{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LHAE4NGNL4DF3EZ52A2FRJQNOH","short_pith_number":"pith:LHAE4NGN","schema_version":"1.0","canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","source":{"kind":"arxiv","id":"2506.23762","version":1},"attestation_state":"computed","paper":{"title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Haoyu Wang, Hongzhou Rao, Shenao Wang, Xinyi Hou, Yanjie Zhao","submitted_at":"2025-06-30T12:09:29Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for both academia and the industry. However, LLM development faces increasingly complex challenges throughout its lifecycle, yet no existing research systematically explores these challenges and solutions from the perspective of software engineering (SE) approaches. To fill the gap, we systematically analyze research status throughout the LLM development lifecycle, divided into six phases: requirements engineering, dataset "},"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":"2506.23762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-30T12:09:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71614683f28ba5d31f6b704f8d755b9221b4c4788e401cebdc8472e4b15cf6b4","abstract_canon_sha256":"1ca834d793bf298277505e4869602bcf20c0b9744d49ab273061b09537447674"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:27.627843Z","signature_b64":"JZY+TjxB+u0y3V+Kjr5kmNizdSDurZg8tre/dXyCDONBJHVRRkpsJQG+nMcoRR7w4vspKBMvQhA3ImuyeyvHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","last_reissued_at":"2026-07-05T11:29:27.627431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:27.627431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Haoyu Wang, Hongzhou Rao, Shenao Wang, Xinyi Hou, Yanjie Zhao","submitted_at":"2025-06-30T12:09:29Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for both academia and the industry. However, LLM development faces increasingly complex challenges throughout its lifecycle, yet no existing research systematically explores these challenges and solutions from the perspective of software engineering (SE) approaches. To fill the gap, we systematically analyze research status throughout the LLM development lifecycle, divided into six phases: requirements engineering, dataset "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23762","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/2506.23762/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":"2506.23762","created_at":"2026-07-05T11:29:27.627489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23762v1","created_at":"2026-07-05T11:29:27.627489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23762","created_at":"2026-07-05T11:29:27.627489+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHAE4NGNL4DF","created_at":"2026-07-05T11:29:27.627489+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHAE4NGNL4DF3EZ5","created_at":"2026-07-05T11:29:27.627489+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHAE4NGN","created_at":"2026-07-05T11:29:27.627489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.15411","citing_title":"Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH","json":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH.json","graph_json":"https://pith.science/api/pith-number/LHAE4NGNL4DF3EZ52A2FRJQNOH/graph.json","events_json":"https://pith.science/api/pith-number/LHAE4NGNL4DF3EZ52A2FRJQNOH/events.json","paper":"https://pith.science/paper/LHAE4NGN"},"agent_actions":{"view_html":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH","download_json":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH.json","view_paper":"https://pith.science/paper/LHAE4NGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23762&json=true","fetch_graph":"https://pith.science/api/pith-number/LHAE4NGNL4DF3EZ52A2FRJQNOH/graph.json","fetch_events":"https://pith.science/api/pith-number/LHAE4NGNL4DF3EZ52A2FRJQNOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/action/storage_attestation","attest_author":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/action/author_attestation","sign_citation":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/action/citation_signature","submit_replication":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/action/replication_record"}},"created_at":"2026-07-05T11:29:27.627489+00:00","updated_at":"2026-07-05T11:29:27.627489+00:00"}