{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LGHLMVQDGAMOW7O5KETDFJP37S","short_pith_number":"pith:LGHLMVQD","schema_version":"1.0","canonical_sha256":"598eb656033018eb7ddd512632a5fbfc8604c1747ea90f4357c21bc2c937134e","source":{"kind":"arxiv","id":"2402.14310","version":1},"attestation_state":"computed","paper":{"title":"Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Yan, Jinlan Fu, See-kiong Ng, Shenzhen Huangfu, Xipeng Qiu","submitted_at":"2024-02-22T05:58:03Z","abstract_excerpt":"Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains. Despite their extensive knowledge, LLMs still face challenges in efficiently utilizing encoded knowledge to develop accurate and logical reasoning processes. To mitigate this problem, we introduced Hint-before-Solving Prompting (HSP), which guides the model to generate hints (e.g., specific knowledge or key ideas) for solving the problem and then generate solutions containing intermediate reasoning steps. Since HSP is orthogonal to prompting methods (e.g., Chain-of-Thought (CoT)), we applied HS"},"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":"2402.14310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T05:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"4572a2c1aa222db74c550999b6de12060c0ea2e5e4d1d6dedee9f23451de1705","abstract_canon_sha256":"93bee576d9772adcc223659ca412c3a50a8bb166cd5da2625eacd8714f186443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:08.498812Z","signature_b64":"eVOhz8ibXCSu2xAkp9CDmC2/lRqxzbdEqiGnWrTk7m4L8hyKjm/iaVYagXnEXfZa2unCFVxXCxAQ/mMYYN26Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"598eb656033018eb7ddd512632a5fbfc8604c1747ea90f4357c21bc2c937134e","last_reissued_at":"2026-07-05T07:48:08.498293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:08.498293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Yan, Jinlan Fu, See-kiong Ng, Shenzhen Huangfu, Xipeng Qiu","submitted_at":"2024-02-22T05:58:03Z","abstract_excerpt":"Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains. Despite their extensive knowledge, LLMs still face challenges in efficiently utilizing encoded knowledge to develop accurate and logical reasoning processes. To mitigate this problem, we introduced Hint-before-Solving Prompting (HSP), which guides the model to generate hints (e.g., specific knowledge or key ideas) for solving the problem and then generate solutions containing intermediate reasoning steps. Since HSP is orthogonal to prompting methods (e.g., Chain-of-Thought (CoT)), we applied HS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14310","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/2402.14310/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":"2402.14310","created_at":"2026-07-05T07:48:08.498360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14310v1","created_at":"2026-07-05T07:48:08.498360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14310","created_at":"2026-07-05T07:48:08.498360+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGHLMVQDGAMO","created_at":"2026-07-05T07:48:08.498360+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGHLMVQDGAMOW7O5","created_at":"2026-07-05T07:48:08.498360+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGHLMVQD","created_at":"2026-07-05T07:48:08.498360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.19451","citing_title":"Computational Experiments in Number Theory","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17002","citing_title":"Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S","json":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S.json","graph_json":"https://pith.science/api/pith-number/LGHLMVQDGAMOW7O5KETDFJP37S/graph.json","events_json":"https://pith.science/api/pith-number/LGHLMVQDGAMOW7O5KETDFJP37S/events.json","paper":"https://pith.science/paper/LGHLMVQD"},"agent_actions":{"view_html":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S","download_json":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S.json","view_paper":"https://pith.science/paper/LGHLMVQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14310&json=true","fetch_graph":"https://pith.science/api/pith-number/LGHLMVQDGAMOW7O5KETDFJP37S/graph.json","fetch_events":"https://pith.science/api/pith-number/LGHLMVQDGAMOW7O5KETDFJP37S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S/action/storage_attestation","attest_author":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S/action/author_attestation","sign_citation":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S/action/citation_signature","submit_replication":"https://pith.science/pith/LGHLMVQDGAMOW7O5KETDFJP37S/action/replication_record"}},"created_at":"2026-07-05T07:48:08.498360+00:00","updated_at":"2026-07-05T07:48:08.498360+00:00"}