{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HAURFE5Y6WCZWIUSBQ7JDHG7RM","short_pith_number":"pith:HAURFE5Y","schema_version":"1.0","canonical_sha256":"38291293b8f5859b22920c3e919cdf8b3a181b845c7477fcce72e772cbd41088","source":{"kind":"arxiv","id":"2605.11671","version":2},"attestation_state":"computed","paper":{"title":"Cochise: A Reference Harness for Autonomous Penetration Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Cochise supplies a minimal 597-line Python harness that separates planning from execution to support reproducible comparisons of LLM agents in penetration testing.","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Andreas Happe, J\\\"urgen Cito","submitted_at":"2026-05-12T07:28:12Z","abstract_excerpt":"Recent work on LLM-driven autonomous penetration testing reports promising results, but existing systems often bundle architectural, prompting, and tool-integration choices together. This makes it difficult to determine what is gained over a simple agent and harness. We present Cochise, a 630 LOC Python reference implementation for autonomous penetration-testing experiments. Cochise connects to a Linux execution host over SSH and supports attacking controlled target environments reachable from that jump host.\n  The prototype implements a Planner--Executor architecture in which long-term state "},"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":"2605.11671","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-12T07:28:12Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"f587461ba2975a30759dda0f5c33803b32df7e008310a9698c170736083deffa","abstract_canon_sha256":"6c2a9a041d30bcee62f3df33112029aa9ecf9a3b866ecab60e6c3d001c4f071f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:40:41.820171Z","signature_b64":"CndZq3wiDh7oERicIBYqSp/D+9xD0VUJDn1HS1xc5Msn9ei8h7tM6/izsjBPVHgLg8edDaZrCzqyIMFKGjI7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38291293b8f5859b22920c3e919cdf8b3a181b845c7477fcce72e772cbd41088","last_reissued_at":"2026-08-04T02:40:41.817461Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:40:41.817461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cochise: A Reference Harness for Autonomous Penetration Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Cochise supplies a minimal 597-line Python harness that separates planning from execution to support reproducible comparisons of LLM agents in penetration testing.","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Andreas Happe, J\\\"urgen Cito","submitted_at":"2026-05-12T07:28:12Z","abstract_excerpt":"Recent work on LLM-driven autonomous penetration testing reports promising results, but existing systems often bundle architectural, prompting, and tool-integration choices together. This makes it difficult to determine what is gained over a simple agent and harness. We present Cochise, a 630 LOC Python reference implementation for autonomous penetration-testing experiments. Cochise connects to a Linux execution host over SSH and supports attacking controlled target environments reachable from that jump host.\n  The prototype implements a Planner--Executor architecture in which long-term state "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Cochise is intended not as a state-of-the-art pen-testing agent, but as reusable experimental infrastructure for comparing models, agent architectures, and penetration-testing traces.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a minimal separated Planner-Executor architecture connected via SSH to a Linux host is sufficient to enable meaningful comparisons of LLM choices and agent designs across different penetration-testing scenarios.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Cochise is a minimal open-source harness implementing a Planner-Executor architecture over SSH for LLM-driven autonomous penetration testing, demonstrated on the GOAD testbed with released replay tools and trajectory logs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Cochise supplies a minimal 597-line Python harness that separates planning from execution to support reproducible comparisons of LLM agents in penetration testing.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3e47aea00163169b0a38934adf42f41ef89cf8634cc8298827cbdf1e58e6230f"},"source":{"id":"2605.11671","kind":"arxiv","version":2},"verdict":{"id":"4d33dc8e-668b-4986-abe8-e0d2451c9acf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T01:02:50.261474Z","strongest_claim":"Cochise is intended not as a state-of-the-art pen-testing agent, but as reusable experimental infrastructure for comparing models, agent architectures, and penetration-testing traces.","one_line_summary":"Cochise is a minimal open-source harness implementing a Planner-Executor architecture over SSH for LLM-driven autonomous penetration testing, demonstrated on the GOAD testbed with released replay tools and trajectory logs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a minimal separated Planner-Executor architecture connected via SSH to a Linux host is sufficient to enable meaningful comparisons of LLM choices and agent designs across different penetration-testing scenarios.","pith_extraction_headline":"Cochise supplies a minimal 597-line Python harness that separates planning from execution to support reproducible comparisons of LLM agents in penetration testing."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11671/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-21T00:01:32.354152Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T14:07:12.726511Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-20T03:42:00.541479Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:40:09.424891Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2f56123c23f7f752107ae214c0e25b40aa9c93e5ca440ea8803342678c720774"},"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":"2605.11671","created_at":"2026-08-04T02:40:41.819990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11671v2","created_at":"2026-08-04T02:40:41.819990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11671","created_at":"2026-08-04T02:40:41.819990+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAURFE5Y6WCZ","created_at":"2026-08-04T02:40:41.819990+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAURFE5Y6WCZWIUS","created_at":"2026-08-04T02:40:41.819990+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAURFE5Y","created_at":"2026-08-04T02:40:41.819990+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/HAURFE5Y6WCZWIUSBQ7JDHG7RM","json":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM.json","graph_json":"https://pith.science/api/pith-number/HAURFE5Y6WCZWIUSBQ7JDHG7RM/graph.json","events_json":"https://pith.science/api/pith-number/HAURFE5Y6WCZWIUSBQ7JDHG7RM/events.json","paper":"https://pith.science/paper/HAURFE5Y"},"agent_actions":{"view_html":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM","download_json":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM.json","view_paper":"https://pith.science/paper/HAURFE5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11671&json=true","fetch_graph":"https://pith.science/api/pith-number/HAURFE5Y6WCZWIUSBQ7JDHG7RM/graph.json","fetch_events":"https://pith.science/api/pith-number/HAURFE5Y6WCZWIUSBQ7JDHG7RM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/action/storage_attestation","attest_author":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/action/author_attestation","sign_citation":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/action/citation_signature","submit_replication":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/action/replication_record"}},"created_at":"2026-08-04T02:40:41.819990+00:00","updated_at":"2026-08-04T02:40:41.819990+00:00"}