{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HAURFE5Y6WCZWIUSBQ7JDHG7RM","short_pith_number":"pith:HAURFE5Y","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"},"canonical_sha256":"38291293b8f5859b22920c3e919cdf8b3a181b845c7477fcce72e772cbd41088","source":{"kind":"arxiv","id":"2605.11671","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11671","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11671v2","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11671","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"HAURFE5Y6WCZ","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"HAURFE5Y6WCZWIUS","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"HAURFE5Y","created_at":"2026-08-04T02:40:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HAURFE5Y6WCZWIUSBQ7JDHG7RM","target":"record","payload":{"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"},"canonical_sha256":"38291293b8f5859b22920c3e919cdf8b3a181b845c7477fcce72e772cbd41088","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"},"source_kind":"arxiv","source_id":"2605.11671","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T02:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zilZvdS+Rex8aNiNCDqpnrwhRHcM4ajycz/lXzBMjNoOSBTCsu1KGR/gCNO9dCrGx8yRlQMZhZCSPELTdmIICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:13:07.046728Z"},"content_sha256":"fa27b4f4275d8db9cbc38be1617ce7023cf2043e2f26c33c7afba3f6592f5756","schema_version":"1.0","event_id":"sha256:fa27b4f4275d8db9cbc38be1617ce7023cf2043e2f26c33c7afba3f6592f5756"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HAURFE5Y6WCZWIUSBQ7JDHG7RM","target":"graph","payload":{"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"},"verdict_id":"4d33dc8e-668b-4986-abe8-e0d2451c9acf"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T02:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmnUrIMH/8Ejl2lSV8HssoX0O6Ij0VSvEHbQM0Cl5/9roWM3bSW2zQ3Uuhl59e7qqDNrq96PmOBopJt5joElAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:13:07.047527Z"},"content_sha256":"ea8aeae409f6da05ddbe7b974d139fb58e0466cd4da2344ef9e1690a0667b68b","schema_version":"1.0","event_id":"sha256:ea8aeae409f6da05ddbe7b974d139fb58e0466cd4da2344ef9e1690a0667b68b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/bundle.json","state_url":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/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":"2026-08-04T16:13:07Z","links":{"resolver":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM","bundle":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/bundle.json","state":"https://pith.science/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAURFE5Y6WCZWIUSBQ7JDHG7RM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HAURFE5Y6WCZWIUSBQ7JDHG7RM","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":"6c2a9a041d30bcee62f3df33112029aa9ecf9a3b866ecab60e6c3d001c4f071f","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-12T07:28:12Z","title_canon_sha256":"f587461ba2975a30759dda0f5c33803b32df7e008310a9698c170736083deffa"},"schema_version":"1.0","source":{"id":"2605.11671","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11671","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11671v2","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11671","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"HAURFE5Y6WCZ","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"HAURFE5Y6WCZWIUS","created_at":"2026-08-04T02:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"HAURFE5Y","created_at":"2026-08-04T02:40:41Z"}],"graph_snapshots":[{"event_id":"sha256:ea8aeae409f6da05ddbe7b974d139fb58e0466cd4da2344ef9e1690a0667b68b","target":"graph","created_at":"2026-08-04T02:40:41Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Cochise supplies a minimal 597-line Python harness that separates planning from execution to support reproducible comparisons of LLM agents in penetration testing."}],"snapshot_sha256":"3e47aea00163169b0a38934adf42f41ef89cf8634cc8298827cbdf1e58e6230f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.11671/integrity.json","findings":[],"snapshot_sha256":"2f56123c23f7f752107ae214c0e25b40aa9c93e5ca440ea8803342678c720774","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Andreas Happe, J\\\"urgen Cito","cross_cats":["cs.AI","cs.SE"],"headline":"Cochise supplies a minimal 597-line Python harness that separates planning from execution to support reproducible comparisons of LLM agents in penetration testing.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-12T07:28:12Z","title":"Cochise: A Reference Harness for Autonomous Penetration Testing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11671","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T01:02:50.261474Z","id":"4d33dc8e-668b-4986-abe8-e0d2451c9acf","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"4d33dc8e-668b-4986-abe8-e0d2451c9acf"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fa27b4f4275d8db9cbc38be1617ce7023cf2043e2f26c33c7afba3f6592f5756","target":"record","created_at":"2026-08-04T02:40:41Z","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":"6c2a9a041d30bcee62f3df33112029aa9ecf9a3b866ecab60e6c3d001c4f071f","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-12T07:28:12Z","title_canon_sha256":"f587461ba2975a30759dda0f5c33803b32df7e008310a9698c170736083deffa"},"schema_version":"1.0","source":{"id":"2605.11671","kind":"arxiv","version":2}},"canonical_sha256":"38291293b8f5859b22920c3e919cdf8b3a181b845c7477fcce72e772cbd41088","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38291293b8f5859b22920c3e919cdf8b3a181b845c7477fcce72e772cbd41088","first_computed_at":"2026-08-04T02:40:41.817461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:40:41.817461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CndZq3wiDh7oERicIBYqSp/D+9xD0VUJDn1HS1xc5Msn9ei8h7tM6/izsjBPVHgLg8edDaZrCzqyIMFKGjI7DA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:40:41.820171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11671","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa27b4f4275d8db9cbc38be1617ce7023cf2043e2f26c33c7afba3f6592f5756","sha256:ea8aeae409f6da05ddbe7b974d139fb58e0466cd4da2344ef9e1690a0667b68b"],"state_sha256":"093c060a646c6efa04ba520dc483d7a3235e0c0bbbb44cdf6044df2f27ec350a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I98cU+KPBDmiE45VkKrx5ePSdYhHd2p701ZJZOIYWzrxDTg3cEeDS13mITTw6BD73ck1t7neUHYK5R+0UTdaCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:13:07.053320Z","bundle_sha256":"ce62b6ef1c9fcf30f3f3744d59c3a3adad74cefc696917390534d82eeeb5cf38"}}