{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BSCGZIVI3Y2CVZUKSGR7GP5767","short_pith_number":"pith:BSCGZIVI","schema_version":"1.0","canonical_sha256":"0c846ca2a8de342ae68a91a3f33fbff7f35c750acf70cb8e0d4da74fc85744d7","source":{"kind":"arxiv","id":"2409.11547","version":2},"attestation_state":"computed","paper":{"title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guillermo Marco, Julio Gonzalo, Luz Rello","submitted_at":"2024-09-17T20:40:02Z","abstract_excerpt":"In this paper, we evaluate the creative fiction writing abilities of a fine-tuned small language model (SLM), BART-large, and compare its performance to human writers and two large language models (LLMs): GPT-3.5 and GPT-4o. Our evaluation consists of two experiments: (i) a human study in which 68 participants rated short stories from humans and the SLM on grammaticality, relevance, creativity, and attractiveness, and (ii) a qualitative linguistic analysis examining the textual characteristics of stories produced by each model. In the first experiment, BART-large outscored average human writer"},"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":"2409.11547","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T20:40:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e7e945d838a942e97893363c2228b7f1b99f5741f9caf9c42929b3f8f3b8189","abstract_canon_sha256":"7f1ff3a4f74e1034c20b5a635e08e7d1081e32defdf59ed79814d3d4871272c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:17.590710Z","signature_b64":"9He0PjDO9YXmZFpWXpt2gqWw9oXgKDkI9BcoSXrNhyl9SUwTuaLOyD4Ivk5Iy97gdz+iDCDP9XRNbxbS1ypvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c846ca2a8de342ae68a91a3f33fbff7f35c750acf70cb8e0d4da74fc85744d7","last_reissued_at":"2026-07-05T11:15:17.590213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:17.590213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guillermo Marco, Julio Gonzalo, Luz Rello","submitted_at":"2024-09-17T20:40:02Z","abstract_excerpt":"In this paper, we evaluate the creative fiction writing abilities of a fine-tuned small language model (SLM), BART-large, and compare its performance to human writers and two large language models (LLMs): GPT-3.5 and GPT-4o. Our evaluation consists of two experiments: (i) a human study in which 68 participants rated short stories from humans and the SLM on grammaticality, relevance, creativity, and attractiveness, and (ii) a qualitative linguistic analysis examining the textual characteristics of stories produced by each model. In the first experiment, BART-large outscored average human writer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11547","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/2409.11547/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":"2409.11547","created_at":"2026-07-05T11:15:17.590271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11547v2","created_at":"2026-07-05T11:15:17.590271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11547","created_at":"2026-07-05T11:15:17.590271+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSCGZIVI3Y2C","created_at":"2026-07-05T11:15:17.590271+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSCGZIVI3Y2CVZUK","created_at":"2026-07-05T11:15:17.590271+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSCGZIVI","created_at":"2026-07-05T11:15:17.590271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20152","citing_title":"From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22748","citing_title":"AI Fiction in the Wild","ref_index":149,"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":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767","json":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767.json","graph_json":"https://pith.science/api/pith-number/BSCGZIVI3Y2CVZUKSGR7GP5767/graph.json","events_json":"https://pith.science/api/pith-number/BSCGZIVI3Y2CVZUKSGR7GP5767/events.json","paper":"https://pith.science/paper/BSCGZIVI"},"agent_actions":{"view_html":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767","download_json":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767.json","view_paper":"https://pith.science/paper/BSCGZIVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11547&json=true","fetch_graph":"https://pith.science/api/pith-number/BSCGZIVI3Y2CVZUKSGR7GP5767/graph.json","fetch_events":"https://pith.science/api/pith-number/BSCGZIVI3Y2CVZUKSGR7GP5767/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767/action/storage_attestation","attest_author":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767/action/author_attestation","sign_citation":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767/action/citation_signature","submit_replication":"https://pith.science/pith/BSCGZIVI3Y2CVZUKSGR7GP5767/action/replication_record"}},"created_at":"2026-07-05T11:15:17.590271+00:00","updated_at":"2026-07-05T11:15:17.590271+00:00"}