{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:22CZB7EXDDJQXNNXF2WHNWPHAM","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":"10e1f90ef1ba4fcd2177c975365fcdd39efe0a02ec2404f453657094a0bc2502","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-03-15T05:35:02Z","title_canon_sha256":"63389ddd4356c609a8beeb055eb3e5a2878497bb6ca84510428a10b8ede9d2bb"},"schema_version":"1.0","source":{"id":"2403.10576","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10576","created_at":"2026-07-05T08:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10576v2","created_at":"2026-07-05T08:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10576","created_at":"2026-07-05T08:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"22CZB7EXDDJQ","created_at":"2026-07-05T08:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"22CZB7EXDDJQXNNX","created_at":"2026-07-05T08:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"22CZB7EX","created_at":"2026-07-05T08:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:304bc024a1c97ece07da09887153237f4007cc32531acf98e23fba9461cc9108","target":"graph","created_at":"2026-07-05T08:03:11Z","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/2403.10576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cybersecurity information is often technically complex and relayed through unstructured text, making automation of cyber threat intelligence highly challenging. For such text domains that involve high levels of expertise, pretraining on in-domain corpora has been a popular method for language models to obtain domain expertise. However, cybersecurity texts often contain non-linguistic elements (such as URLs and hash values) that could be unsuitable with the established pretraining methodologies. Previous work in other domains have removed or filtered such text as noise, but the effectiveness of","authors_text":"Dayeon Yim, Eugene Jang, Jian Cui, Jin-Woo Chung, Seungwon Shin, Yongjae Lee, Youngjin Jin","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-03-15T05:35:02Z","title":"Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10576","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":"sha256:15aec6ac6487ff95eda864a6d25f6f75f4683be32839df1375dbaa89bbcc6edb","target":"record","created_at":"2026-07-05T08:03:11Z","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":"10e1f90ef1ba4fcd2177c975365fcdd39efe0a02ec2404f453657094a0bc2502","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-03-15T05:35:02Z","title_canon_sha256":"63389ddd4356c609a8beeb055eb3e5a2878497bb6ca84510428a10b8ede9d2bb"},"schema_version":"1.0","source":{"id":"2403.10576","kind":"arxiv","version":2}},"canonical_sha256":"d68590fc9718d30bb5b72eac76d9e7032ca3bc870cc2d8a2390735260924ed7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d68590fc9718d30bb5b72eac76d9e7032ca3bc870cc2d8a2390735260924ed7c","first_computed_at":"2026-07-05T08:03:11.096932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:11.096932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bm7DPaAnynHGdRZODvWj6w/2zSFSFlI5ScpvkxU7HYYqd3JjnhDYkRrc3phSLT6K+N7sPvZkKntKoHENmCyeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:11.097355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10576","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15aec6ac6487ff95eda864a6d25f6f75f4683be32839df1375dbaa89bbcc6edb","sha256:304bc024a1c97ece07da09887153237f4007cc32531acf98e23fba9461cc9108"],"state_sha256":"728c0cfd57d1615d7e75685983740eeb6cd13bce334af657dac867db8c89daee"}