{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LLWA536D63MJCUMC2RYMP4R2SK","short_pith_number":"pith:LLWA536D","schema_version":"1.0","canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","source":{"kind":"arxiv","id":"2507.12064","version":1},"attestation_state":"computed","paper":{"title":"StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jeremi K. Ochab, Mateusz Matias, Tomasz Walkowiak, Tymoteusz Boba","submitted_at":"2025-07-16T09:21:20Z","abstract_excerpt":"This submission to the binary AI detection task is based on a modular stylometric pipeline, where: public spaCy models are used for text preprocessing (including tokenisation, named entity recognition, dependency parsing, part-of-speech tagging, and morphology annotation) and extracting several thousand features (frequencies of n-grams of the above linguistic annotations); light-gradient boosting machines are used as the classifier. We collect a large corpus of more than 500 000 machine-generated texts for the classifier's training. We explore several parameter options to increase the classifi"},"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":"2507.12064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T09:21:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f35b16c63e7af3c9f206f6d88a62287eb562d79609233e680e5973b2751da14d","abstract_canon_sha256":"b10b63cf64ec20e00c1e28ad8f63a7b53717ab9bec448f5382d39170bf0e04ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:13.837437Z","signature_b64":"aswpljN6xImehA66Eoh+djvzOCW2RyX1uhCisvqVPAU82lkbXgiTSUmc7JLhW6u7JHOJnVZcTNOcYWce2d6WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","last_reissued_at":"2026-07-05T11:38:13.836966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:13.836966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jeremi K. Ochab, Mateusz Matias, Tomasz Walkowiak, Tymoteusz Boba","submitted_at":"2025-07-16T09:21:20Z","abstract_excerpt":"This submission to the binary AI detection task is based on a modular stylometric pipeline, where: public spaCy models are used for text preprocessing (including tokenisation, named entity recognition, dependency parsing, part-of-speech tagging, and morphology annotation) and extracting several thousand features (frequencies of n-grams of the above linguistic annotations); light-gradient boosting machines are used as the classifier. We collect a large corpus of more than 500 000 machine-generated texts for the classifier's training. We explore several parameter options to increase the classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12064","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/2507.12064/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":"2507.12064","created_at":"2026-07-05T11:38:13.837034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12064v1","created_at":"2026-07-05T11:38:13.837034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12064","created_at":"2026-07-05T11:38:13.837034+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLWA536D63MJ","created_at":"2026-07-05T11:38:13.837034+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLWA536D63MJCUMC","created_at":"2026-07-05T11:38:13.837034+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLWA536D","created_at":"2026-07-05T11:38:13.837034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK","json":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK.json","graph_json":"https://pith.science/api/pith-number/LLWA536D63MJCUMC2RYMP4R2SK/graph.json","events_json":"https://pith.science/api/pith-number/LLWA536D63MJCUMC2RYMP4R2SK/events.json","paper":"https://pith.science/paper/LLWA536D"},"agent_actions":{"view_html":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK","download_json":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK.json","view_paper":"https://pith.science/paper/LLWA536D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12064&json=true","fetch_graph":"https://pith.science/api/pith-number/LLWA536D63MJCUMC2RYMP4R2SK/graph.json","fetch_events":"https://pith.science/api/pith-number/LLWA536D63MJCUMC2RYMP4R2SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/action/storage_attestation","attest_author":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/action/author_attestation","sign_citation":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/action/citation_signature","submit_replication":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/action/replication_record"}},"created_at":"2026-07-05T11:38:13.837034+00:00","updated_at":"2026-07-05T11:38:13.837034+00:00"}