{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CYJVJAOZYXW44JOQWNORCYVOVM","short_pith_number":"pith:CYJVJAOZ","schema_version":"1.0","canonical_sha256":"16135481d9c5edce25d0b35d1162aeab19d4daaafed39921ba299e3c4b4bb0bf","source":{"kind":"arxiv","id":"2508.18466","version":1},"attestation_state":"computed","paper":{"title":"Integrating gender inclusivity into large language models via instruction tuning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Wr\\'oblewska, Bartosz \\.Zuk","submitted_at":"2025-08-25T20:34:59Z","abstract_excerpt":"Imagine a language with masculine, feminine, and neuter grammatical genders, yet, due to historical and political conventions, masculine forms are predominantly used to refer to men, women and mixed-gender groups. This is the reality of contemporary Polish. A social consequence of this unfair linguistic system is that large language models (LLMs) trained on Polish texts inherit and reinforce this masculine bias, generating gender-imbalanced outputs. This study addresses this issue by tuning LLMs using the IPIS dataset, a collection of human-crafted gender-inclusive proofreading in Polish and P"},"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":"2508.18466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T20:34:59Z","cross_cats_sorted":[],"title_canon_sha256":"18f94d7463fea7d95b525c7d29c71a3ea923550b25e646bf9feec95910c686d8","abstract_canon_sha256":"bbc716579ef3482e759ba77fdae0018c75b5879b8df0980fe323f0317f0cf42b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:24.965049Z","signature_b64":"GYVXW0Ycz7IUG/LaGO6fK1UUyLTtkkmjiN7eFNWOKxZBSUvL5bZyXIiug49ZrjQzcvoIKO1r5IblSisaFa4vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16135481d9c5edce25d0b35d1162aeab19d4daaafed39921ba299e3c4b4bb0bf","last_reissued_at":"2026-07-05T11:59:24.964604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:24.964604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating gender inclusivity into large language models via instruction tuning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Wr\\'oblewska, Bartosz \\.Zuk","submitted_at":"2025-08-25T20:34:59Z","abstract_excerpt":"Imagine a language with masculine, feminine, and neuter grammatical genders, yet, due to historical and political conventions, masculine forms are predominantly used to refer to men, women and mixed-gender groups. This is the reality of contemporary Polish. A social consequence of this unfair linguistic system is that large language models (LLMs) trained on Polish texts inherit and reinforce this masculine bias, generating gender-imbalanced outputs. This study addresses this issue by tuning LLMs using the IPIS dataset, a collection of human-crafted gender-inclusive proofreading in Polish and P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18466","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/2508.18466/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":"2508.18466","created_at":"2026-07-05T11:59:24.964667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18466v1","created_at":"2026-07-05T11:59:24.964667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18466","created_at":"2026-07-05T11:59:24.964667+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYJVJAOZYXW4","created_at":"2026-07-05T11:59:24.964667+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYJVJAOZYXW44JOQ","created_at":"2026-07-05T11:59:24.964667+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYJVJAOZ","created_at":"2026-07-05T11:59:24.964667+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/CYJVJAOZYXW44JOQWNORCYVOVM","json":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM.json","graph_json":"https://pith.science/api/pith-number/CYJVJAOZYXW44JOQWNORCYVOVM/graph.json","events_json":"https://pith.science/api/pith-number/CYJVJAOZYXW44JOQWNORCYVOVM/events.json","paper":"https://pith.science/paper/CYJVJAOZ"},"agent_actions":{"view_html":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM","download_json":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM.json","view_paper":"https://pith.science/paper/CYJVJAOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18466&json=true","fetch_graph":"https://pith.science/api/pith-number/CYJVJAOZYXW44JOQWNORCYVOVM/graph.json","fetch_events":"https://pith.science/api/pith-number/CYJVJAOZYXW44JOQWNORCYVOVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM/action/storage_attestation","attest_author":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM/action/author_attestation","sign_citation":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM/action/citation_signature","submit_replication":"https://pith.science/pith/CYJVJAOZYXW44JOQWNORCYVOVM/action/replication_record"}},"created_at":"2026-07-05T11:59:24.964667+00:00","updated_at":"2026-07-05T11:59:24.964667+00:00"}