{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VVG6IIJZFANEZVQKTHGZ5VYIUD","short_pith_number":"pith:VVG6IIJZ","canonical_record":{"source":{"id":"2507.13870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T12:47:20Z","cross_cats_sorted":[],"title_canon_sha256":"e8acd0b5a1587010128eb331290152e8a6465ba2bcfb8355319275458aa9e230","abstract_canon_sha256":"5a536d81ae7cdc492354a24ea97889428e94ea3b80c0a72b92e6b7febf20face"},"schema_version":"1.0"},"canonical_sha256":"ad4de42139281a4cd60a99cd9ed708a0dd9129c6de709c27d8249330698aa15c","source":{"kind":"arxiv","id":"2507.13870","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13870","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13870v2","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13870","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"VVG6IIJZFANE","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"pith_short_16","alias_value":"VVG6IIJZFANEZVQK","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"pith_short_8","alias_value":"VVG6IIJZ","created_at":"2026-07-05T12:02:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VVG6IIJZFANEZVQKTHGZ5VYIUD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T12:47:20Z","cross_cats_sorted":[],"title_canon_sha256":"e8acd0b5a1587010128eb331290152e8a6465ba2bcfb8355319275458aa9e230","abstract_canon_sha256":"5a536d81ae7cdc492354a24ea97889428e94ea3b80c0a72b92e6b7febf20face"},"schema_version":"1.0"},"canonical_sha256":"ad4de42139281a4cd60a99cd9ed708a0dd9129c6de709c27d8249330698aa15c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:03.726170Z","signature_b64":"tR4iFaDPstncIteMiysfgF6WdlqmFt/9i9/TUbluIqrHDNXUizLZ6or6IDY+vwSnrBByfByYHTZjgW9uugW2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad4de42139281a4cd60a99cd9ed708a0dd9129c6de709c27d8249330698aa15c","last_reissued_at":"2026-07-05T12:02:03.725519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:03.725519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13870","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":"2026-07-05T12:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dchhzRZ4dvmbsZDVqcJTMp3nc0BgJ9MNOZWOId/eCgqNRv770KhwnSDUwGPtpp/fawUJ5ufRJNKW0OHYEe2FBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:23:10.670772Z"},"content_sha256":"b43770f3d347b83af5cf7930a49d68e1be4456e0062c22a17858241c40d3f07f","schema_version":"1.0","event_id":"sha256:b43770f3d347b83af5cf7930a49d68e1be4456e0062c22a17858241c40d3f07f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VVG6IIJZFANEZVQKTHGZ5VYIUD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Label Unification for Cross-Dataset Generalization in Cybersecurity NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Johan Hausted Schmidt, Maciej Jalocha, William Michelseen","submitted_at":"2025-07-18T12:47:20Z","abstract_excerpt":"The field of cybersecurity NER lacks standardized labels, making it challenging to combine datasets. We investigate label unification across four cybersecurity datasets to increase data resource usability. We perform a coarse-grained label unification and conduct pairwise cross-dataset evaluations using BiLSTM models. Qualitative analysis of predictions reveals errors, limitations, and dataset differences. To address unification limitations, we propose alternative architectures including a multihead model and a graph-based transfer model. Results show that models trained on unified datasets ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13870","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/2507.13870/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":"2026-07-05T12:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qN7BpgB5U4GBg9bimJkUatbCyyhJmrLL7U9klQmV8um4YzDDg/I7ZsQ4FipzjaGNWiYZhBBoGG9JsCEP4WtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:23:10.671330Z"},"content_sha256":"0ee5eb6a13464db2e4a7ce3d099a9ec2fec3709e2cd753d53f4aa8ed3c05110a","schema_version":"1.0","event_id":"sha256:0ee5eb6a13464db2e4a7ce3d099a9ec2fec3709e2cd753d53f4aa8ed3c05110a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD/bundle.json","state_url":"https://pith.science/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD/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":"2026-08-07T01:23:10Z","links":{"resolver":"https://pith.science/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD","bundle":"https://pith.science/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD/bundle.json","state":"https://pith.science/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVG6IIJZFANEZVQKTHGZ5VYIUD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VVG6IIJZFANEZVQKTHGZ5VYIUD","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":"5a536d81ae7cdc492354a24ea97889428e94ea3b80c0a72b92e6b7febf20face","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T12:47:20Z","title_canon_sha256":"e8acd0b5a1587010128eb331290152e8a6465ba2bcfb8355319275458aa9e230"},"schema_version":"1.0","source":{"id":"2507.13870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13870","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13870v2","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13870","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"VVG6IIJZFANE","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"pith_short_16","alias_value":"VVG6IIJZFANEZVQK","created_at":"2026-07-05T12:02:03Z"},{"alias_kind":"pith_short_8","alias_value":"VVG6IIJZ","created_at":"2026-07-05T12:02:03Z"}],"graph_snapshots":[{"event_id":"sha256:0ee5eb6a13464db2e4a7ce3d099a9ec2fec3709e2cd753d53f4aa8ed3c05110a","target":"graph","created_at":"2026-07-05T12:02:03Z","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/2507.13870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of cybersecurity NER lacks standardized labels, making it challenging to combine datasets. We investigate label unification across four cybersecurity datasets to increase data resource usability. We perform a coarse-grained label unification and conduct pairwise cross-dataset evaluations using BiLSTM models. Qualitative analysis of predictions reveals errors, limitations, and dataset differences. To address unification limitations, we propose alternative architectures including a multihead model and a graph-based transfer model. Results show that models trained on unified datasets ge","authors_text":"Johan Hausted Schmidt, Maciej Jalocha, William Michelseen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T12:47:20Z","title":"Label Unification for Cross-Dataset Generalization in Cybersecurity NER"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13870","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:b43770f3d347b83af5cf7930a49d68e1be4456e0062c22a17858241c40d3f07f","target":"record","created_at":"2026-07-05T12:02:03Z","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":"5a536d81ae7cdc492354a24ea97889428e94ea3b80c0a72b92e6b7febf20face","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T12:47:20Z","title_canon_sha256":"e8acd0b5a1587010128eb331290152e8a6465ba2bcfb8355319275458aa9e230"},"schema_version":"1.0","source":{"id":"2507.13870","kind":"arxiv","version":2}},"canonical_sha256":"ad4de42139281a4cd60a99cd9ed708a0dd9129c6de709c27d8249330698aa15c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad4de42139281a4cd60a99cd9ed708a0dd9129c6de709c27d8249330698aa15c","first_computed_at":"2026-07-05T12:02:03.725519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:03.725519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tR4iFaDPstncIteMiysfgF6WdlqmFt/9i9/TUbluIqrHDNXUizLZ6or6IDY+vwSnrBByfByYHTZjgW9uugW2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:03.726170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b43770f3d347b83af5cf7930a49d68e1be4456e0062c22a17858241c40d3f07f","sha256:0ee5eb6a13464db2e4a7ce3d099a9ec2fec3709e2cd753d53f4aa8ed3c05110a"],"state_sha256":"ce98fcfe3b44e5e70fcbc749fb23a4653a3fc6a0086d9418957766ae3def1888"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q3eLNhGmzoonawg4oTlTYDIfwEzER0mq/6ohwbzDQ8YZRBLJR4AKY8CTZt4+u0iZNOz82acKdCjluORv3VNvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:23:10.674822Z","bundle_sha256":"2a39b2536613bbd4c9df55ac0e8f177b571c185d8890229a285eef2493b46374"}}