{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S5CYRGCWC7XFWMRUC5VV5H7GTC","short_pith_number":"pith:S5CYRGCW","schema_version":"1.0","canonical_sha256":"974588985617ee5b3234176b5e9fe6989de04c23f5a89d0754d9d725cd589ce0","source":{"kind":"arxiv","id":"2505.24189","version":2},"attestation_state":"computed","paper":{"title":"Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Emily Chen, Jingfei Chen, Maggie Baird, Orlando Marquez Ayala, Patrice Bechard","submitted_at":"2025-05-30T03:59:35Z","abstract_excerpt":"Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster inference, lower costs -- may no longer be clear. In this work, we present evidence that, for domain-specific tasks that require structured outputs, SLMs still have a quality advantage. We compare fine-tuning an SLM against prompting LLMs on the task of generating low-code workflows in JSON form. We observe that while a good prompt can yield reasonable results,"},"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":"2505.24189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T03:59:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"624457a18721ef511891c3b6fb0cc2b9c85db577f11f06b18ea60da47f2f5b6e","abstract_canon_sha256":"990df23bbaf97e2644d7418ee9d0307f0a56f095be5d2c3daf43e798ff85cda9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:29.767181Z","signature_b64":"jIPZas2WJUt/XTAHDBLOMrPDo2nzcAmMdgLHGJoFxh+ByaBO0mLyQsbp1s/nb6d/pDCK07GclsQeslJadSw9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"974588985617ee5b3234176b5e9fe6989de04c23f5a89d0754d9d725cd589ce0","last_reissued_at":"2026-07-05T11:38:29.766681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:29.766681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Emily Chen, Jingfei Chen, Maggie Baird, Orlando Marquez Ayala, Patrice Bechard","submitted_at":"2025-05-30T03:59:35Z","abstract_excerpt":"Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster inference, lower costs -- may no longer be clear. In this work, we present evidence that, for domain-specific tasks that require structured outputs, SLMs still have a quality advantage. We compare fine-tuning an SLM against prompting LLMs on the task of generating low-code workflows in JSON form. We observe that while a good prompt can yield reasonable results,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24189","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/2505.24189/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":"2505.24189","created_at":"2026-07-05T11:38:29.766735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24189v2","created_at":"2026-07-05T11:38:29.766735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24189","created_at":"2026-07-05T11:38:29.766735+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5CYRGCWC7XF","created_at":"2026-07-05T11:38:29.766735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5CYRGCWC7XFWMRU","created_at":"2026-07-05T11:38:29.766735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5CYRGCW","created_at":"2026-07-05T11:38:29.766735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23695","citing_title":"Quantifying Prior Dominance in RAG Systems","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC","json":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC.json","graph_json":"https://pith.science/api/pith-number/S5CYRGCWC7XFWMRUC5VV5H7GTC/graph.json","events_json":"https://pith.science/api/pith-number/S5CYRGCWC7XFWMRUC5VV5H7GTC/events.json","paper":"https://pith.science/paper/S5CYRGCW"},"agent_actions":{"view_html":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC","download_json":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC.json","view_paper":"https://pith.science/paper/S5CYRGCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24189&json=true","fetch_graph":"https://pith.science/api/pith-number/S5CYRGCWC7XFWMRUC5VV5H7GTC/graph.json","fetch_events":"https://pith.science/api/pith-number/S5CYRGCWC7XFWMRUC5VV5H7GTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC/action/storage_attestation","attest_author":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC/action/author_attestation","sign_citation":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC/action/citation_signature","submit_replication":"https://pith.science/pith/S5CYRGCWC7XFWMRUC5VV5H7GTC/action/replication_record"}},"created_at":"2026-07-05T11:38:29.766735+00:00","updated_at":"2026-07-05T11:38:29.766735+00:00"}