{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O3VINZWZWXUUJY67M7S3KXTJHM","short_pith_number":"pith:O3VINZWZ","schema_version":"1.0","canonical_sha256":"76ea86e6d9b5e944e3df67e5b55e693b3b76ccc89e1c3242157099fb75385845","source":{"kind":"arxiv","id":"2501.11354","version":1},"attestation_state":"computed","paper":{"title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Haolin Jin, Huaming Chen, Liming Zhu, Qinghua Lu","submitted_at":"2025-01-20T09:33:44Z","abstract_excerpt":"Recently, we have witnessed the rapid development of large language models, which have demonstrated excellent capabilities in the downstream task of code generation. However, despite their potential, LLM-based code generation still faces numerous technical and evaluation challenges, particularly when embedded in real-world development. In this paper, we present our vision for current research directions, and provide an in-depth analysis of existing studies on this task. We propose a six-layer vision framework that categorizes code generation process into distinct phases, namely Input Phase, Or"},"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":"2501.11354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-20T09:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f196a63895fbd5a2d1fb11c4f9d0c0b7d339643d9e426db889329a469cf4a179","abstract_canon_sha256":"effc9af221b521e1b4957173fce76a91d334e485f82290f5426ca213ef264989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:07.459589Z","signature_b64":"7l5MAIIOlGp7LwUWhjA+F6XtG58XcDyWBjDR1c9YH3HCS8qC/9wkuKpdjbDdr87jgRtdiosNtP3h89eVKbv8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76ea86e6d9b5e944e3df67e5b55e693b3b76ccc89e1c3242157099fb75385845","last_reissued_at":"2026-07-05T10:03:07.459115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:07.459115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Haolin Jin, Huaming Chen, Liming Zhu, Qinghua Lu","submitted_at":"2025-01-20T09:33:44Z","abstract_excerpt":"Recently, we have witnessed the rapid development of large language models, which have demonstrated excellent capabilities in the downstream task of code generation. However, despite their potential, LLM-based code generation still faces numerous technical and evaluation challenges, particularly when embedded in real-world development. In this paper, we present our vision for current research directions, and provide an in-depth analysis of existing studies on this task. We propose a six-layer vision framework that categorizes code generation process into distinct phases, namely Input Phase, Or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11354","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/2501.11354/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":"2501.11354","created_at":"2026-07-05T10:03:07.459168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11354v1","created_at":"2026-07-05T10:03:07.459168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11354","created_at":"2026-07-05T10:03:07.459168+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3VINZWZWXUU","created_at":"2026-07-05T10:03:07.459168+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3VINZWZWXUUJY67","created_at":"2026-07-05T10:03:07.459168+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3VINZWZ","created_at":"2026-07-05T10:03:07.459168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM","json":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM.json","graph_json":"https://pith.science/api/pith-number/O3VINZWZWXUUJY67M7S3KXTJHM/graph.json","events_json":"https://pith.science/api/pith-number/O3VINZWZWXUUJY67M7S3KXTJHM/events.json","paper":"https://pith.science/paper/O3VINZWZ"},"agent_actions":{"view_html":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM","download_json":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM.json","view_paper":"https://pith.science/paper/O3VINZWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11354&json=true","fetch_graph":"https://pith.science/api/pith-number/O3VINZWZWXUUJY67M7S3KXTJHM/graph.json","fetch_events":"https://pith.science/api/pith-number/O3VINZWZWXUUJY67M7S3KXTJHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM/action/storage_attestation","attest_author":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM/action/author_attestation","sign_citation":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM/action/citation_signature","submit_replication":"https://pith.science/pith/O3VINZWZWXUUJY67M7S3KXTJHM/action/replication_record"}},"created_at":"2026-07-05T10:03:07.459168+00:00","updated_at":"2026-07-05T10:03:07.459168+00:00"}