{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EZ7SB446RBJCIIXCJJETAV2BGI","short_pith_number":"pith:EZ7SB446","canonical_record":{"source":{"id":"2605.28146","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-27T08:29:28Z","cross_cats_sorted":[],"title_canon_sha256":"7d8f069ef148059217b9715f8a4245d4179cac8dc20530927ff176efa4661a0c","abstract_canon_sha256":"ea3bb4fc9165e24c70ee8cad48478b4cc5b484f2a827e8073719eff6a7ff5824"},"schema_version":"1.0"},"canonical_sha256":"267f20f39e88522422e24a49305741322794413a6848af2414450576dd2ffccc","source":{"kind":"arxiv","id":"2605.28146","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28146","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28146v1","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28146","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"EZ7SB446RBJC","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"EZ7SB446RBJCIIXC","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"EZ7SB446","created_at":"2026-05-28T01:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EZ7SB446RBJCIIXCJJETAV2BGI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28146","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-27T08:29:28Z","cross_cats_sorted":[],"title_canon_sha256":"7d8f069ef148059217b9715f8a4245d4179cac8dc20530927ff176efa4661a0c","abstract_canon_sha256":"ea3bb4fc9165e24c70ee8cad48478b4cc5b484f2a827e8073719eff6a7ff5824"},"schema_version":"1.0"},"canonical_sha256":"267f20f39e88522422e24a49305741322794413a6848af2414450576dd2ffccc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:00.336530Z","signature_b64":"WM9FTgJ1TCR9ufY1oZ5ic7i5Fp1PGkD69acEwPziObQy+UgBT5ID7ZVAzy3BohUPfB+X5B1OTVANYoo4bN/0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"267f20f39e88522422e24a49305741322794413a6848af2414450576dd2ffccc","last_reissued_at":"2026-05-28T01:05:00.336109Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:00.336109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28146","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":"2026-05-28T01:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdIHg2PApOt5FqqqB49rRWgSjScCD4c7uoia1M+kDeju+OFNLYK50A73iJnFZGeNeejCwUJqS+mbQ5MNngRSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T09:32:54.421099Z"},"content_sha256":"e5ac6d0ce6a2860b32592905e07d27116ac137e91f46ecf85bfc76fdaf5e8ef9","schema_version":"1.0","event_id":"sha256:e5ac6d0ce6a2860b32592905e07d27116ac137e91f46ecf85bfc76fdaf5e8ef9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EZ7SB446RBJCIIXCJJETAV2BGI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cybersecurity AI (CAI) Dataset","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"V\\'ictor Mayoral-Vilches","submitted_at":"2026-05-27T08:29:28Z","abstract_excerpt":"We present CAI Dataset, a fourteen-month corpus of cybersecurity LLM trajectories collected through the open-source CAI agent framework, built in response to PentestGPT's finding that expert operator trajectories, not base-model capability, are the bottleneck for cybersecurity LLM performance. CAI Dataset aggregates 230,935 session logs and 26,027,742 user prompts from 16,768 source IPs across 123 countries, exercising 4,187 unique LLM identifiers against 23,147 target domains over 18.07 TB of durable storage. The mix is hands-on (36.4% offensive, 20.1% attacker-intent, 27.5% business / integr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28146","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/2605.28146/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":"2026-05-28T01:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l92C49UPcH2GDvooMPOJQ1nCTgYNWkoSzk07PCiOoJM34B1yIWeEYmCgxT72sExMMeGaCskBNHbmW7WIZuLvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T09:32:54.421483Z"},"content_sha256":"98a507b71c4918cdc507d5173451a54e8d08a65753d0e611b8c229aa7ddc77e3","schema_version":"1.0","event_id":"sha256:98a507b71c4918cdc507d5173451a54e8d08a65753d0e611b8c229aa7ddc77e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EZ7SB446RBJCIIXCJJETAV2BGI/bundle.json","state_url":"https://pith.science/pith/EZ7SB446RBJCIIXCJJETAV2BGI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EZ7SB446RBJCIIXCJJETAV2BGI/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":"2026-06-30T09:32:54Z","links":{"resolver":"https://pith.science/pith/EZ7SB446RBJCIIXCJJETAV2BGI","bundle":"https://pith.science/pith/EZ7SB446RBJCIIXCJJETAV2BGI/bundle.json","state":"https://pith.science/pith/EZ7SB446RBJCIIXCJJETAV2BGI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EZ7SB446RBJCIIXCJJETAV2BGI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EZ7SB446RBJCIIXCJJETAV2BGI","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":"ea3bb4fc9165e24c70ee8cad48478b4cc5b484f2a827e8073719eff6a7ff5824","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-27T08:29:28Z","title_canon_sha256":"7d8f069ef148059217b9715f8a4245d4179cac8dc20530927ff176efa4661a0c"},"schema_version":"1.0","source":{"id":"2605.28146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28146","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28146v1","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28146","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"EZ7SB446RBJC","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"EZ7SB446RBJCIIXC","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"EZ7SB446","created_at":"2026-05-28T01:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:98a507b71c4918cdc507d5173451a54e8d08a65753d0e611b8c229aa7ddc77e3","target":"graph","created_at":"2026-05-28T01:05:00Z","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/2605.28146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CAI Dataset, a fourteen-month corpus of cybersecurity LLM trajectories collected through the open-source CAI agent framework, built in response to PentestGPT's finding that expert operator trajectories, not base-model capability, are the bottleneck for cybersecurity LLM performance. CAI Dataset aggregates 230,935 session logs and 26,027,742 user prompts from 16,768 source IPs across 123 countries, exercising 4,187 unique LLM identifiers against 23,147 target domains over 18.07 TB of durable storage. The mix is hands-on (36.4% offensive, 20.1% attacker-intent, 27.5% business / integr","authors_text":"V\\'ictor Mayoral-Vilches","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-27T08:29:28Z","title":"Cybersecurity AI (CAI) Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28146","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:e5ac6d0ce6a2860b32592905e07d27116ac137e91f46ecf85bfc76fdaf5e8ef9","target":"record","created_at":"2026-05-28T01:05:00Z","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":"ea3bb4fc9165e24c70ee8cad48478b4cc5b484f2a827e8073719eff6a7ff5824","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-27T08:29:28Z","title_canon_sha256":"7d8f069ef148059217b9715f8a4245d4179cac8dc20530927ff176efa4661a0c"},"schema_version":"1.0","source":{"id":"2605.28146","kind":"arxiv","version":1}},"canonical_sha256":"267f20f39e88522422e24a49305741322794413a6848af2414450576dd2ffccc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"267f20f39e88522422e24a49305741322794413a6848af2414450576dd2ffccc","first_computed_at":"2026-05-28T01:05:00.336109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:00.336109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WM9FTgJ1TCR9ufY1oZ5ic7i5Fp1PGkD69acEwPziObQy+UgBT5ID7ZVAzy3BohUPfB+X5B1OTVANYoo4bN/0Cg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:00.336530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5ac6d0ce6a2860b32592905e07d27116ac137e91f46ecf85bfc76fdaf5e8ef9","sha256:98a507b71c4918cdc507d5173451a54e8d08a65753d0e611b8c229aa7ddc77e3"],"state_sha256":"7b282896d2952753d403d051cf4e3ce5d78dee27f59e45e9316dba5b38234cc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQMa9JnqkCidzuS9CgAKn8jeuwZSMzeizgIR13lLDV6b2UNcSvdpkhVviOkQlnXkLOvSmWKX4/DaHN5/NnMPCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T09:32:54.423416Z","bundle_sha256":"c86b141ae5c9d5f30072482ae166d5c49e5c1673f35bb91df6d27f43f1a05341"}}