{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VUZ23QA3UPCWC32OG64GOBGHPZ","short_pith_number":"pith:VUZ23QA3","schema_version":"1.0","canonical_sha256":"ad33adc01ba3c5616f4e37b86704c77e532a4cb4280375358a5ce0d189033a82","source":{"kind":"arxiv","id":"2309.12810","version":1},"attestation_state":"computed","paper":{"title":"StyloMetrix: An Open-Source Multilingual Tool for Representing Stylometric Vectors","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Nowakowski, Agnieszka Karli\\'nska, Anna Ko{\\l}os, Daria Stetsenko, Inez Okulska, Kinga G{\\l}\\k{a}bi\\'nska","submitted_at":"2023-09-22T11:53:47Z","abstract_excerpt":"This work aims to provide an overview on the open-source multilanguage tool called StyloMetrix. It offers stylometric text representations that cover various aspects of grammar, syntax and lexicon. StyloMetrix covers four languages: Polish as the primary language, English, Ukrainian and Russian. The normalized output of each feature can become a fruitful course for machine learning models and a valuable addition to the embeddings layer for any deep learning algorithm. We strive to provide a concise, but exhaustive overview on the application of the StyloMetrix vectors as well as explain the se"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.12810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-22T11:53:47Z","cross_cats_sorted":[],"title_canon_sha256":"078f44907aa05e5095d632d9cd496b07bc3ed4c3b44a88f401c9ee42c6222602","abstract_canon_sha256":"30526d5d37d43838a05284dfe90a9ef7f410944b7aee27696dba5951da01d85a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:18.154198Z","signature_b64":"aH3DFjcEgP5HukIG8lNldcnZRoGlN36J51Zp8dxsmJ7SQjMImdWQzoga/l/PKtBEoHn1wgpTOV2K6susSVmrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad33adc01ba3c5616f4e37b86704c77e532a4cb4280375358a5ce0d189033a82","last_reissued_at":"2026-07-05T06:53:18.153718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:18.153718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyloMetrix: An Open-Source Multilingual Tool for Representing Stylometric Vectors","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Nowakowski, Agnieszka Karli\\'nska, Anna Ko{\\l}os, Daria Stetsenko, Inez Okulska, Kinga G{\\l}\\k{a}bi\\'nska","submitted_at":"2023-09-22T11:53:47Z","abstract_excerpt":"This work aims to provide an overview on the open-source multilanguage tool called StyloMetrix. It offers stylometric text representations that cover various aspects of grammar, syntax and lexicon. StyloMetrix covers four languages: Polish as the primary language, English, Ukrainian and Russian. The normalized output of each feature can become a fruitful course for machine learning models and a valuable addition to the embeddings layer for any deep learning algorithm. We strive to provide a concise, but exhaustive overview on the application of the StyloMetrix vectors as well as explain the se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12810","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.12810/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.12810","created_at":"2026-07-05T06:53:18.153774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.12810v1","created_at":"2026-07-05T06:53:18.153774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12810","created_at":"2026-07-05T06:53:18.153774+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUZ23QA3UPCW","created_at":"2026-07-05T06:53:18.153774+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUZ23QA3UPCWC32O","created_at":"2026-07-05T06:53:18.153774+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUZ23QA3","created_at":"2026-07-05T06:53:18.153774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.03465","citing_title":"Tuning for TraceTarnish: Techniques, Trends, and Testing Tangible Traits","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04925","citing_title":"Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ","json":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ.json","graph_json":"https://pith.science/api/pith-number/VUZ23QA3UPCWC32OG64GOBGHPZ/graph.json","events_json":"https://pith.science/api/pith-number/VUZ23QA3UPCWC32OG64GOBGHPZ/events.json","paper":"https://pith.science/paper/VUZ23QA3"},"agent_actions":{"view_html":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ","download_json":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ.json","view_paper":"https://pith.science/paper/VUZ23QA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.12810&json=true","fetch_graph":"https://pith.science/api/pith-number/VUZ23QA3UPCWC32OG64GOBGHPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VUZ23QA3UPCWC32OG64GOBGHPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ/action/storage_attestation","attest_author":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ/action/author_attestation","sign_citation":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ/action/citation_signature","submit_replication":"https://pith.science/pith/VUZ23QA3UPCWC32OG64GOBGHPZ/action/replication_record"}},"created_at":"2026-07-05T06:53:18.153774+00:00","updated_at":"2026-07-05T06:53:18.153774+00:00"}