{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LAYSNEYIADZNQRSDB4NMNTYMSU","short_pith_number":"pith:LAYSNEYI","schema_version":"1.0","canonical_sha256":"583126930800f2d846430f1ac6cf0c952d577d4c01cc9189e905a4cf1a34880b","source":{"kind":"arxiv","id":"2504.15080","version":1},"attestation_state":"computed","paper":{"title":"Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Beijun Shen, Chen Xie, Mingsheng Jiao, Xiaodong Gu","submitted_at":"2025-04-21T13:09:25Z","abstract_excerpt":"While large language models (LLMs) have been widely applied to code generation, they struggle with generating entire deep learning projects, which are characterized by complex structures, longer functions, and stronger reliance on domain knowledge than general-purpose code. An open-domain LLM often lacks coherent contextual guidance and domain expertise for specific projects, making it challenging to produce complete code that fully meets user requirements.\n  In this paper, we propose a novel planning-guided code generation method, DLCodeGen, tailored for generating deep learning projects. DLC"},"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":"2504.15080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-21T13:09:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d5fce4653cd7c5e6f4e24ef8bf4fd6f63543b827428ed7a19ae5dcce6354eaf","abstract_canon_sha256":"f53761d9325e040d284f88405772eb1838795e09df1566fa3546031aa97742cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:55.908824Z","signature_b64":"hq8MvcnXxIWDMKnyiX5rxtNa0SEljj9Jrsx7H6EF/NEjAfioq/+OKQuGfHYkLdGz4T9HAP7N3J/Di3D0g1ysCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"583126930800f2d846430f1ac6cf0c952d577d4c01cc9189e905a4cf1a34880b","last_reissued_at":"2026-07-05T10:51:55.908337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:55.908337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Beijun Shen, Chen Xie, Mingsheng Jiao, Xiaodong Gu","submitted_at":"2025-04-21T13:09:25Z","abstract_excerpt":"While large language models (LLMs) have been widely applied to code generation, they struggle with generating entire deep learning projects, which are characterized by complex structures, longer functions, and stronger reliance on domain knowledge than general-purpose code. An open-domain LLM often lacks coherent contextual guidance and domain expertise for specific projects, making it challenging to produce complete code that fully meets user requirements.\n  In this paper, we propose a novel planning-guided code generation method, DLCodeGen, tailored for generating deep learning projects. DLC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15080","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/2504.15080/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":"2504.15080","created_at":"2026-07-05T10:51:55.908393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15080v1","created_at":"2026-07-05T10:51:55.908393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15080","created_at":"2026-07-05T10:51:55.908393+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAYSNEYIADZN","created_at":"2026-07-05T10:51:55.908393+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAYSNEYIADZNQRSD","created_at":"2026-07-05T10:51:55.908393+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAYSNEYI","created_at":"2026-07-05T10:51:55.908393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU","json":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU.json","graph_json":"https://pith.science/api/pith-number/LAYSNEYIADZNQRSDB4NMNTYMSU/graph.json","events_json":"https://pith.science/api/pith-number/LAYSNEYIADZNQRSDB4NMNTYMSU/events.json","paper":"https://pith.science/paper/LAYSNEYI"},"agent_actions":{"view_html":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU","download_json":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU.json","view_paper":"https://pith.science/paper/LAYSNEYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15080&json=true","fetch_graph":"https://pith.science/api/pith-number/LAYSNEYIADZNQRSDB4NMNTYMSU/graph.json","fetch_events":"https://pith.science/api/pith-number/LAYSNEYIADZNQRSDB4NMNTYMSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU/action/storage_attestation","attest_author":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU/action/author_attestation","sign_citation":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU/action/citation_signature","submit_replication":"https://pith.science/pith/LAYSNEYIADZNQRSDB4NMNTYMSU/action/replication_record"}},"created_at":"2026-07-05T10:51:55.908393+00:00","updated_at":"2026-07-05T10:51:55.908393+00:00"}