{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L7UPOUPXIKPWZEK6DJT3RQ3KDU","short_pith_number":"pith:L7UPOUPX","schema_version":"1.0","canonical_sha256":"5fe8f751f7429f6c915e1a67b8c36a1d2681660d90415b52a918df713ed690b2","source":{"kind":"arxiv","id":"2503.12483","version":1},"attestation_state":"computed","paper":{"title":"Modularization is Better: Effective Code Generation with Modular Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Ruwei Pan","submitted_at":"2025-03-16T12:23:23Z","abstract_excerpt":"Large Language Models are transforming software development by automatically generating code. Current prompting techniques such as Chain-of-Thought (CoT) suggest tasks step by step and the reasoning process follows a linear structure, which hampers the understanding of complex programming problems, particularly those requiring hierarchical solutions. Inspired by the principle of modularization in software development, in this work, we propose a novel prompting technique, called MoT, to enhance the code generation performance of LLMs. At first, MoT exploits modularization principles to decompos"},"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":"2503.12483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-16T12:23:23Z","cross_cats_sorted":[],"title_canon_sha256":"6517a6a31937d62f1707f524d1e326e0e82bcab2de2828c63a3c1c1713ed4f0e","abstract_canon_sha256":"f348a69b9a77170e22ac4c29a3e2f5aa5d4ab06d3d3b0a3fce4b61ab498de3ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:14.496791Z","signature_b64":"g0CL3pr+jm6OrEiewcBEdx3O3sOjsymdHy8sBqSjYmVHplX44hQF5fzLTyJuNVtUU1DyoQJs0Iy/vcOIUxmBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe8f751f7429f6c915e1a67b8c36a1d2681660d90415b52a918df713ed690b2","last_reissued_at":"2026-07-05T10:32:14.495737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:14.495737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modularization is Better: Effective Code Generation with Modular Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Ruwei Pan","submitted_at":"2025-03-16T12:23:23Z","abstract_excerpt":"Large Language Models are transforming software development by automatically generating code. Current prompting techniques such as Chain-of-Thought (CoT) suggest tasks step by step and the reasoning process follows a linear structure, which hampers the understanding of complex programming problems, particularly those requiring hierarchical solutions. Inspired by the principle of modularization in software development, in this work, we propose a novel prompting technique, called MoT, to enhance the code generation performance of LLMs. At first, MoT exploits modularization principles to decompos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12483","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/2503.12483/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":"2503.12483","created_at":"2026-07-05T10:32:14.495866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12483v1","created_at":"2026-07-05T10:32:14.495866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12483","created_at":"2026-07-05T10:32:14.495866+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7UPOUPXIKPW","created_at":"2026-07-05T10:32:14.495866+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7UPOUPXIKPWZEK6","created_at":"2026-07-05T10:32:14.495866+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7UPOUPX","created_at":"2026-07-05T10:32:14.495866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.02761","citing_title":"Sustainability Analysis of Prompt Strategies for SLM-based Automated Test Generation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU","json":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU.json","graph_json":"https://pith.science/api/pith-number/L7UPOUPXIKPWZEK6DJT3RQ3KDU/graph.json","events_json":"https://pith.science/api/pith-number/L7UPOUPXIKPWZEK6DJT3RQ3KDU/events.json","paper":"https://pith.science/paper/L7UPOUPX"},"agent_actions":{"view_html":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU","download_json":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU.json","view_paper":"https://pith.science/paper/L7UPOUPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12483&json=true","fetch_graph":"https://pith.science/api/pith-number/L7UPOUPXIKPWZEK6DJT3RQ3KDU/graph.json","fetch_events":"https://pith.science/api/pith-number/L7UPOUPXIKPWZEK6DJT3RQ3KDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU/action/storage_attestation","attest_author":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU/action/author_attestation","sign_citation":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU/action/citation_signature","submit_replication":"https://pith.science/pith/L7UPOUPXIKPWZEK6DJT3RQ3KDU/action/replication_record"}},"created_at":"2026-07-05T10:32:14.495866+00:00","updated_at":"2026-07-05T10:32:14.495866+00:00"}