{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GAASFT3KD6NREHTBCL3N7EIP5P","short_pith_number":"pith:GAASFT3K","schema_version":"1.0","canonical_sha256":"300122cf6a1f9b121e6112f6df910febf137b6bddf458a66c2c2528097f9661a","source":{"kind":"arxiv","id":"2605.29963","version":1},"attestation_state":"computed","paper":{"title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Fabian Kaczmarczyck, Ilia Shumailov, Ivan Petrov, Jamie Hayes, Luca Invernizzi, Mark Vero, Martin Vechev, Niels Heinen, Tianqi Fan","submitted_at":"2026-05-28T14:02:27Z","abstract_excerpt":"Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots with low system security risks. However, LLM-powered honeypot development lacks a unified evaluation framework. Most evaluations consist of measuring response similarity on fixed commands, manual testing, or real-world deployment. These methods are often not scalable for development, reproducible across evaluations, representative of practical attacks, or adap"},"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":"2605.29963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-28T14:02:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"baef8fa0bfd657cf0b71f042abacdff829e5b13625935b17d42e83d33da94fab","abstract_canon_sha256":"2de2e418f9cbb499bccc8fab7b8548eac346712c5f656bb86fb46f47c9b0c9fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:04.094878Z","signature_b64":"73KurVj1DlKxu1XnvEobXmlD3GTCiCuk9sh+9CQXzjlMVCh9iQAXnxKEj3ST06HTx6ophn+NjQ9641Mzixk7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300122cf6a1f9b121e6112f6df910febf137b6bddf458a66c2c2528097f9661a","last_reissued_at":"2026-05-29T02:06:04.094004Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:04.094004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Fabian Kaczmarczyck, Ilia Shumailov, Ivan Petrov, Jamie Hayes, Luca Invernizzi, Mark Vero, Martin Vechev, Niels Heinen, Tianqi Fan","submitted_at":"2026-05-28T14:02:27Z","abstract_excerpt":"Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots with low system security risks. However, LLM-powered honeypot development lacks a unified evaluation framework. Most evaluations consist of measuring response similarity on fixed commands, manual testing, or real-world deployment. These methods are often not scalable for development, reproducible across evaluations, representative of practical attacks, or adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29963","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/2605.29963/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":"2605.29963","created_at":"2026-05-29T02:06:04.094146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29963v1","created_at":"2026-05-29T02:06:04.094146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29963","created_at":"2026-05-29T02:06:04.094146+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAASFT3KD6NR","created_at":"2026-05-29T02:06:04.094146+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAASFT3KD6NREHTB","created_at":"2026-05-29T02:06:04.094146+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAASFT3K","created_at":"2026-05-29T02:06:04.094146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P","json":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P.json","graph_json":"https://pith.science/api/pith-number/GAASFT3KD6NREHTBCL3N7EIP5P/graph.json","events_json":"https://pith.science/api/pith-number/GAASFT3KD6NREHTBCL3N7EIP5P/events.json","paper":"https://pith.science/paper/GAASFT3K"},"agent_actions":{"view_html":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P","download_json":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P.json","view_paper":"https://pith.science/paper/GAASFT3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29963&json=true","fetch_graph":"https://pith.science/api/pith-number/GAASFT3KD6NREHTBCL3N7EIP5P/graph.json","fetch_events":"https://pith.science/api/pith-number/GAASFT3KD6NREHTBCL3N7EIP5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P/action/storage_attestation","attest_author":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P/action/author_attestation","sign_citation":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P/action/citation_signature","submit_replication":"https://pith.science/pith/GAASFT3KD6NREHTBCL3N7EIP5P/action/replication_record"}},"created_at":"2026-05-29T02:06:04.094146+00:00","updated_at":"2026-05-29T02:06:04.094146+00:00"}