{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7KPAY4BHWPBSK2PNEO3JRLX4YU","short_pith_number":"pith:7KPAY4BH","schema_version":"1.0","canonical_sha256":"fa9e0c7027b3c32569ed23b698aefcc502537c6746ac819b9268efc04ed13b78","source":{"kind":"arxiv","id":"2506.05614","version":1},"attestation_state":"computed","paper":{"title":"Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"David Freitas, Eduardo Almeida, E. G. Santana Jr, Gabriel Benjamin, Harrison Santos, Iftekhar Ahmed, Jiawei Li, Jina Chun, Melissa Araujo, Paulo Anselmo da M. S. Neto","submitted_at":"2025-06-05T21:58:44Z","abstract_excerpt":"A growing variety of prompt engineering techniques has been proposed for Large Language Models (LLMs), yet systematic evaluation of each technique on individual software engineering (SE) tasks remains underexplored. In this study, we present a systematic evaluation of 14 established prompt techniques across 10 SE tasks using four LLM models. As identified in the prior literature, the selected prompting techniques span six core dimensions (Zero-Shot, Few-Shot, Thought Generation, Ensembling, Self-Criticism, and Decomposition). They are evaluated on tasks such as code generation, bug fixing, and"},"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":"2506.05614","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-05T21:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"188dfc8f9ed6079d0ff8d5252bc1eadb7c7213540a01a39c78536f8394e5e4e4","abstract_canon_sha256":"034fb7af6db007b8af96e8fd75488afb9fe23d2131e7d45dc653b11f5cfc11b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:06.952098Z","signature_b64":"q4f8buiLBBchiC4XbOI2yy9jWJPEQuZp+ELYy9G5NNZzevWXbOvBRtlxRnNtuTLpzzBhTHcs2l1obuu0n0MPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa9e0c7027b3c32569ed23b698aefcc502537c6746ac819b9268efc04ed13b78","last_reissued_at":"2026-07-05T11:17:06.951560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:06.951560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"David Freitas, Eduardo Almeida, E. G. Santana Jr, Gabriel Benjamin, Harrison Santos, Iftekhar Ahmed, Jiawei Li, Jina Chun, Melissa Araujo, Paulo Anselmo da M. S. Neto","submitted_at":"2025-06-05T21:58:44Z","abstract_excerpt":"A growing variety of prompt engineering techniques has been proposed for Large Language Models (LLMs), yet systematic evaluation of each technique on individual software engineering (SE) tasks remains underexplored. In this study, we present a systematic evaluation of 14 established prompt techniques across 10 SE tasks using four LLM models. As identified in the prior literature, the selected prompting techniques span six core dimensions (Zero-Shot, Few-Shot, Thought Generation, Ensembling, Self-Criticism, and Decomposition). They are evaluated on tasks such as code generation, bug fixing, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05614","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/2506.05614/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":"2506.05614","created_at":"2026-07-05T11:17:06.951641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05614v1","created_at":"2026-07-05T11:17:06.951641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05614","created_at":"2026-07-05T11:17:06.951641+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KPAY4BHWPBS","created_at":"2026-07-05T11:17:06.951641+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KPAY4BHWPBSK2PN","created_at":"2026-07-05T11:17:06.951641+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KPAY4BH","created_at":"2026-07-05T11:17:06.951641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00049","citing_title":"Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00048","citing_title":"Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31002","citing_title":"Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22202","citing_title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10477","citing_title":"PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26615","citing_title":"TDD Governance for Multi-Agent Code Generation via Prompt Engineering","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU","json":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU.json","graph_json":"https://pith.science/api/pith-number/7KPAY4BHWPBSK2PNEO3JRLX4YU/graph.json","events_json":"https://pith.science/api/pith-number/7KPAY4BHWPBSK2PNEO3JRLX4YU/events.json","paper":"https://pith.science/paper/7KPAY4BH"},"agent_actions":{"view_html":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU","download_json":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU.json","view_paper":"https://pith.science/paper/7KPAY4BH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05614&json=true","fetch_graph":"https://pith.science/api/pith-number/7KPAY4BHWPBSK2PNEO3JRLX4YU/graph.json","fetch_events":"https://pith.science/api/pith-number/7KPAY4BHWPBSK2PNEO3JRLX4YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU/action/storage_attestation","attest_author":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU/action/author_attestation","sign_citation":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU/action/citation_signature","submit_replication":"https://pith.science/pith/7KPAY4BHWPBSK2PNEO3JRLX4YU/action/replication_record"}},"created_at":"2026-07-05T11:17:06.951641+00:00","updated_at":"2026-07-05T11:17:06.951641+00:00"}