{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QMPMT4CUCVR6OVIOLNF3PQRYSO","short_pith_number":"pith:QMPMT4CU","schema_version":"1.0","canonical_sha256":"831ec9f0541563e7550e5b4bb7c2389385f38c554a259b6f4171adc2d7ed4ce6","source":{"kind":"arxiv","id":"2506.05388","version":1},"attestation_state":"computed","paper":{"title":"taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Matthias A{\\ss}enmacher, Stefanie Urchs, Stephanie Thiemichen, Veronika Thurner","submitted_at":"2025-06-03T16:24:33Z","abstract_excerpt":"Open-access corpora are essential for advancing natural language processing (NLP) and computational social science (CSS). However, large-scale resources for German remain limited, restricting research on linguistic trends and societal issues such as gender bias. We present taz2024full, the largest publicly available corpus of German newspaper articles to date, comprising over 1.8 million texts from taz, spanning 1980 to 2024.\n  As a demonstration of the corpus's utility for bias and discrimination research, we analyse gender representation across four decades of reporting. We find a consistent"},"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":"2506.05388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"a6bf226cc662afc912dad99cdd8df98c1048d450458e853c7121eaa5a2b26f6b","abstract_canon_sha256":"da9856ea392a1c364d611abb21de608bf5ce0baadb22b1273a60083d6d5cc06a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:01.820040Z","signature_b64":"cZelUaswRUnMNkJl0LWdk/plouauCu6ExYSUdSr+Ea1NYYaQYxzwNCToDtd6dTFsZzwLLZyqdjZgHt8/bUpIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"831ec9f0541563e7550e5b4bb7c2389385f38c554a259b6f4171adc2d7ed4ce6","last_reissued_at":"2026-07-05T11:17:01.819579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:01.819579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Matthias A{\\ss}enmacher, Stefanie Urchs, Stephanie Thiemichen, Veronika Thurner","submitted_at":"2025-06-03T16:24:33Z","abstract_excerpt":"Open-access corpora are essential for advancing natural language processing (NLP) and computational social science (CSS). However, large-scale resources for German remain limited, restricting research on linguistic trends and societal issues such as gender bias. We present taz2024full, the largest publicly available corpus of German newspaper articles to date, comprising over 1.8 million texts from taz, spanning 1980 to 2024.\n  As a demonstration of the corpus's utility for bias and discrimination research, we analyse gender representation across four decades of reporting. We find a consistent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05388","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/2506.05388/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":"2506.05388","created_at":"2026-07-05T11:17:01.819637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05388v1","created_at":"2026-07-05T11:17:01.819637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05388","created_at":"2026-07-05T11:17:01.819637+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMPMT4CUCVR6","created_at":"2026-07-05T11:17:01.819637+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMPMT4CUCVR6OVIO","created_at":"2026-07-05T11:17:01.819637+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMPMT4CU","created_at":"2026-07-05T11:17:01.819637+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/QMPMT4CUCVR6OVIOLNF3PQRYSO","json":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO.json","graph_json":"https://pith.science/api/pith-number/QMPMT4CUCVR6OVIOLNF3PQRYSO/graph.json","events_json":"https://pith.science/api/pith-number/QMPMT4CUCVR6OVIOLNF3PQRYSO/events.json","paper":"https://pith.science/paper/QMPMT4CU"},"agent_actions":{"view_html":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO","download_json":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO.json","view_paper":"https://pith.science/paper/QMPMT4CU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05388&json=true","fetch_graph":"https://pith.science/api/pith-number/QMPMT4CUCVR6OVIOLNF3PQRYSO/graph.json","fetch_events":"https://pith.science/api/pith-number/QMPMT4CUCVR6OVIOLNF3PQRYSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO/action/storage_attestation","attest_author":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO/action/author_attestation","sign_citation":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO/action/citation_signature","submit_replication":"https://pith.science/pith/QMPMT4CUCVR6OVIOLNF3PQRYSO/action/replication_record"}},"created_at":"2026-07-05T11:17:01.819637+00:00","updated_at":"2026-07-05T11:17:01.819637+00:00"}