{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NFT4R4KH74MQKD4DPUZJ2WE7RV","short_pith_number":"pith:NFT4R4KH","canonical_record":{"source":{"id":"2605.17530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-17T16:30:06Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NI"],"title_canon_sha256":"dadbfb3a66013feedc36369d437a01ac4634f2822aceb8cc7694400594c8ba19","abstract_canon_sha256":"1d7b9da98baf9f635bfe7964f0dbf4e0fb8a4387572e9a7d2cee7bde4cec3efd"},"schema_version":"1.0"},"canonical_sha256":"6967c8f147ff19050f837d329d589f8d481e3f95b729cf65a509448d38ed2be3","source":{"kind":"arxiv","id":"2605.17530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17530","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17530v1","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17530","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"NFT4R4KH74MQ","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"NFT4R4KH74MQKD4D","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"NFT4R4KH","created_at":"2026-05-20T00:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NFT4R4KH74MQKD4DPUZJ2WE7RV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-17T16:30:06Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NI"],"title_canon_sha256":"dadbfb3a66013feedc36369d437a01ac4634f2822aceb8cc7694400594c8ba19","abstract_canon_sha256":"1d7b9da98baf9f635bfe7964f0dbf4e0fb8a4387572e9a7d2cee7bde4cec3efd"},"schema_version":"1.0"},"canonical_sha256":"6967c8f147ff19050f837d329d589f8d481e3f95b729cf65a509448d38ed2be3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:44.289017Z","signature_b64":"0CuhpkO4cT4jhIIKrvm4orTakQEVMGfx/qMlNGw/M45y2luqn784FJYo0gi482Fq5Jx+YuhEWkw9C6bqzmdQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6967c8f147ff19050f837d329d589f8d481e3f95b729cf65a509448d38ed2be3","last_reissued_at":"2026-05-20T00:04:44.288205Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:44.288205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17530","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":"2026-05-20T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymCJTO7KdcjiIdqIWm2c8UqiX+kq+pO4zzG3FTxXUjXGlWra4PacqvW8sVx1kMoDtqzNiVGYcSxDdv0/9TQoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:58:27.190199Z"},"content_sha256":"bc488d2a9f9cd53a7c002b00030b1aae820b9b72367cca4b6d16907215cfeba4","schema_version":"1.0","event_id":"sha256:bc488d2a9f9cd53a7c002b00030b1aae820b9b72367cca4b6d16907215cfeba4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NFT4R4KH74MQKD4DPUZJ2WE7RV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-Shot Network Intrusion Detection Using Online Triplet Mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A triplet network with online mining and KNN classification detects intrusions competitively after training on only ten malicious samples per class.","cross_cats":["cs.AI","cs.LG","cs.NI"],"primary_cat":"cs.CR","authors_text":"Christos Tachtatzis, Hanan Hindy, Jack Wilkie, Miroslav Bures, Robert Atkinson","submitted_at":"2026-05-17T16:30:06Z","abstract_excerpt":"Network intrusion detection systems play a vital role in protecting networks by detecting malicious network traffic which can then be investigated by a cybersecurity operations centre. State-of-the-art approaches utilise supervised machine learning methods to train a classification model to recognise known cyberattacks; however, these models require a large labelled dataset to train and show poor performance when trained on smaller datasets. In an attempt to address this shortcoming, anomaly detection models learn the distribution of benign traffic and flag non-conforming traffic as malicious."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the proposed approach was found to be competitive with existing methods when trained on as little as 10 malicious samples of each class.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the learned embeddings from the triplet network with online mining will form clusters separable by KNN even when trained on very small numbers of malicious samples from network traffic datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A triplet network using online triplet mining and KNN classifier achieves competitive few-shot performance on network intrusion detection with as few as 10 malicious samples per class.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A triplet network with online mining and KNN classification detects intrusions competitively after training on only ten malicious samples per class.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"896f032ddd9e46901be99b8374124cbe658c239bda0e245cef6eb59d4c9a0492"},"source":{"id":"2605.17530","kind":"arxiv","version":1},"verdict":{"id":"fa05e57c-785f-4c05-879f-4d149f8cf198","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T23:03:28.511118Z","strongest_claim":"the proposed approach was found to be competitive with existing methods when trained on as little as 10 malicious samples of each class.","one_line_summary":"A triplet network using online triplet mining and KNN classifier achieves competitive few-shot performance on network intrusion detection with as few as 10 malicious samples per class.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the learned embeddings from the triplet network with online mining will form clusters separable by KNN even when trained on very small numbers of malicious samples from network traffic datasets.","pith_extraction_headline":"A triplet network with online mining and KNN classification detects intrusions competitively after training on only ten malicious samples per class."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17530/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:19.860505Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:11:39.245345Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.619553Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.558413Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"15b5e0985836c34165379f288d2daf5af0f5c8c51956a90e43bcf921bb3d99ee"},"references":{"count":39,"sample":[{"doi":"","year":2022,"title":"Corporation, I.Cost of a Data Breach Report 2022; Technical Report; IBM Security: Cambridge, MA, USA, 2022","work_id":"4ee081ab-a271-4275-b302-94b1e0dd3aef","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/access.2019.2925828","year":2019,"title":"An optimization method for intrusion detection classification model based on deep belief network.IEEE Access2019,7, 87593–87605","work_id":"c0c236fa-24b7-4cf2-a8d0-28493272efd6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/access.2019.2904620","year":2019,"title":"An Intrusion Detection Model Based on Feature Reduction and Convolutional Neural Networks.IEEE Access2019,7, 42210–42219","work_id":"afe0393a-dde6-4152-93ff-f6d75e3930cf","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"A CNN-LSTM Model for Intrusion Detection System from High Dimensional Data.J","work_id":"2a047728-384c-4453-b2f2-d3f34b12db21","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Learning a Neural-network-based Representation for Open Set Recognition","work_id":"3bfbbb86-5b02-495a-b23f-7cad92a3ad62","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"123e45f6c57b00df95454b8872e125745f662e317551627b6433ef0cbe62007b","internal_anchors":3},"formal_canon":{"evidence_count":1,"snapshot_sha256":"6ba23195726099660d76e597e0367f0f4879052b655b7230f5d5d58aaae25978"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"fa05e57c-785f-4c05-879f-4d149f8cf198"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCGU6XEhyh1d4vFDZx2BIX6uYsQb7ygi7gLxwQObpBn9VgnEPKsD7J7aT/RBIeF4UpXK8ujND0x0OMZKWe5FCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:58:27.191174Z"},"content_sha256":"a81337337ceea48b5cf59a670dc430d9835a1a5f096606e5803f4d9824fe7a9b","schema_version":"1.0","event_id":"sha256:a81337337ceea48b5cf59a670dc430d9835a1a5f096606e5803f4d9824fe7a9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV/bundle.json","state_url":"https://pith.science/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV/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":"2026-05-26T00:58:27Z","links":{"resolver":"https://pith.science/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV","bundle":"https://pith.science/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV/bundle.json","state":"https://pith.science/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFT4R4KH74MQKD4DPUZJ2WE7RV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NFT4R4KH74MQKD4DPUZJ2WE7RV","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":"1d7b9da98baf9f635bfe7964f0dbf4e0fb8a4387572e9a7d2cee7bde4cec3efd","cross_cats_sorted":["cs.AI","cs.LG","cs.NI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-17T16:30:06Z","title_canon_sha256":"dadbfb3a66013feedc36369d437a01ac4634f2822aceb8cc7694400594c8ba19"},"schema_version":"1.0","source":{"id":"2605.17530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17530","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17530v1","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17530","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"NFT4R4KH74MQ","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"NFT4R4KH74MQKD4D","created_at":"2026-05-20T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"NFT4R4KH","created_at":"2026-05-20T00:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:a81337337ceea48b5cf59a670dc430d9835a1a5f096606e5803f4d9824fe7a9b","target":"graph","created_at":"2026-05-20T00:04:44Z","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":"the proposed approach was found to be competitive with existing methods when trained on as little as 10 malicious samples of each class."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the learned embeddings from the triplet network with online mining will form clusters separable by KNN even when trained on very small numbers of malicious samples from network traffic datasets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A triplet network using online triplet mining and KNN classifier achieves competitive few-shot performance on network intrusion detection with as few as 10 malicious samples per class."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A triplet network with online mining and KNN classification detects intrusions competitively after training on only ten malicious samples per class."}],"snapshot_sha256":"896f032ddd9e46901be99b8374124cbe658c239bda0e245cef6eb59d4c9a0492"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"6ba23195726099660d76e597e0367f0f4879052b655b7230f5d5d58aaae25978"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:19.860505Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:11:39.245345Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.619553Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.558413Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17530/integrity.json","findings":[],"snapshot_sha256":"15b5e0985836c34165379f288d2daf5af0f5c8c51956a90e43bcf921bb3d99ee","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Network intrusion detection systems play a vital role in protecting networks by detecting malicious network traffic which can then be investigated by a cybersecurity operations centre. State-of-the-art approaches utilise supervised machine learning methods to train a classification model to recognise known cyberattacks; however, these models require a large labelled dataset to train and show poor performance when trained on smaller datasets. In an attempt to address this shortcoming, anomaly detection models learn the distribution of benign traffic and flag non-conforming traffic as malicious.","authors_text":"Christos Tachtatzis, Hanan Hindy, Jack Wilkie, Miroslav Bures, Robert Atkinson","cross_cats":["cs.AI","cs.LG","cs.NI"],"headline":"A triplet network with online mining and KNN classification detects intrusions competitively after training on only ten malicious samples per class.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-17T16:30:06Z","title":"Few-Shot Network Intrusion Detection Using Online Triplet Mining"},"references":{"count":39,"internal_anchors":3,"resolved_work":39,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Corporation, I.Cost of a Data Breach Report 2022; Technical Report; IBM Security: Cambridge, MA, USA, 2022","work_id":"4ee081ab-a271-4275-b302-94b1e0dd3aef","year":2022},{"cited_arxiv_id":"","doi":"10.1109/access.2019.2925828","is_internal_anchor":false,"ref_index":2,"title":"An optimization method for intrusion detection classification model based on deep belief network.IEEE Access2019,7, 87593–87605","work_id":"c0c236fa-24b7-4cf2-a8d0-28493272efd6","year":2019},{"cited_arxiv_id":"","doi":"10.1109/access.2019.2904620","is_internal_anchor":false,"ref_index":3,"title":"An Intrusion Detection Model Based on Feature Reduction and Convolutional Neural Networks.IEEE Access2019,7, 42210–42219","work_id":"afe0393a-dde6-4152-93ff-f6d75e3930cf","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A CNN-LSTM Model for Intrusion Detection System from High Dimensional Data.J","work_id":"2a047728-384c-4453-b2f2-d3f34b12db21","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Learning a Neural-network-based Representation for Open Set Recognition","work_id":"3bfbbb86-5b02-495a-b23f-7cad92a3ad62","year":2020}],"snapshot_sha256":"123e45f6c57b00df95454b8872e125745f662e317551627b6433ef0cbe62007b"},"source":{"id":"2605.17530","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:03:28.511118Z","id":"fa05e57c-785f-4c05-879f-4d149f8cf198","model_set":{"reader":"grok-4.3"},"one_line_summary":"A triplet network using online triplet mining and KNN classifier achieves competitive few-shot performance on network intrusion detection with as few as 10 malicious samples per class.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A triplet network with online mining and KNN classification detects intrusions competitively after training on only ten malicious samples per class.","strongest_claim":"the proposed approach was found to be competitive with existing methods when trained on as little as 10 malicious samples of each class.","weakest_assumption":"That the learned embeddings from the triplet network with online mining will form clusters separable by KNN even when trained on very small numbers of malicious samples from network traffic datasets."}},"verdict_id":"fa05e57c-785f-4c05-879f-4d149f8cf198"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bc488d2a9f9cd53a7c002b00030b1aae820b9b72367cca4b6d16907215cfeba4","target":"record","created_at":"2026-05-20T00:04:44Z","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":"1d7b9da98baf9f635bfe7964f0dbf4e0fb8a4387572e9a7d2cee7bde4cec3efd","cross_cats_sorted":["cs.AI","cs.LG","cs.NI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-17T16:30:06Z","title_canon_sha256":"dadbfb3a66013feedc36369d437a01ac4634f2822aceb8cc7694400594c8ba19"},"schema_version":"1.0","source":{"id":"2605.17530","kind":"arxiv","version":1}},"canonical_sha256":"6967c8f147ff19050f837d329d589f8d481e3f95b729cf65a509448d38ed2be3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6967c8f147ff19050f837d329d589f8d481e3f95b729cf65a509448d38ed2be3","first_computed_at":"2026-05-20T00:04:44.288205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:44.288205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0CuhpkO4cT4jhIIKrvm4orTakQEVMGfx/qMlNGw/M45y2luqn784FJYo0gi482Fq5Jx+YuhEWkw9C6bqzmdQBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:44.289017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc488d2a9f9cd53a7c002b00030b1aae820b9b72367cca4b6d16907215cfeba4","sha256:a81337337ceea48b5cf59a670dc430d9835a1a5f096606e5803f4d9824fe7a9b"],"state_sha256":"1954b8f15831a8cf37c0da2a7ef39b12072e12adbf3e0a1e54fa67ba524feae2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/h14F82kYT71cHDLif+gIZdusjgCo/iNEAgqBdwjS774/RpIZglpU2nQn6yRIcPgkFhla3N2Eaad5O9jXslVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:58:27.195396Z","bundle_sha256":"7f0283fb2085cd1e061ba8c0b9a097d753b03cfcc1511f157627dd2bb3744608"}}