{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UAA565IIEYNRM3XTWB2N22HD3A","short_pith_number":"pith:UAA565II","schema_version":"1.0","canonical_sha256":"a001df7508261b166ef3b074dd68e3d8250556b37fb0507a128c3ac251c49612","source":{"kind":"arxiv","id":"2409.13843","version":2},"attestation_state":"computed","paper":{"title":"STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Robert Morabito, Sangmitra Madhusudan, Tyler McDonald","submitted_at":"2024-09-20T18:34:38Z","abstract_excerpt":"Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the broader context or the spectrum of potential biases within each situation. To address this, we introduce the Sensitivity Testing on Offensive Progressions (STOP) dataset, which includes 450 offensive progressions containing 2,700 unique sentences of varying severity that progressively escalate from less to more explicitly offensive. Covering a broad spectrum o"},"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":"2409.13843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T18:34:38Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"39e9f1aa7c4a0ed4360a9d78e0fb5be349b7bff22d616d10525b8af82c40142d","abstract_canon_sha256":"2de4f87f96f056cafa61ed2ecde604b1f06ac072a7a3c91aee98d7fc8d5291cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:53.618891Z","signature_b64":"z712T+EzZRBZoBEA5g0pIhRPzuNy7uUF/CoxvdkCBpRlzAglGR/+dxqdi4sFPq5nsmHgvjG7gdpEEnwAMz0hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a001df7508261b166ef3b074dd68e3d8250556b37fb0507a128c3ac251c49612","last_reissued_at":"2026-07-05T10:08:53.618466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:53.618466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Robert Morabito, Sangmitra Madhusudan, Tyler McDonald","submitted_at":"2024-09-20T18:34:38Z","abstract_excerpt":"Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the broader context or the spectrum of potential biases within each situation. To address this, we introduce the Sensitivity Testing on Offensive Progressions (STOP) dataset, which includes 450 offensive progressions containing 2,700 unique sentences of varying severity that progressively escalate from less to more explicitly offensive. Covering a broad spectrum o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13843","kind":"arxiv","version":2},"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/2409.13843/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":"2409.13843","created_at":"2026-07-05T10:08:53.618520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13843v2","created_at":"2026-07-05T10:08:53.618520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13843","created_at":"2026-07-05T10:08:53.618520+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAA565IIEYNR","created_at":"2026-07-05T10:08:53.618520+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAA565IIEYNRM3XT","created_at":"2026-07-05T10:08:53.618520+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAA565II","created_at":"2026-07-05T10:08:53.618520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03993","citing_title":"Words of Warmth: Trust and Sociability Norms for over 26k English Words","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A","json":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A.json","graph_json":"https://pith.science/api/pith-number/UAA565IIEYNRM3XTWB2N22HD3A/graph.json","events_json":"https://pith.science/api/pith-number/UAA565IIEYNRM3XTWB2N22HD3A/events.json","paper":"https://pith.science/paper/UAA565II"},"agent_actions":{"view_html":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A","download_json":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A.json","view_paper":"https://pith.science/paper/UAA565II","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13843&json=true","fetch_graph":"https://pith.science/api/pith-number/UAA565IIEYNRM3XTWB2N22HD3A/graph.json","fetch_events":"https://pith.science/api/pith-number/UAA565IIEYNRM3XTWB2N22HD3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A/action/storage_attestation","attest_author":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A/action/author_attestation","sign_citation":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A/action/citation_signature","submit_replication":"https://pith.science/pith/UAA565IIEYNRM3XTWB2N22HD3A/action/replication_record"}},"created_at":"2026-07-05T10:08:53.618520+00:00","updated_at":"2026-07-05T10:08:53.618520+00:00"}