSQOD3OBM","created_at":"2026-07-20T01:18:28.023983+00:00"},{"alias_kind":"pith_short_8","alias_value":"STH5XJ7X","created_at":"2026-07-20T01:18:28.023983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.24081","citing_title":"PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6","json":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6.json","graph_json":"https://pith.science/api/pith-number/STH5XJ7XSQOD3OBMDLPVBSEAU6/graph.json","events_json":"https://pith.science/api/pith-number/STH5XJ7XSQOD3OBMDLPVBSEAU6/events.json","paper":"https://pith.science/paper/STH5XJ7X"},"agent_actions":{"view_html":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6","download_json":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6.json","view_paper":"https://pith.science/paper/STH5XJ7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.24009&json=true","fetch_graph":"https://pith.science/api/pith-number/STH5XJ7XSQOD3OBMDLPVBSEAU6/graph.json","fetch_events":"https://pith.science/api/pith-number/STH5XJ7XSQOD3OBMDLPVBSEAU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6/action/storage_attestation","attest_author":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6/action/author_attestation","sign_citation":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6/action/citation_signature","submit_replication":"https://pith.science/pith/STH5XJ7XSQOD3OBMDLPVBSEAU6/action/replication_record"}},"created_at":"2026-07-20T01:18:28.023983+00:00","updated_at":"2026-07-20T01:18:28.023983+00:00"}