{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YPFYFNW2KJ4VVOYUZOV2YKXV46","short_pith_number":"pith:YPFYFNW2","schema_version":"1.0","canonical_sha256":"c3cb82b6da52795abb14cbabac2af5e78660026cacc8be6788ea5e289a054fce","source":{"kind":"arxiv","id":"2406.06608","version":6},"attestation_state":"computed","paper":{"title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 for other modalities, supported by a 33-term vocabulary and best practices.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aayush Gupta, Alexander Hoyle, Amanda Liu, Ashay Srivastava, Chau Pham, Chenglei Si, Dayeon Ki, Denis Peskoff, Feileen Li, Gerson Kroiz, Giuseppe Sarli, Hevander Da Costa, Hudson Tao, HyoJung Han, Igor Galynker, Inna Goncearenco, Jules White, Konstantine Kahadze, Marine Carpuat, Megan L. Rogers, Michael Ilie, Nishant Balepur, Philip Resnik, Pranav Sandeep Dulepet, Saloni Gupta, Sander Schulhoff, Saurav Vidyadhara, Sevien Schulhoff, Shyamal Anadkat, Sweta Agrawal, Yinheng Li","submitted_at":"2024-06-06T18:10:11Z","abstract_excerpt":"Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these systems through the use of prompting and prompt engineering. Although prompt engineering is a widely adopted and extensively researched area, it suffers from conflicting terminology and a fragmented ontological understanding of what constitutes an effective prompt due to its relatively recent emergence. We establish a structured understanding of prompt engineering by assembling a taxonomy of prompting techniques and anal"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2406.06608","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T18:10:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bfdc0b855be5f2c43b2f8034696222ac18f87815ec861f29d5160033cc0f72b","abstract_canon_sha256":"c0ecf27a8df7f9ccb02f872995985b77c58a656ff4792ab3ec2123fa4b931360"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.842739Z","signature_b64":"M8BDX+bUaG2NK0a/qfI+ZukYZqvf/aCaBaLr7gna0YYSO0d9aaerwhxn4TDiikmj5vBsWBnz6Edt46fc2bpnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3cb82b6da52795abb14cbabac2af5e78660026cacc8be6788ea5e289a054fce","last_reissued_at":"2026-05-17T23:38:53.842061Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.842061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 for other modalities, supported by a 33-term vocabulary and best practices.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aayush Gupta, Alexander Hoyle, Amanda Liu, Ashay Srivastava, Chau Pham, Chenglei Si, Dayeon Ki, Denis Peskoff, Feileen Li, Gerson Kroiz, Giuseppe Sarli, Hevander Da Costa, Hudson Tao, HyoJung Han, Igor Galynker, Inna Goncearenco, Jules White, Konstantine Kahadze, Marine Carpuat, Megan L. Rogers, Michael Ilie, Nishant Balepur, Philip Resnik, Pranav Sandeep Dulepet, Saloni Gupta, Sander Schulhoff, Saurav Vidyadhara, Sevien Schulhoff, Shyamal Anadkat, Sweta Agrawal, Yinheng Li","submitted_at":"2024-06-06T18:10:11Z","abstract_excerpt":"Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these systems through the use of prompting and prompt engineering. Although prompt engineering is a widely adopted and extensively researched area, it suffers from conflicting terminology and a fragmented ontological understanding of what constitutes an effective prompt due to its relatively recent emergence. We establish a structured understanding of prompt engineering by assembling a taxonomy of prompting techniques and anal"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"this paper presents the most comprehensive survey on prompt engineering to date","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The literature search and categorization process captured a representative and exhaustive set of prompting techniques without significant omissions or misclassifications.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"This systematic survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 others, supplies a shared vocabulary, and offers guidelines for state-of-the-art models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 for other modalities, supported by a 33-term vocabulary and best practices.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"00031b8fcefe5d1b4aa2fb7ad63b1ece146a0c3cde8c90b0098e07e88636c26d"},"source":{"id":"2406.06608","kind":"arxiv","version":6},"verdict":{"id":"0dd79df9-6eb4-4a8e-84ab-489251e4a246","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:11:47.649500Z","strongest_claim":"this paper presents the most comprehensive survey on prompt engineering to date","one_line_summary":"This systematic survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 others, supplies a shared vocabulary, and offers guidelines for state-of-the-art models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The literature search and categorization process captured a representative and exhaustive set of prompting techniques without significant omissions or misclassifications.","pith_extraction_headline":"A survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 for other modalities, supported by a 33-term vocabulary and best practices."},"references":{"count":27,"sample":[{"doi":"","year":2023,"title":"Agrawal, P., Craig, N., Madden, A., and Lombera, I","work_id":"1ff25d89-9966-4623-9f61-876eb43549b4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Muhammad Awais, Muzammal Naseer, Salman Khan, Rao Muhammad Anwer, Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, and Fahad Shah- baz Khan","work_id":"c45bce50-cd8c-40e6-9de1-3e9a062280a5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"In Proceedings of the 17th Conference of the European Chapter of the As- sociation for Computational Linguistics, pages 2455– 2467, Dubrovnik, Croatia","work_id":"fe1d71c4-986b-4d61-9d33-7c5170b660b9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"arXiv preprint arXiv:2405.00200 , year=","work_id":"16af75a7-d946-4ab5-a85c-1a423767113b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","work_id":"a23cfe92-7f7c-424b-98d4-b386a83002fb","ref_index":5,"cited_arxiv_id":"2303.12712","is_internal_anchor":true}],"resolved_work":27,"snapshot_sha256":"98f382ffb659a493db9634410f16e49e156617e12fde7d0ade4c9c199afab011","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"501323478f33b05580ea328c39b4ccc18f76272c17e54852682e8591888c503d"},"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":"2406.06608","created_at":"2026-05-17T23:38:53.842171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06608v6","created_at":"2026-05-17T23:38:53.842171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06608","created_at":"2026-05-17T23:38:53.842171+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPFYFNW2KJ4V","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPFYFNW2KJ4VVOYU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPFYFNW2","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":36,"internal_anchor_count":36,"sample":[{"citing_arxiv_id":"2509.03117","citing_title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2501.03544","citing_title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2504.16155","citing_title":"PRIMETIME : Limits of LLMs in Temporal Primitives","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22645","citing_title":"AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15104","citing_title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20254","citing_title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":248,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18652","citing_title":"From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16538","citing_title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2506.06921","citing_title":"Teaching Astronomy with Large Language Models","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2509.09544","citing_title":"MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2509.18052","citing_title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2510.13907","citing_title":"LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2408.08435","citing_title":"Automated Design of Agentic Systems","ref_index":206,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14553","citing_title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19777","citing_title":"Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12657","citing_title":"User Reviews as a Source for Usability Requirements: A Precursor Study on Using Large Language Models","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14197","citing_title":"The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10593","citing_title":"LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22016","citing_title":"Looking Into the Past: Eye Movements Characterize Elements of Autobiographical Recall in Interviews with Holocaust Survivors","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04534","citing_title":"Characterizing Students' LLM Usage Behaviors and Their Association with Learning in Critical Thinking Tasks","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02170","citing_title":"CLaC at SemEval-2026 Task 6: Response Clarity Detection in Political Discourse","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00060","citing_title":"TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46","json":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46.json","graph_json":"https://pith.science/api/pith-number/YPFYFNW2KJ4VVOYUZOV2YKXV46/graph.json","events_json":"https://pith.science/api/pith-number/YPFYFNW2KJ4VVOYUZOV2YKXV46/events.json","paper":"https://pith.science/paper/YPFYFNW2"},"agent_actions":{"view_html":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46","download_json":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46.json","view_paper":"https://pith.science/paper/YPFYFNW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06608&json=true","fetch_graph":"https://pith.science/api/pith-number/YPFYFNW2KJ4VVOYUZOV2YKXV46/graph.json","fetch_events":"https://pith.science/api/pith-number/YPFYFNW2KJ4VVOYUZOV2YKXV46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46/action/storage_attestation","attest_author":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46/action/author_attestation","sign_citation":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46/action/citation_signature","submit_replication":"https://pith.science/pith/YPFYFNW2KJ4VVOYUZOV2YKXV46/action/replication_record"}},"created_at":"2026-05-17T23:38:53.842171+00:00","updated_at":"2026-05-17T23:38:53.842171+00:00"}