{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:C7QJ7UVPTFDJW4JE5WWXR6BRVE","short_pith_number":"pith:C7QJ7UVP","canonical_record":{"source":{"id":"2607.28826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T20:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"6e246db40f2df5ab5564afab342e72b48cf133c4a9c79a509800f61a52a2f04b","abstract_canon_sha256":"bedce908e84507fffafb809acf085410acf1e1f7f3a3389e95fdb171431ad05c"},"schema_version":"1.0"},"canonical_sha256":"17e09fd2af99469b7124edad78f831a928143b72280bf1022bd952f1dc145b16","source":{"kind":"arxiv","id":"2607.28826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28826","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28826v1","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28826","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"C7QJ7UVPTFDJ","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"C7QJ7UVPTFDJW4JE","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"C7QJ7UVP","created_at":"2026-08-03T01:16:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:C7QJ7UVPTFDJW4JE5WWXR6BRVE","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T20:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"6e246db40f2df5ab5564afab342e72b48cf133c4a9c79a509800f61a52a2f04b","abstract_canon_sha256":"bedce908e84507fffafb809acf085410acf1e1f7f3a3389e95fdb171431ad05c"},"schema_version":"1.0"},"canonical_sha256":"17e09fd2af99469b7124edad78f831a928143b72280bf1022bd952f1dc145b16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:16:53.747217Z","signature_b64":"wt0Kta3yMtSwVM9f0paQ1daoJwhRswSACbzW5GuOglX/jFiYGW9yP+X8A0jb4mJM0XYM4q5M60ibB59vyaCiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17e09fd2af99469b7124edad78f831a928143b72280bf1022bd952f1dc145b16","last_reissued_at":"2026-08-03T01:16:53.745544Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:16:53.745544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.28826","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":"2026-08-03T01:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2YchbH0vfpZkjcOY2JWPxC2h+wkrwa20i5G2rHyIpH3JGFKL9BcIcSsVWuRwPtbk9kG9qWTIYbwWnpYD9AygCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:06:46.682453Z"},"content_sha256":"0adf398380713623e5bf2662b207f26cd3ef58f4ca60fe2863abc15f5c06189f","schema_version":"1.0","event_id":"sha256:0adf398380713623e5bf2662b207f26cd3ef58f4ca60fe2863abc15f5c06189f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:C7QJ7UVPTFDJW4JE5WWXR6BRVE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian Taylor, Fran\\c{c}ois Rivest, Konur Tholl, Mariam El Mezouar, Ranwa Al Mallah","submitted_at":"2026-07-30T20:28:02Z","abstract_excerpt":"Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. ACO applications commonly employ Reinforcement Learning (RL) agents to learn defensive behaviors through interaction with environments. However, RL agents typically require extensive exploration during training, often resulting in unstable behavior and poor initial decision-making before converging toward effective defense strategies.\n  In this work, we investigate the use of a Large Language Model (LLM) to improve autonomous defensive decision-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28826","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/2607.28826/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":"2026-08-03T01:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2iUMBedZqpqZKMDk2s2TVi6I+mQ6VOqMGOSLMkVr2TzxIGOMzZGfin88oNivEKiZmBgijnVx7qtmnQ5iNPAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:06:46.683694Z"},"content_sha256":"9817f343586b29f98c85dd1c96a879ccc3fc9db18ffbcfe9c6de9c9f39a3413c","schema_version":"1.0","event_id":"sha256:9817f343586b29f98c85dd1c96a879ccc3fc9db18ffbcfe9c6de9c9f39a3413c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:C7QJ7UVPTFDJW4JE5WWXR6BRVE","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/s00521-025-11162-0) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Pozzi, A., Incremona, A., Tessera, D., Toti, D.: Mitigating exposure bias in large languagemodeldistillation:animitationlearningapproach.NeuralComputingand Applications37(18), 12013–12029 (Jun 2025). https://doi.org/10.1007/s00521- 025-1116","arxiv_id":"2607.28826","detector":"doi_compliance","evidence":{"ref_index":15,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/s00521-","reconstructed_doi":"10.1007/s00521-025-11162-0"},"severity":"advisory","ref_index":15,"audited_at":"2026-08-03T01:48:36.918158Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/s00521-025-11162-0","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"efc93c1bdd295a4cce87d91c6322450c0c0fb151b06df287920a172b8f394c9c","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17518,"payload_sha256":"c14a2b3def251c51710dd3d37b804b3345bb61c1a1b2d4ef99d9018120475513","signature_b64":"OKfdYd+Ihj4WubuIOGOhAbZQv6ShWb369qUF6cVL9nYqG2kYsst3NSIIHPiFSWGdKdK+bH8LiTJORk9bEz27AQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:53:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DoQLgXk9iHiMsyhaYjqBf7Xy9DjTL8OBW3+pLB3m1wzxP+JBlosy34HUccNg1oEd/xdxlvja9UZCrcQMQ/ToAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:06:46.690774Z"},"content_sha256":"bb3b1d5cf508c31f802a5d8a8b7d6f9ad539bb64345901adf535fd97eff1413c","schema_version":"1.0","event_id":"sha256:bb3b1d5cf508c31f802a5d8a8b7d6f9ad539bb64345901adf535fd97eff1413c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE/bundle.json","state_url":"https://pith.science/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE/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":"2026-08-06T20:06:46Z","links":{"resolver":"https://pith.science/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE","bundle":"https://pith.science/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE/bundle.json","state":"https://pith.science/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C7QJ7UVPTFDJW4JE5WWXR6BRVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C7QJ7UVPTFDJW4JE5WWXR6BRVE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bedce908e84507fffafb809acf085410acf1e1f7f3a3389e95fdb171431ad05c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T20:28:02Z","title_canon_sha256":"6e246db40f2df5ab5564afab342e72b48cf133c4a9c79a509800f61a52a2f04b"},"schema_version":"1.0","source":{"id":"2607.28826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28826","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28826v1","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28826","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"C7QJ7UVPTFDJ","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"C7QJ7UVPTFDJW4JE","created_at":"2026-08-03T01:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"C7QJ7UVP","created_at":"2026-08-03T01:16:53Z"}],"graph_snapshots":[{"event_id":"sha256:9817f343586b29f98c85dd1c96a879ccc3fc9db18ffbcfe9c6de9c9f39a3413c","target":"graph","created_at":"2026-08-03T01:16:53Z","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/2607.28826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. ACO applications commonly employ Reinforcement Learning (RL) agents to learn defensive behaviors through interaction with environments. However, RL agents typically require extensive exploration during training, often resulting in unstable behavior and poor initial decision-making before converging toward effective defense strategies.\n  In this work, we investigate the use of a Large Language Model (LLM) to improve autonomous defensive decision-m","authors_text":"Adrian Taylor, Fran\\c{c}ois Rivest, Konur Tholl, Mariam El Mezouar, Ranwa Al Mallah","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T20:28:02Z","title":"Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28826","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":"sha256:0adf398380713623e5bf2662b207f26cd3ef58f4ca60fe2863abc15f5c06189f","target":"record","created_at":"2026-08-03T01:16:53Z","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":"bedce908e84507fffafb809acf085410acf1e1f7f3a3389e95fdb171431ad05c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T20:28:02Z","title_canon_sha256":"6e246db40f2df5ab5564afab342e72b48cf133c4a9c79a509800f61a52a2f04b"},"schema_version":"1.0","source":{"id":"2607.28826","kind":"arxiv","version":1}},"canonical_sha256":"17e09fd2af99469b7124edad78f831a928143b72280bf1022bd952f1dc145b16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17e09fd2af99469b7124edad78f831a928143b72280bf1022bd952f1dc145b16","first_computed_at":"2026-08-03T01:16:53.745544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:16:53.745544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wt0Kta3yMtSwVM9f0paQ1daoJwhRswSACbzW5GuOglX/jFiYGW9yP+X8A0jb4mJM0XYM4q5M60ibB59vyaCiCQ==","signature_status":"signed_v1","signed_at":"2026-08-03T01:16:53.747217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0adf398380713623e5bf2662b207f26cd3ef58f4ca60fe2863abc15f5c06189f","sha256:9817f343586b29f98c85dd1c96a879ccc3fc9db18ffbcfe9c6de9c9f39a3413c","sha256:bb3b1d5cf508c31f802a5d8a8b7d6f9ad539bb64345901adf535fd97eff1413c"],"state_sha256":"d79eeea5b8158a59082c0dd7bc75d1b3760cfce5f3475ec66f2a53275b26dbc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOeYOFn8EsD39gd5aVdy3C5AVSFxftgaBhfiHYnVnVhV71Q7A3L1aTHKTh0JIjXAbQyRh04QT6ygyBxVPkJICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:06:46.697483Z","bundle_sha256":"80b742bd98efd52c1df72423f6c6ce1d8f647b3edc22cce50ab48ba089d0a53c"}}