{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QVMUDD26L3POXT5P2VWG7U2WCU","short_pith_number":"pith:QVMUDD26","schema_version":"1.0","canonical_sha256":"8559418f5e5edeebcfafd56c6fd35615194ed1955783d7881843565c47d4dd81","source":{"kind":"arxiv","id":"2107.13586","version":1},"attestation_state":"computed","paper":{"title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Hiroaki Hayashi, Jinlan Fu, Pengfei Liu, Weizhe Yuan, Zhengbao Jiang","submitted_at":"2021-07-28T18:09:46Z","abstract_excerpt":"This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub \"prompt-based learning\". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P(y|x), prompt-based learning is based on language models that model the probability of text directly. To use these models to perform prediction tasks, the original input x is modified using a template into a textual string prompt x' that has some unfilled slots, and then the language model is used to probabilistically fill the unfilled information to "},"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":"2107.13586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-28T18:09:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6dc36e1047205acff589cfd477f93bf7cd11e47c8335e5947dda22dca13c6439","abstract_canon_sha256":"26898853d386d650e93d66a1ea7af8c58c67d3c9c147671a29d15297a8a5f6f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:37.955259Z","signature_b64":"TS6aikjvE6W6diMeyJ+OAL3wwEndt9d876L4Bre+A/8e4WaltnVcGHXigoRIVNBaKGECIP0bZ3LxhwCP3qVtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8559418f5e5edeebcfafd56c6fd35615194ed1955783d7881843565c47d4dd81","last_reissued_at":"2026-07-05T03:01:37.954847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:37.954847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Hiroaki Hayashi, Jinlan Fu, Pengfei Liu, Weizhe Yuan, Zhengbao Jiang","submitted_at":"2021-07-28T18:09:46Z","abstract_excerpt":"This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub \"prompt-based learning\". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P(y|x), prompt-based learning is based on language models that model the probability of text directly. To use these models to perform prediction tasks, the original input x is modified using a template into a textual string prompt x' that has some unfilled slots, and then the language model is used to probabilistically fill the unfilled information to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13586","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/2107.13586/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":"2107.13586","created_at":"2026-07-05T03:01:37.954902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13586v1","created_at":"2026-07-05T03:01:37.954902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13586","created_at":"2026-07-05T03:01:37.954902+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVMUDD26L3PO","created_at":"2026-07-05T03:01:37.954902+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVMUDD26L3POXT5P","created_at":"2026-07-05T03:01:37.954902+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVMUDD26","created_at":"2026-07-05T03:01:37.954902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26749","citing_title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","ref_index":176,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09498","citing_title":"Self-Harness: Harnesses That Improve Themselves","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04661","citing_title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","ref_index":209,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00776","citing_title":"Latent Diffusion Pretraining for Crystal Property Prediction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2305.09617","citing_title":"Towards Expert-Level Medical Question Answering with Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16359","citing_title":"LLM4Log: A Systematic Review of Large Language Model-based Log Analysis","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2104.08773","citing_title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08566","citing_title":"Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16359","citing_title":"LLM4Log: A Systematic Review of Large Language Model-based Log Analysis","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14055","citing_title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2211.10435","citing_title":"PAL: Program-aided Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03088","citing_title":"SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10403","citing_title":"PaLM 2 Technical Report","ref_index":263,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24544","citing_title":"STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18864","citing_title":"Towards an AI co-scientist","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05732","citing_title":"Graph Topology Information Enhanced Heterogeneous Graph Representation Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":252,"is_internal_anchor":false},{"citing_arxiv_id":"2201.11903","citing_title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU","json":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU.json","graph_json":"https://pith.science/api/pith-number/QVMUDD26L3POXT5P2VWG7U2WCU/graph.json","events_json":"https://pith.science/api/pith-number/QVMUDD26L3POXT5P2VWG7U2WCU/events.json","paper":"https://pith.science/paper/QVMUDD26"},"agent_actions":{"view_html":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU","download_json":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU.json","view_paper":"https://pith.science/paper/QVMUDD26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13586&json=true","fetch_graph":"https://pith.science/api/pith-number/QVMUDD26L3POXT5P2VWG7U2WCU/graph.json","fetch_events":"https://pith.science/api/pith-number/QVMUDD26L3POXT5P2VWG7U2WCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU/action/storage_attestation","attest_author":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU/action/author_attestation","sign_citation":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU/action/citation_signature","submit_replication":"https://pith.science/pith/QVMUDD26L3POXT5P2VWG7U2WCU/action/replication_record"}},"created_at":"2026-07-05T03:01:37.954902+00:00","updated_at":"2026-07-05T03:01:37.954902+00:00"}