{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:BRP7RICLYHYTHQFUV47R6CV75G","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":"ceb466bfc2b6b5e4ad3ace58536874e036bc0409ac25fc5ae933eb874a1c5176","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-28T15:06:50Z","title_canon_sha256":"a94b26c6e11f7776820560a5b56bb218087e24b2d2d548e2f2b31bf76e35b0cb"},"schema_version":"1.0","source":{"id":"1408.6746","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.6746","created_at":"2026-05-18T02:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"1408.6746v2","created_at":"2026-05-18T02:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.6746","created_at":"2026-05-18T02:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"BRP7RICLYHYT","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"BRP7RICLYHYTHQFU","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"BRP7RICL","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:059f12d163d9903eda1ec22521543126639fdf81167e910034aac7624692aef2","target":"graph","created_at":"2026-05-18T02:35:47Z","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":"This paper presents categorization of Croatian texts using Non-Standard Words (NSW) as features. Non-Standard Words are: numbers, dates, acronyms, abbreviations, currency, etc. NSWs in Croatian language are determined according to Croatian NSW taxonomy. For the purpose of this research, 390 text documents were collected and formed the SKIPEZ collection with 6 classes: official, literary, informative, popular, educational and scientific. Text categorization experiment was conducted on three different representations of the SKIPEZ collection: in the first representation, the frequencies of NSWs ","authors_text":"Sanda Martin\\v{c}i\\'c-Ip\\v{s}i\\'c, Slobodan Beliga","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-28T15:06:50Z","title":"Non-Standard Words as Features for Text Categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.6746","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":"sha256:28580ccaed226ec43086e5d1a1cdef24f0fadfc96ef8c5116b8377c2cc346673","target":"record","created_at":"2026-05-18T02:35:47Z","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":"ceb466bfc2b6b5e4ad3ace58536874e036bc0409ac25fc5ae933eb874a1c5176","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-28T15:06:50Z","title_canon_sha256":"a94b26c6e11f7776820560a5b56bb218087e24b2d2d548e2f2b31bf76e35b0cb"},"schema_version":"1.0","source":{"id":"1408.6746","kind":"arxiv","version":2}},"canonical_sha256":"0c5ff8a04bc1f133c0b4af3f1f0abfe9a3b65dd3bede0115f62edc48efd48e66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c5ff8a04bc1f133c0b4af3f1f0abfe9a3b65dd3bede0115f62edc48efd48e66","first_computed_at":"2026-05-18T02:35:47.012148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:35:47.012148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EtxfHj7FO6sNffvPntnT6/luQsVUW39/eXXvulxUO9A2ZXE8P0CEn5GZVm6b/dAwX+IwjuMDTH2o2+mSJPu3Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:35:47.012594Z","signed_message":"canonical_sha256_bytes"},"source_id":"1408.6746","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28580ccaed226ec43086e5d1a1cdef24f0fadfc96ef8c5116b8377c2cc346673","sha256:059f12d163d9903eda1ec22521543126639fdf81167e910034aac7624692aef2"],"state_sha256":"ebf1032f60c86bdf10e4bd40872051ceb209d3bbdfeccee488b06541a3dbbac1"}