{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A2NPDYYX4HDS4QF5H62BO3DWH3","short_pith_number":"pith:A2NPDYYX","schema_version":"1.0","canonical_sha256":"069af1e317e1c72e40bd3fb4176c763ec9932a4a75f3be5a2f04149975a1e9d8","source":{"kind":"arxiv","id":"2505.09056","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brandon Smith, Mohamed Reda Bouadjenek, Phillip Dawson, Sunil Aryal, Tahsin Alamgir Kheya","submitted_at":"2025-05-14T01:21:46Z","abstract_excerpt":"Large Language Models (LLMs) represent a major step toward artificial general intelligence, significantly advancing our ability to interact with technology. While LLMs perform well on Natural Language Processing tasks -- such as translation, generation, code writing, and summarization -- questions remain about their output similarity, variability, and ethical implications. For instance, how similar are texts generated by the same model? How does this compare across different models? And which models best uphold ethical standards? To investigate, we used 5{,}000 prompts spanning diverse tasks l"},"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":"2505.09056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-14T01:21:46Z","cross_cats_sorted":[],"title_canon_sha256":"fd229ec25b85d4fb8ea51064561edd8d3e165af9267eedd6c86337daf0e35e7d","abstract_canon_sha256":"141c59e0c1e296aebc5b28d2915411195d66b5798d9ed123e8a4200520b09271"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:49.578137Z","signature_b64":"rmTM13FZF77xWapnvufjyJlBYBFpM7kF3nbWyIzEzBJpeYcj6Dq/Af9BhbZkfQKO1XbEd2bsVii+iKtQCZW+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"069af1e317e1c72e40bd3fb4176c763ec9932a4a75f3be5a2f04149975a1e9d8","last_reissued_at":"2026-07-05T11:02:49.577554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:49.577554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brandon Smith, Mohamed Reda Bouadjenek, Phillip Dawson, Sunil Aryal, Tahsin Alamgir Kheya","submitted_at":"2025-05-14T01:21:46Z","abstract_excerpt":"Large Language Models (LLMs) represent a major step toward artificial general intelligence, significantly advancing our ability to interact with technology. While LLMs perform well on Natural Language Processing tasks -- such as translation, generation, code writing, and summarization -- questions remain about their output similarity, variability, and ethical implications. For instance, how similar are texts generated by the same model? How does this compare across different models? And which models best uphold ethical standards? To investigate, we used 5{,}000 prompts spanning diverse tasks l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09056","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/2505.09056/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":"2505.09056","created_at":"2026-07-05T11:02:49.577627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09056v1","created_at":"2026-07-05T11:02:49.577627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09056","created_at":"2026-07-05T11:02:49.577627+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2NPDYYX4HDS","created_at":"2026-07-05T11:02:49.577627+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2NPDYYX4HDS4QF5","created_at":"2026-07-05T11:02:49.577627+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2NPDYYX","created_at":"2026-07-05T11:02:49.577627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01233","citing_title":"Measuring the Gap Between Human and LLM Research Ideas","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06540","citing_title":"Ex Ante Evaluation of AI-Induced Idea Diversity Collapse","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18038","citing_title":"First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3","json":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3.json","graph_json":"https://pith.science/api/pith-number/A2NPDYYX4HDS4QF5H62BO3DWH3/graph.json","events_json":"https://pith.science/api/pith-number/A2NPDYYX4HDS4QF5H62BO3DWH3/events.json","paper":"https://pith.science/paper/A2NPDYYX"},"agent_actions":{"view_html":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3","download_json":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3.json","view_paper":"https://pith.science/paper/A2NPDYYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09056&json=true","fetch_graph":"https://pith.science/api/pith-number/A2NPDYYX4HDS4QF5H62BO3DWH3/graph.json","fetch_events":"https://pith.science/api/pith-number/A2NPDYYX4HDS4QF5H62BO3DWH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3/action/storage_attestation","attest_author":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3/action/author_attestation","sign_citation":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3/action/citation_signature","submit_replication":"https://pith.science/pith/A2NPDYYX4HDS4QF5H62BO3DWH3/action/replication_record"}},"created_at":"2026-07-05T11:02:49.577627+00:00","updated_at":"2026-07-05T11:02:49.577627+00:00"}