{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OMHJLO544X7ZMY4OU6X4EDLHDF","short_pith_number":"pith:OMHJLO54","canonical_record":{"source":{"id":"2509.20008","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T11:27:54Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"c64a3f6aeec868b081709c90a8221b8cae2950e7ed8dfdd9cd6137a13525e646","abstract_canon_sha256":"1ee8cd09d19d302d81a11df221a527d18de47cdbb6de004d73a5c2dc36620984"},"schema_version":"1.0"},"canonical_sha256":"730e95bbbce5ff96638ea7afc20d6719487385905ed8bf2fecba5a24bf150023","source":{"kind":"arxiv","id":"2509.20008","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20008","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20008v2","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20008","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"OMHJLO544X7Z","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"OMHJLO544X7ZMY4O","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"OMHJLO54","created_at":"2026-06-26T01:15:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OMHJLO544X7ZMY4OU6X4EDLHDF","target":"record","payload":{"canonical_record":{"source":{"id":"2509.20008","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T11:27:54Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"c64a3f6aeec868b081709c90a8221b8cae2950e7ed8dfdd9cd6137a13525e646","abstract_canon_sha256":"1ee8cd09d19d302d81a11df221a527d18de47cdbb6de004d73a5c2dc36620984"},"schema_version":"1.0"},"canonical_sha256":"730e95bbbce5ff96638ea7afc20d6719487385905ed8bf2fecba5a24bf150023","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:46.043485Z","signature_b64":"lyfMGDT3TCVOYFaK0gAiijzzibH9W4LkMtj71HZT7UJ2VBq8+2vQgckd8i04qQEvugmu8qEAhVOecv/tyEXxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"730e95bbbce5ff96638ea7afc20d6719487385905ed8bf2fecba5a24bf150023","last_reissued_at":"2026-06-26T01:15:46.042980Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:46.042980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.20008","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":"2026-06-26T01:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mV2wfrrTMaMCM0Un55SMKmcA8FtyhEBCTlYFTZ9T3R8s/tPaKzFc5Iaw1w5wnOSwuMIlKzdT+Se1QyizMBs+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:41:51.370709Z"},"content_sha256":"a80b0ba721cf9f6e15c64f8a4ed9544aba204d00a4eae4d62581ecbf768976bb","schema_version":"1.0","event_id":"sha256:a80b0ba721cf9f6e15c64f8a4ed9544aba204d00a4eae4d62581ecbf768976bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OMHJLO544X7ZMY4OU6X4EDLHDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Pieter Libin, Raphael Simon, Wim Mees","submitted_at":"2025-09-24T11:27:54Z","abstract_excerpt":"Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investigate stochastic, partially observable penetration testing scenarios over host networks of varying siz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20008","kind":"arxiv","version":2},"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/2509.20008/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":"2026-06-26T01:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3n/4d6dOqMjd5GDPqFuX/AT8TNqiMCcDrbzMdtOvV8suPngXHJ1riRcAXR/GVnKkJ+kFo6fyNDBFstwX0WzdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:41:51.371521Z"},"content_sha256":"3feb9b885297bfe7427d8e8baf4caf036b53c11f7fa5d5eb8ae91c69d3e434ce","schema_version":"1.0","event_id":"sha256:3feb9b885297bfe7427d8e8baf4caf036b53c11f7fa5d5eb8ae91c69d3e434ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMHJLO544X7ZMY4OU6X4EDLHDF/bundle.json","state_url":"https://pith.science/pith/OMHJLO544X7ZMY4OU6X4EDLHDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMHJLO544X7ZMY4OU6X4EDLHDF/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":"2026-08-07T15:41:51Z","links":{"resolver":"https://pith.science/pith/OMHJLO544X7ZMY4OU6X4EDLHDF","bundle":"https://pith.science/pith/OMHJLO544X7ZMY4OU6X4EDLHDF/bundle.json","state":"https://pith.science/pith/OMHJLO544X7ZMY4OU6X4EDLHDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMHJLO544X7ZMY4OU6X4EDLHDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OMHJLO544X7ZMY4OU6X4EDLHDF","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":"1ee8cd09d19d302d81a11df221a527d18de47cdbb6de004d73a5c2dc36620984","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T11:27:54Z","title_canon_sha256":"c64a3f6aeec868b081709c90a8221b8cae2950e7ed8dfdd9cd6137a13525e646"},"schema_version":"1.0","source":{"id":"2509.20008","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20008","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20008v2","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20008","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"OMHJLO544X7Z","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"OMHJLO544X7ZMY4O","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"OMHJLO54","created_at":"2026-06-26T01:15:46Z"}],"graph_snapshots":[{"event_id":"sha256:3feb9b885297bfe7427d8e8baf4caf036b53c11f7fa5d5eb8ae91c69d3e434ce","target":"graph","created_at":"2026-06-26T01:15:46Z","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/2509.20008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investigate stochastic, partially observable penetration testing scenarios over host networks of varying siz","authors_text":"Pieter Libin, Raphael Simon, Wim Mees","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T11:27:54Z","title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20008","kind":"arxiv","version":2},"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:a80b0ba721cf9f6e15c64f8a4ed9544aba204d00a4eae4d62581ecbf768976bb","target":"record","created_at":"2026-06-26T01:15:46Z","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":"1ee8cd09d19d302d81a11df221a527d18de47cdbb6de004d73a5c2dc36620984","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T11:27:54Z","title_canon_sha256":"c64a3f6aeec868b081709c90a8221b8cae2950e7ed8dfdd9cd6137a13525e646"},"schema_version":"1.0","source":{"id":"2509.20008","kind":"arxiv","version":2}},"canonical_sha256":"730e95bbbce5ff96638ea7afc20d6719487385905ed8bf2fecba5a24bf150023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"730e95bbbce5ff96638ea7afc20d6719487385905ed8bf2fecba5a24bf150023","first_computed_at":"2026-06-26T01:15:46.042980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:46.042980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lyfMGDT3TCVOYFaK0gAiijzzibH9W4LkMtj71HZT7UJ2VBq8+2vQgckd8i04qQEvugmu8qEAhVOecv/tyEXxAw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:46.043485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.20008","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a80b0ba721cf9f6e15c64f8a4ed9544aba204d00a4eae4d62581ecbf768976bb","sha256:3feb9b885297bfe7427d8e8baf4caf036b53c11f7fa5d5eb8ae91c69d3e434ce"],"state_sha256":"943b1f6555c936699af1b6d0c97c5e15969d099e372fd01c5fb5a5efe97e2fd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ydsevdbh3VTMlcsViBxQsYa5kVXh1pmIU32D9eDyhK6v0fMls53HVZVs1d7Mj7RAJbbJmmK3I7rPDCGH3fFbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:41:51.377324Z","bundle_sha256":"1082f5f963613fcc17d75d500392879c20380e5cd7eaa3273856cdbbcd8d54e5"}}