{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3MSJE7HOZDEPJ432EEGSBCSHOA","short_pith_number":"pith:3MSJE7HO","canonical_record":{"source":{"id":"2506.14682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-17T16:19:06Z","cross_cats_sorted":[],"title_canon_sha256":"b19e11441be7883818081b5bac12cbf9477f223477f3bca48ffc6cb0e2a0eb2c","abstract_canon_sha256":"98c12305e88ebf9c501d17d743fe135d1391269217ad2a200a875ef845a71dc5"},"schema_version":"1.0"},"canonical_sha256":"db24927ceec8c8f4f37a210d208a477038cccb41685778c7e8decb79c41f9520","source":{"kind":"arxiv","id":"2506.14682","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14682","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14682v1","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14682","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"3MSJE7HOZDEP","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"3MSJE7HOZDEPJ432","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"3MSJE7HO","created_at":"2026-07-05T11:23:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3MSJE7HOZDEPJ432EEGSBCSHOA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-17T16:19:06Z","cross_cats_sorted":[],"title_canon_sha256":"b19e11441be7883818081b5bac12cbf9477f223477f3bca48ffc6cb0e2a0eb2c","abstract_canon_sha256":"98c12305e88ebf9c501d17d743fe135d1391269217ad2a200a875ef845a71dc5"},"schema_version":"1.0"},"canonical_sha256":"db24927ceec8c8f4f37a210d208a477038cccb41685778c7e8decb79c41f9520","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:00.725300Z","signature_b64":"6AsFkq5ukcAPyrsW2CSl4VZJ1GuEc9FPDyH85icozUqCsxzn1kyKeH8VVkMv1VRD4eauD4SzQXIe/DpIG1UFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db24927ceec8c8f4f37a210d208a477038cccb41685778c7e8decb79c41f9520","last_reissued_at":"2026-07-05T11:23:00.724774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:00.724774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14682","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AjJxorn7BEe8OwB+iGPLdiotqq3mCc7qLUkv4u1Z34vrP/2h1kq8uZQnusIQk0qhLdCTFha2SJz5HlQs9NAqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:48:09.633245Z"},"content_sha256":"baaf5e146475cfbf691cc27b6a719272a8dd612d74d3e3721a4e6ff953a7e2c1","schema_version":"1.0","event_id":"sha256:baaf5e146475cfbf691cc27b6a719272a8dd612d74d3e3721a4e6ff953a7e2c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3MSJE7HOZDEPJ432EEGSBCSHOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Ads Dawson, Nick Landers, Rob Mulla, Shane Caldwell","submitted_at":"2025-06-17T16:19:06Z","abstract_excerpt":"We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning (AI/ML) security vulnerabilities. The benchmark consists of 70 realistic black-box capture-the-flag (CTF) challenges from the Crucible challenge environment on the Dreadnode platform, requiring models to write python code to interact with and compromise AI systems. Claude-3.7-Sonnet emerged as the clear leader, solving 43 challenges (61% of the total suite, 46.9% overall success rate), with Gemini-2.5-Pro following at 39 c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14682","kind":"arxiv","version":1},"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/2506.14682/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":"2026-07-05T11:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNTSBVJDdDkQAXNdRC6DoSKSUSrgXeXyzb4Axl9xy8/rsE5sjDB29CDndkpfuYuBsNElglAXJhtrlJT+VvDkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:48:09.634665Z"},"content_sha256":"d15f46d1db01514b31327a8454424c9097684e83916c1c432158a6c8864ab7d7","schema_version":"1.0","event_id":"sha256:d15f46d1db01514b31327a8454424c9097684e83916c1c432158a6c8864ab7d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MSJE7HOZDEPJ432EEGSBCSHOA/bundle.json","state_url":"https://pith.science/pith/3MSJE7HOZDEPJ432EEGSBCSHOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MSJE7HOZDEPJ432EEGSBCSHOA/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":"2026-08-17T02:48:09Z","links":{"resolver":"https://pith.science/pith/3MSJE7HOZDEPJ432EEGSBCSHOA","bundle":"https://pith.science/pith/3MSJE7HOZDEPJ432EEGSBCSHOA/bundle.json","state":"https://pith.science/pith/3MSJE7HOZDEPJ432EEGSBCSHOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MSJE7HOZDEPJ432EEGSBCSHOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3MSJE7HOZDEPJ432EEGSBCSHOA","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":"98c12305e88ebf9c501d17d743fe135d1391269217ad2a200a875ef845a71dc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-17T16:19:06Z","title_canon_sha256":"b19e11441be7883818081b5bac12cbf9477f223477f3bca48ffc6cb0e2a0eb2c"},"schema_version":"1.0","source":{"id":"2506.14682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14682","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14682v1","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14682","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"3MSJE7HOZDEP","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"3MSJE7HOZDEPJ432","created_at":"2026-07-05T11:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"3MSJE7HO","created_at":"2026-07-05T11:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:d15f46d1db01514b31327a8454424c9097684e83916c1c432158a6c8864ab7d7","target":"graph","created_at":"2026-07-05T11:23:00Z","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/2506.14682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning (AI/ML) security vulnerabilities. The benchmark consists of 70 realistic black-box capture-the-flag (CTF) challenges from the Crucible challenge environment on the Dreadnode platform, requiring models to write python code to interact with and compromise AI systems. Claude-3.7-Sonnet emerged as the clear leader, solving 43 challenges (61% of the total suite, 46.9% overall success rate), with Gemini-2.5-Pro following at 39 c","authors_text":"Ads Dawson, Nick Landers, Rob Mulla, Shane Caldwell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-17T16:19:06Z","title":"AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14682","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:baaf5e146475cfbf691cc27b6a719272a8dd612d74d3e3721a4e6ff953a7e2c1","target":"record","created_at":"2026-07-05T11:23:00Z","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":"98c12305e88ebf9c501d17d743fe135d1391269217ad2a200a875ef845a71dc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-17T16:19:06Z","title_canon_sha256":"b19e11441be7883818081b5bac12cbf9477f223477f3bca48ffc6cb0e2a0eb2c"},"schema_version":"1.0","source":{"id":"2506.14682","kind":"arxiv","version":1}},"canonical_sha256":"db24927ceec8c8f4f37a210d208a477038cccb41685778c7e8decb79c41f9520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db24927ceec8c8f4f37a210d208a477038cccb41685778c7e8decb79c41f9520","first_computed_at":"2026-07-05T11:23:00.724774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:00.724774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6AsFkq5ukcAPyrsW2CSl4VZJ1GuEc9FPDyH85icozUqCsxzn1kyKeH8VVkMv1VRD4eauD4SzQXIe/DpIG1UFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:00.725300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baaf5e146475cfbf691cc27b6a719272a8dd612d74d3e3721a4e6ff953a7e2c1","sha256:d15f46d1db01514b31327a8454424c9097684e83916c1c432158a6c8864ab7d7"],"state_sha256":"ad31c188e2a13b0d3a4b9c795fcd816bcc60ba76341c7b30eac49796cf5f91c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PLnWxoXmiJlSTeXERPI2J6NqY3fPyI2On61rzoOQtufFvzmfxqvIAnyIIYR8JMY2eO0IjAaGvAMXFrj6Fe/XAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:48:09.653020Z","bundle_sha256":"161954e6a4cebb61fc107581aa0609db48c7d5e4b61625ebc2680f0a3d844e86"}}