{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AW3IRFU45RVAWSKVZBCL3TRMSG","short_pith_number":"pith:AW3IRFU4","canonical_record":{"source":{"id":"1803.07292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-03-20T08:32:56Z","cross_cats_sorted":[],"title_canon_sha256":"346582f94500b82ae697b916814905bcaaebfca1ea7be15785601b644fa851ac","abstract_canon_sha256":"c0687ee42069ff3c7443e6cbaca3b7f19d3a2b2b27de9618f5fcf83cb328da55"},"schema_version":"1.0"},"canonical_sha256":"05b688969cec6a0b4955c844bdce2c9186d0b5f8e108d86bcd70724d62f14ad6","source":{"kind":"arxiv","id":"1803.07292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07292","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07292v1","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07292","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"pith_short_12","alias_value":"AW3IRFU45RVA","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AW3IRFU45RVAWSKV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AW3IRFU4","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AW3IRFU45RVAWSKVZBCL3TRMSG","target":"record","payload":{"canonical_record":{"source":{"id":"1803.07292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-03-20T08:32:56Z","cross_cats_sorted":[],"title_canon_sha256":"346582f94500b82ae697b916814905bcaaebfca1ea7be15785601b644fa851ac","abstract_canon_sha256":"c0687ee42069ff3c7443e6cbaca3b7f19d3a2b2b27de9618f5fcf83cb328da55"},"schema_version":"1.0"},"canonical_sha256":"05b688969cec6a0b4955c844bdce2c9186d0b5f8e108d86bcd70724d62f14ad6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:33.729928Z","signature_b64":"al4GvGSFqqngiWwYvtdz2AWxSlIv2FNznWLu/PfqHUJMgA1D9DjNKRxFV/1c8et/6kjO++Txv+2aJbrMCLtICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05b688969cec6a0b4955c844bdce2c9186d0b5f8e108d86bcd70724d62f14ad6","last_reissued_at":"2026-05-18T00:20:33.729439Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:33.729439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.07292","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":"2026-05-18T00:20:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kc9Y/HnYf9r7Y96UuotS58apaif9FYsRl1zkZpDbVox053MwwUAmhiB579sINC5pmx2ldv4ZKH5iFGiqfkOPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:15:02.090092Z"},"content_sha256":"26a70a489ed70ed7bee84cd56cc1ab7ac427fb74819d759673e6c34aad73e207","schema_version":"1.0","event_id":"sha256:26a70a489ed70ed7bee84cd56cc1ab7ac427fb74819d759673e6c34aad73e207"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AW3IRFU45RVAWSKVZBCL3TRMSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language or Not (NLoN) - A Package for Software Engineering Text Analysis Pipeline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fabio Calefato, Maelick Claes, Mika V. M\\\"antyl\\\"a","submitted_at":"2018-03-20T08:32:56Z","abstract_excerpt":"The use of natural language processing (NLP) is gaining popularity in software engineering. In order to correctly perform NLP, we must pre-process the textual information to separate natural language from other information, such as log messages, that are often part of the communication in software engineering. We present a simple approach for classifying whether some textual input is natural language or not. Although our NLoN package relies on only 11 language features and character tri-grams, we are able to achieve an area under the ROC curve performances between 0.976-0.987 on three differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07292","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":""},"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":"2026-05-18T00:20:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QEkJZ3bWl70yCQBwT3rnQovh/jkHmlDGtFuFwjnLBemixFLY0F6IhjIuAX+qLWVaggFE44it0snGgNccQGlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:15:02.090545Z"},"content_sha256":"a3df1be3bb4e65174c73495d27b9b40353468c38ff06a3de0fa87710a1aa5a38","schema_version":"1.0","event_id":"sha256:a3df1be3bb4e65174c73495d27b9b40353468c38ff06a3de0fa87710a1aa5a38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AW3IRFU45RVAWSKVZBCL3TRMSG/bundle.json","state_url":"https://pith.science/pith/AW3IRFU45RVAWSKVZBCL3TRMSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AW3IRFU45RVAWSKVZBCL3TRMSG/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":"2026-08-21T22:15:02Z","links":{"resolver":"https://pith.science/pith/AW3IRFU45RVAWSKVZBCL3TRMSG","bundle":"https://pith.science/pith/AW3IRFU45RVAWSKVZBCL3TRMSG/bundle.json","state":"https://pith.science/pith/AW3IRFU45RVAWSKVZBCL3TRMSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AW3IRFU45RVAWSKVZBCL3TRMSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AW3IRFU45RVAWSKVZBCL3TRMSG","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":"c0687ee42069ff3c7443e6cbaca3b7f19d3a2b2b27de9618f5fcf83cb328da55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-03-20T08:32:56Z","title_canon_sha256":"346582f94500b82ae697b916814905bcaaebfca1ea7be15785601b644fa851ac"},"schema_version":"1.0","source":{"id":"1803.07292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07292","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07292v1","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07292","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"pith_short_12","alias_value":"AW3IRFU45RVA","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AW3IRFU45RVAWSKV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AW3IRFU4","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:a3df1be3bb4e65174c73495d27b9b40353468c38ff06a3de0fa87710a1aa5a38","target":"graph","created_at":"2026-05-18T00:20:33Z","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"},"paper":{"abstract_excerpt":"The use of natural language processing (NLP) is gaining popularity in software engineering. In order to correctly perform NLP, we must pre-process the textual information to separate natural language from other information, such as log messages, that are often part of the communication in software engineering. We present a simple approach for classifying whether some textual input is natural language or not. Although our NLoN package relies on only 11 language features and character tri-grams, we are able to achieve an area under the ROC curve performances between 0.976-0.987 on three differen","authors_text":"Fabio Calefato, Maelick Claes, Mika V. M\\\"antyl\\\"a","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-03-20T08:32:56Z","title":"Natural Language or Not (NLoN) - A Package for Software Engineering Text Analysis Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07292","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":"sha256:26a70a489ed70ed7bee84cd56cc1ab7ac427fb74819d759673e6c34aad73e207","target":"record","created_at":"2026-05-18T00:20:33Z","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":"c0687ee42069ff3c7443e6cbaca3b7f19d3a2b2b27de9618f5fcf83cb328da55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-03-20T08:32:56Z","title_canon_sha256":"346582f94500b82ae697b916814905bcaaebfca1ea7be15785601b644fa851ac"},"schema_version":"1.0","source":{"id":"1803.07292","kind":"arxiv","version":1}},"canonical_sha256":"05b688969cec6a0b4955c844bdce2c9186d0b5f8e108d86bcd70724d62f14ad6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05b688969cec6a0b4955c844bdce2c9186d0b5f8e108d86bcd70724d62f14ad6","first_computed_at":"2026-05-18T00:20:33.729439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:33.729439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"al4GvGSFqqngiWwYvtdz2AWxSlIv2FNznWLu/PfqHUJMgA1D9DjNKRxFV/1c8et/6kjO++Txv+2aJbrMCLtICg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:33.729928Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.07292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26a70a489ed70ed7bee84cd56cc1ab7ac427fb74819d759673e6c34aad73e207","sha256:a3df1be3bb4e65174c73495d27b9b40353468c38ff06a3de0fa87710a1aa5a38"],"state_sha256":"711f948b7d7cadbd9d1a06d7674eef07bb0e8ab43a3f2a80c4ab339e7d4070f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jF1kfwcvQgjF7lOO3zUYQq4p64v2DQBxcKA7oNqLadV0u5NrkAKdLPmgphOBvKZr8HwA5XOynp08E3y6qiJmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:15:02.094220Z","bundle_sha256":"f4c3598507af11a8e6c4421d3515f7070aa059ccbf79973161bfb1f786bd85cd"}}