{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LLPZ5DSAWR5YZT5NCZYVN5IMBV","short_pith_number":"pith:LLPZ5DSA","canonical_record":{"source":{"id":"2408.08926","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-15T17:23:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"title_canon_sha256":"9d606e70cdbe558916d80b5c5b48be2c362c9b90458bc0f487d5242334657ae4","abstract_canon_sha256":"61cff41d13a23379bab61317532c9e9b970345c4ba5ac04fe2f3242726f1da04"},"schema_version":"1.0"},"canonical_sha256":"5adf9e8e40b47b8ccfad167156f50c0d41b658de8bcd4ffc04c5f05102cd8a57","source":{"kind":"arxiv","id":"2408.08926","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08926","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08926v4","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08926","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"LLPZ5DSAWR5Y","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"LLPZ5DSAWR5YZT5N","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"LLPZ5DSA","created_at":"2026-07-05T10:48:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LLPZ5DSAWR5YZT5NCZYVN5IMBV","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08926","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-15T17:23:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"title_canon_sha256":"9d606e70cdbe558916d80b5c5b48be2c362c9b90458bc0f487d5242334657ae4","abstract_canon_sha256":"61cff41d13a23379bab61317532c9e9b970345c4ba5ac04fe2f3242726f1da04"},"schema_version":"1.0"},"canonical_sha256":"5adf9e8e40b47b8ccfad167156f50c0d41b658de8bcd4ffc04c5f05102cd8a57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:18.488909Z","signature_b64":"cah+xz+FBUq7cPjtH+0/MOy4+JaqPJcLpAtY/qQRLjqoDxYTt0CLXOK2gxdKT7klzH9DGMfU5ZMKVb6NJmABCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5adf9e8e40b47b8ccfad167156f50c0d41b658de8bcd4ffc04c5f05102cd8a57","last_reissued_at":"2026-07-05T10:48:18.488389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:18.488389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08926","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":"2026-07-05T10:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUaleDr3/mTQqBgL64DIixqcFCHv25WNyeHt4DzLjaCHNCw96AB8UTMhQBl2GyLjne7RYRy8bIRceApcnjvgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T13:50:52.376572Z"},"content_sha256":"3b11d0fcdaf0ed72c765e806af5f1cd6d309b45c7f7a925ab2c0c749493eae61","schema_version":"1.0","event_id":"sha256:3b11d0fcdaf0ed72c765e806af5f1cd6d309b45c7f7a925ab2c0c749493eae61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LLPZ5DSAWR5YZT5NCZYVN5IMBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.CR","authors_text":"Andy K. Zhang, Ari Glenn, Celeste Menders, Dan Boneh, Daniel E. Ho, Daniel Zamoshchin, Derek Askaryar, Donovan Jasper, Eliot Jones, Gashon Hussein, Gautham Raghupathi, Joey Ji, Justin W. Lin, Kenny Osele, Leo Glikbarg, Mike Yang, Nathan Tran, Neil Perry, Percy Liang, Polycarpos Yiorkadjis, Pura Peetathawatchai, Rinnara Sangpisit, Rishi Alluri, Riya Dulepet, Samantha Liu, Teddy Zhang, Vikram Sivashankar","submitted_at":"2024-08-15T17:23:10Z","abstract_excerpt":"Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08926","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/2408.08926/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":"2026-07-05T10:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sW1jIF7DxowfBu5m3SqHgcSirDyi/CQ9P0lK6JOa+LF4GweKAaa+n+5JXpLaUCzyRy1/HFcrF9+MkhqBMC3wCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T13:50:52.376951Z"},"content_sha256":"d179f77e697fb43751712e0abc402058b62d04b98b3937f1e3127afc4205ff1f","schema_version":"1.0","event_id":"sha256:d179f77e697fb43751712e0abc402058b62d04b98b3937f1e3127afc4205ff1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV/bundle.json","state_url":"https://pith.science/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV/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":"2026-07-20T13:50:52Z","links":{"resolver":"https://pith.science/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV","bundle":"https://pith.science/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV/bundle.json","state":"https://pith.science/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLPZ5DSAWR5YZT5NCZYVN5IMBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LLPZ5DSAWR5YZT5NCZYVN5IMBV","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":"61cff41d13a23379bab61317532c9e9b970345c4ba5ac04fe2f3242726f1da04","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-15T17:23:10Z","title_canon_sha256":"9d606e70cdbe558916d80b5c5b48be2c362c9b90458bc0f487d5242334657ae4"},"schema_version":"1.0","source":{"id":"2408.08926","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08926","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08926v4","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08926","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"LLPZ5DSAWR5Y","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"LLPZ5DSAWR5YZT5N","created_at":"2026-07-05T10:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"LLPZ5DSA","created_at":"2026-07-05T10:48:18Z"}],"graph_snapshots":[{"event_id":"sha256:d179f77e697fb43751712e0abc402058b62d04b98b3937f1e3127afc4205ff1f","target":"graph","created_at":"2026-07-05T10:48:18Z","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/2408.08926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 dist","authors_text":"Andy K. Zhang, Ari Glenn, Celeste Menders, Dan Boneh, Daniel E. Ho, Daniel Zamoshchin, Derek Askaryar, Donovan Jasper, Eliot Jones, Gashon Hussein, Gautham Raghupathi, Joey Ji, Justin W. Lin, Kenny Osele, Leo Glikbarg, Mike Yang, Nathan Tran, Neil Perry, Percy Liang, Polycarpos Yiorkadjis, Pura Peetathawatchai, Rinnara Sangpisit, Rishi Alluri, Riya Dulepet, Samantha Liu, Teddy Zhang, Vikram Sivashankar","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-15T17:23:10Z","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08926","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":"sha256:3b11d0fcdaf0ed72c765e806af5f1cd6d309b45c7f7a925ab2c0c749493eae61","target":"record","created_at":"2026-07-05T10:48:18Z","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":"61cff41d13a23379bab61317532c9e9b970345c4ba5ac04fe2f3242726f1da04","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-15T17:23:10Z","title_canon_sha256":"9d606e70cdbe558916d80b5c5b48be2c362c9b90458bc0f487d5242334657ae4"},"schema_version":"1.0","source":{"id":"2408.08926","kind":"arxiv","version":4}},"canonical_sha256":"5adf9e8e40b47b8ccfad167156f50c0d41b658de8bcd4ffc04c5f05102cd8a57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5adf9e8e40b47b8ccfad167156f50c0d41b658de8bcd4ffc04c5f05102cd8a57","first_computed_at":"2026-07-05T10:48:18.488389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:18.488389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cah+xz+FBUq7cPjtH+0/MOy4+JaqPJcLpAtY/qQRLjqoDxYTt0CLXOK2gxdKT7klzH9DGMfU5ZMKVb6NJmABCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:18.488909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08926","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b11d0fcdaf0ed72c765e806af5f1cd6d309b45c7f7a925ab2c0c749493eae61","sha256:d179f77e697fb43751712e0abc402058b62d04b98b3937f1e3127afc4205ff1f"],"state_sha256":"958aaafffbbf438d23dce49b210ad4c41f26645b8fb6c92a545484c5e2f81e62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FTv9CSjrtuzaATv8DeaC4IKCyMdp4FbahXPvnrEt3CK8ZiQOQub8Sg1jDAN1ChrzN8vXy2lbemnD3CKRs09rDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T13:50:52.379588Z","bundle_sha256":"146cb5e27a3c2bf721e7298c8c3515d0089a4e3db4e77020d7b6221b9f780725"}}