{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UZEWDQIB2TLPKVIGVMMYYRRCY4","short_pith_number":"pith:UZEWDQIB","schema_version":"1.0","canonical_sha256":"a64961c101d4d6f55506ab198c4622c7104f7bf45fed1cd9905147775ec49d29","source":{"kind":"arxiv","id":"2307.07415","version":2},"attestation_state":"computed","paper":{"title":"AutoHint: Automatic Prompt Optimization with Hint Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Denis Charles, Hong Sun, Jian Jiao, Min Wu, Qi Cao, Xue Li, Yinchuan Xu, Youkow Homma","submitted_at":"2023-07-13T00:49:27Z","abstract_excerpt":"This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the key to applying this ability to specific tasks lies in developing high-quality prompts. Thus we propose a framework to inherit the merits of both in-context learning and zero-shot learning by incorporating enriched instructions derived from input-output demonstrations to optimize original prompt. We refer to the enrichment as the hint and propose a framework t"},"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":"2307.07415","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-13T00:49:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77f9ec8438981d9ae1c570cc178ed321adc5e4aa34c68f32a5c1b753cc6a4669","abstract_canon_sha256":"62638dcc433c0733163bfcf07de262d25a62bf6d1f9e286161fe2d5df7e5916d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:36.333080Z","signature_b64":"xhpxpNoBI1Uo08i0t59jnoAc/Ja5Fn3d61oUoLD9CdUHOQVaPLIdROH6fYnx92BgWt6i9ov5SSFwRn0mSpzMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a64961c101d4d6f55506ab198c4622c7104f7bf45fed1cd9905147775ec49d29","last_reissued_at":"2026-07-05T06:39:36.332569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:36.332569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoHint: Automatic Prompt Optimization with Hint Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Denis Charles, Hong Sun, Jian Jiao, Min Wu, Qi Cao, Xue Li, Yinchuan Xu, Youkow Homma","submitted_at":"2023-07-13T00:49:27Z","abstract_excerpt":"This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the key to applying this ability to specific tasks lies in developing high-quality prompts. Thus we propose a framework to inherit the merits of both in-context learning and zero-shot learning by incorporating enriched instructions derived from input-output demonstrations to optimize original prompt. We refer to the enrichment as the hint and propose a framework t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07415","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/2307.07415/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":"2307.07415","created_at":"2026-07-05T06:39:36.332629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07415v2","created_at":"2026-07-05T06:39:36.332629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07415","created_at":"2026-07-05T06:39:36.332629+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZEWDQIB2TLP","created_at":"2026-07-05T06:39:36.332629+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZEWDQIB2TLPKVIG","created_at":"2026-07-05T06:39:36.332629+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZEWDQIB","created_at":"2026-07-05T06:39:36.332629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24004","citing_title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12387","citing_title":"TAHOE: Text-to-SQL with Automated Hint Optimization from Experience","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04661","citing_title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24004","citing_title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03117","citing_title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4","json":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4.json","graph_json":"https://pith.science/api/pith-number/UZEWDQIB2TLPKVIGVMMYYRRCY4/graph.json","events_json":"https://pith.science/api/pith-number/UZEWDQIB2TLPKVIGVMMYYRRCY4/events.json","paper":"https://pith.science/paper/UZEWDQIB"},"agent_actions":{"view_html":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4","download_json":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4.json","view_paper":"https://pith.science/paper/UZEWDQIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07415&json=true","fetch_graph":"https://pith.science/api/pith-number/UZEWDQIB2TLPKVIGVMMYYRRCY4/graph.json","fetch_events":"https://pith.science/api/pith-number/UZEWDQIB2TLPKVIGVMMYYRRCY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4/action/storage_attestation","attest_author":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4/action/author_attestation","sign_citation":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4/action/citation_signature","submit_replication":"https://pith.science/pith/UZEWDQIB2TLPKVIGVMMYYRRCY4/action/replication_record"}},"created_at":"2026-07-05T06:39:36.332629+00:00","updated_at":"2026-07-05T06:39:36.332629+00:00"}