{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ULBKL7V6B2FTPVT2GVBY37GJLQ","short_pith_number":"pith:ULBKL7V6","canonical_record":{"source":{"id":"2302.02463","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-05T19:15:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea10abc153baa772b465a6b97cdf1f4c0c9f9b15489919eb9b3e3e66c1751993","abstract_canon_sha256":"5d50965c70a035c6dc8c8e8a0c4342272cce43daaff37e03cb50cf52f2e6af38"},"schema_version":"1.0"},"canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","source":{"kind":"arxiv","id":"2302.02463","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02463","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02463v3","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02463","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"ULBKL7V6B2FT","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"pith_short_16","alias_value":"ULBKL7V6B2FTPVT2","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"pith_short_8","alias_value":"ULBKL7V6","created_at":"2026-07-05T05:41:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ULBKL7V6B2FTPVT2GVBY37GJLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02463","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-05T19:15:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea10abc153baa772b465a6b97cdf1f4c0c9f9b15489919eb9b3e3e66c1751993","abstract_canon_sha256":"5d50965c70a035c6dc8c8e8a0c4342272cce43daaff37e03cb50cf52f2e6af38"},"schema_version":"1.0"},"canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:52.209196Z","signature_b64":"Un1Ur0l2OkvY7LxD6fzjnTLQ69gTonBCVzqyu94ku7mdFa/4aV6LtzAa1uOZH66y2QVO8YkWklrovXdEaSGfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","last_reissued_at":"2026-07-05T05:41:52.208789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:52.208789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02463","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzmMNhZfSmuSbcSeBYSZUx1anRjHdh3TVq5JCJ5L8QQkgP+8KnXh9tdJ1kWBBHbEXdV3BVDvxsjpSfb5QXPpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:53.473644Z"},"content_sha256":"bef04de57cc688aeb3f5d1895dea602df2b8a5724f118b45ddf4aba26b6e940c","schema_version":"1.0","event_id":"sha256:bef04de57cc688aeb3f5d1895dea602df2b8a5724f118b45ddf4aba26b6e940c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ULBKL7V6B2FTPVT2GVBY37GJLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nationality Bias in Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pranav Narayanan Venkit, Ruchi Panchanadikar, Sanjana Gautam, Shomir Wilson, Ting-Hao 'Kenneth' Huang","submitted_at":"2023-02-05T19:15:33Z","abstract_excerpt":"Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02463","kind":"arxiv","version":3},"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/2302.02463/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ducjj702QIyuPyoB8rDkaxtAxll+GXwxoqcheQJUUXwd0Di5QTWBC8/u/W+0qaSD7dyK+bqxIwhL6Kmr8ttaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:53.474276Z"},"content_sha256":"89afe32b0d9fc9a1d99ad98a6ef635c77d066aec6502dbb9e9eb7cf64799e52a","schema_version":"1.0","event_id":"sha256:89afe32b0d9fc9a1d99ad98a6ef635c77d066aec6502dbb9e9eb7cf64799e52a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/bundle.json","state_url":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T05:01:53Z","links":{"resolver":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ","bundle":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/bundle.json","state":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ULBKL7V6B2FTPVT2GVBY37GJLQ","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":"5d50965c70a035c6dc8c8e8a0c4342272cce43daaff37e03cb50cf52f2e6af38","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-05T19:15:33Z","title_canon_sha256":"ea10abc153baa772b465a6b97cdf1f4c0c9f9b15489919eb9b3e3e66c1751993"},"schema_version":"1.0","source":{"id":"2302.02463","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02463","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02463v3","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02463","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"ULBKL7V6B2FT","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"pith_short_16","alias_value":"ULBKL7V6B2FTPVT2","created_at":"2026-07-05T05:41:52Z"},{"alias_kind":"pith_short_8","alias_value":"ULBKL7V6","created_at":"2026-07-05T05:41:52Z"}],"graph_snapshots":[{"event_id":"sha256:89afe32b0d9fc9a1d99ad98a6ef635c77d066aec6502dbb9e9eb7cf64799e52a","target":"graph","created_at":"2026-07-05T05:41:52Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.02463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore th","authors_text":"Pranav Narayanan Venkit, Ruchi Panchanadikar, Sanjana Gautam, Shomir Wilson, Ting-Hao 'Kenneth' Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-05T19:15:33Z","title":"Nationality Bias in Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02463","kind":"arxiv","version":3},"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:bef04de57cc688aeb3f5d1895dea602df2b8a5724f118b45ddf4aba26b6e940c","target":"record","created_at":"2026-07-05T05:41:52Z","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":"5d50965c70a035c6dc8c8e8a0c4342272cce43daaff37e03cb50cf52f2e6af38","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-05T19:15:33Z","title_canon_sha256":"ea10abc153baa772b465a6b97cdf1f4c0c9f9b15489919eb9b3e3e66c1751993"},"schema_version":"1.0","source":{"id":"2302.02463","kind":"arxiv","version":3}},"canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","first_computed_at":"2026-07-05T05:41:52.208789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:41:52.208789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Un1Ur0l2OkvY7LxD6fzjnTLQ69gTonBCVzqyu94ku7mdFa/4aV6LtzAa1uOZH66y2QVO8YkWklrovXdEaSGfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:41:52.209196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02463","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bef04de57cc688aeb3f5d1895dea602df2b8a5724f118b45ddf4aba26b6e940c","sha256:89afe32b0d9fc9a1d99ad98a6ef635c77d066aec6502dbb9e9eb7cf64799e52a"],"state_sha256":"117835bbaa9c4d4e33fa62ba8dc884634181e1e472db7793f806421e2d3e4ef4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tK2t++tQG2panPRhmD9WKAU7Ct03FUG6vaIhMwVxGEtG1HPE29NdyxaAjljSPr1t/3qIBbN4FejWb+8DqLMCDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:01:53.476869Z","bundle_sha256":"f3034f8c71777c007cee7f555513916ffac55c60f6384f36934f74e53b0d8ebd"}}