{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HFKNGNZUZ52HCJRAP32J7L6YU7","short_pith_number":"pith:HFKNGNZU","schema_version":"1.0","canonical_sha256":"3954d33734cf747126207ef49fafd8a7e43bf367f5851211328f298c9bb2f77f","source":{"kind":"arxiv","id":"2410.04197","version":1},"attestation_state":"computed","paper":{"title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Atmakuru, Anirudh Lakkaraju, Hamed Zamani, Haw-Shiuan Chang, Jatin Nainani, Rohith Siddhartha Reddy Bheemreddy, Zonghai Yao","submitted_at":"2024-10-05T15:22:36Z","abstract_excerpt":"Evaluating the creativity of large language models (LLMs) in story writing is difficult because LLM-generated stories could seemingly look creative but be very similar to some existing stories in their huge and proprietary training corpus. To overcome this challenge, we introduce a novel benchmark dataset with varying levels of prompt specificity: CS4 ($\\mathbf{C}$omparing the $\\mathbf{S}$kill of $\\mathbf{C}$reating $\\mathbf{S}$tories by $\\mathbf{C}$ontrolling the $\\mathbf{S}$ynthesized $\\mathbf{C}$onstraint $\\mathbf{S}$pecificity). By increasing the number of requirements/constraints in the p"},"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":"2410.04197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T15:22:36Z","cross_cats_sorted":[],"title_canon_sha256":"834977cef82afd3d3d147b63b0d7097346462bcacdc3a32e8695a2663a7acc40","abstract_canon_sha256":"de840ce30238438e7d148e84f33382f5440d9e24cdcf16ce98ccb3de2def2386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:30.631883Z","signature_b64":"UWkO9fW5jkbqIVM2JtFlMDe1n7SCwKV1emS3kPmwio8ekYZVn8Z1NnnJMltXYuaQ/NXYLMPLvzephqU3Bqp+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3954d33734cf747126207ef49fafd8a7e43bf367f5851211328f298c9bb2f77f","last_reissued_at":"2026-07-05T09:16:30.631395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:30.631395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Atmakuru, Anirudh Lakkaraju, Hamed Zamani, Haw-Shiuan Chang, Jatin Nainani, Rohith Siddhartha Reddy Bheemreddy, Zonghai Yao","submitted_at":"2024-10-05T15:22:36Z","abstract_excerpt":"Evaluating the creativity of large language models (LLMs) in story writing is difficult because LLM-generated stories could seemingly look creative but be very similar to some existing stories in their huge and proprietary training corpus. To overcome this challenge, we introduce a novel benchmark dataset with varying levels of prompt specificity: CS4 ($\\mathbf{C}$omparing the $\\mathbf{S}$kill of $\\mathbf{C}$reating $\\mathbf{S}$tories by $\\mathbf{C}$ontrolling the $\\mathbf{S}$ynthesized $\\mathbf{C}$onstraint $\\mathbf{S}$pecificity). By increasing the number of requirements/constraints in the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04197","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/2410.04197/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":"2410.04197","created_at":"2026-07-05T09:16:30.631464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04197v1","created_at":"2026-07-05T09:16:30.631464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04197","created_at":"2026-07-05T09:16:30.631464+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFKNGNZUZ52H","created_at":"2026-07-05T09:16:30.631464+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFKNGNZUZ52HCJRA","created_at":"2026-07-05T09:16:30.631464+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFKNGNZU","created_at":"2026-07-05T09:16:30.631464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":201,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23206","citing_title":"High-quality generation of dynamic game content via small language models: A proof of concept","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08503","citing_title":"NARRA-Gym for Evaluating Interactive Narrative Agents","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18031","citing_title":"How Creative Are Large Language Models in Generating Molecules?","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7","json":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7.json","graph_json":"https://pith.science/api/pith-number/HFKNGNZUZ52HCJRAP32J7L6YU7/graph.json","events_json":"https://pith.science/api/pith-number/HFKNGNZUZ52HCJRAP32J7L6YU7/events.json","paper":"https://pith.science/paper/HFKNGNZU"},"agent_actions":{"view_html":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7","download_json":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7.json","view_paper":"https://pith.science/paper/HFKNGNZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04197&json=true","fetch_graph":"https://pith.science/api/pith-number/HFKNGNZUZ52HCJRAP32J7L6YU7/graph.json","fetch_events":"https://pith.science/api/pith-number/HFKNGNZUZ52HCJRAP32J7L6YU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7/action/storage_attestation","attest_author":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7/action/author_attestation","sign_citation":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7/action/citation_signature","submit_replication":"https://pith.science/pith/HFKNGNZUZ52HCJRAP32J7L6YU7/action/replication_record"}},"created_at":"2026-07-05T09:16:30.631464+00:00","updated_at":"2026-07-05T09:16:30.631464+00:00"}