{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DJMLZ423RT3HVMULN7K4UMGXEY","short_pith_number":"pith:DJMLZ423","schema_version":"1.0","canonical_sha256":"1a58bcf35b8cf67ab28b6fd5ca30d7261054324048ccff8c75d7c493db2d4d44","source":{"kind":"arxiv","id":"2504.12320","version":1},"attestation_state":"computed","paper":{"title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jennifer Haase, Paul H. P. Hanel, Sebastian Pokutta","submitted_at":"2025-04-10T19:18:56Z","abstract_excerpt":"Following the widespread adoption of ChatGPT in early 2023, numerous studies reported that large language models (LLMs) can match or even surpass human performance in creative tasks. However, it remains unclear whether LLMs have become more creative over time, and how consistent their creative output is. In this study, we evaluated 14 widely used LLMs -- including GPT-4, Claude, Llama, Grok, Mistral, and DeepSeek -- across two validated creativity assessments: the Divergent Association Task (DAT) and the Alternative Uses Task (AUT). Contrary to expectations, we found no evidence of increased c"},"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":"2504.12320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T19:18:56Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"bf3a87466bd5229568990894b64737b29632c718e98ee29c8ff5d2fcc5806783","abstract_canon_sha256":"1184c620203ca1cd1b1afe09cf791253ad2649de58288bbe7091b7a9de40ec74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:14.026681Z","signature_b64":"Yd+jb5viAgwCixA72vVhk3diF8xoYqMvhabvCNVyoX90R+3IXI0ffF2Zlh+lE9/uTIaQ/Pff9RrZ79Bun/HNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a58bcf35b8cf67ab28b6fd5ca30d7261054324048ccff8c75d7c493db2d4d44","last_reissued_at":"2026-07-05T10:50:14.026105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:14.026105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jennifer Haase, Paul H. P. Hanel, Sebastian Pokutta","submitted_at":"2025-04-10T19:18:56Z","abstract_excerpt":"Following the widespread adoption of ChatGPT in early 2023, numerous studies reported that large language models (LLMs) can match or even surpass human performance in creative tasks. However, it remains unclear whether LLMs have become more creative over time, and how consistent their creative output is. In this study, we evaluated 14 widely used LLMs -- including GPT-4, Claude, Llama, Grok, Mistral, and DeepSeek -- across two validated creativity assessments: the Divergent Association Task (DAT) and the Alternative Uses Task (AUT). Contrary to expectations, we found no evidence of increased c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12320","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/2504.12320/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":"2504.12320","created_at":"2026-07-05T10:50:14.026170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12320v1","created_at":"2026-07-05T10:50:14.026170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12320","created_at":"2026-07-05T10:50:14.026170+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJMLZ423RT3H","created_at":"2026-07-05T10:50:14.026170+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJMLZ423RT3HVMUL","created_at":"2026-07-05T10:50:14.026170+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJMLZ423","created_at":"2026-07-05T10:50:14.026170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10113","citing_title":"Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing","ref_index":204,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY","json":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY.json","graph_json":"https://pith.science/api/pith-number/DJMLZ423RT3HVMULN7K4UMGXEY/graph.json","events_json":"https://pith.science/api/pith-number/DJMLZ423RT3HVMULN7K4UMGXEY/events.json","paper":"https://pith.science/paper/DJMLZ423"},"agent_actions":{"view_html":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY","download_json":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY.json","view_paper":"https://pith.science/paper/DJMLZ423","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12320&json=true","fetch_graph":"https://pith.science/api/pith-number/DJMLZ423RT3HVMULN7K4UMGXEY/graph.json","fetch_events":"https://pith.science/api/pith-number/DJMLZ423RT3HVMULN7K4UMGXEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY/action/storage_attestation","attest_author":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY/action/author_attestation","sign_citation":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY/action/citation_signature","submit_replication":"https://pith.science/pith/DJMLZ423RT3HVMULN7K4UMGXEY/action/replication_record"}},"created_at":"2026-07-05T10:50:14.026170+00:00","updated_at":"2026-07-05T10:50:14.026170+00:00"}