{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GVQ6XJFDUEBONKSIJQSF4FEG2C","short_pith_number":"pith:GVQ6XJFD","schema_version":"1.0","canonical_sha256":"3561eba4a3a102e6aa484c245e1486d08299fc1eb0f2323dfc7cf6e400e3dab9","source":{"kind":"arxiv","id":"2410.22793","version":3},"attestation_state":"computed","paper":{"title":"Less is More: DocString Compression in Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"David Lo, Guang Yang, Ke Liu, Taolue Chen, Terry Yue Zhuo, Wei Cheng, Xiang Chen, Xiangyu Zhang, Xin Zhou, Yu Zhou","submitted_at":"2024-10-30T08:17:10Z","abstract_excerpt":"The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature and DocString to executable code. DocStrings which capture user re quirements for the code and used as the prompt for LLMs, often contains redundant information. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. Our empirical study show th"},"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":"2410.22793","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-30T08:17:10Z","cross_cats_sorted":[],"title_canon_sha256":"267f6e38112c2dd459a989d9e557be0907a1611550a2b3b5eb09a9bfae68581c","abstract_canon_sha256":"b23e28d558fd145ed3c53bcf96b215fe4cb73c7754417793b2aa9e55e7771473"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:22.256188Z","signature_b64":"1IrhORA44MSJuRGSv/bbZ5tDPyAO3uvfUWgci3jTRVju9P1P0RqjEsWT1+nuE9Ni2dnLKuUEhPvH4BYv+72mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3561eba4a3a102e6aa484c245e1486d08299fc1eb0f2323dfc7cf6e400e3dab9","last_reissued_at":"2026-07-05T11:19:22.255704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:22.255704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: DocString Compression in Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"David Lo, Guang Yang, Ke Liu, Taolue Chen, Terry Yue Zhuo, Wei Cheng, Xiang Chen, Xiangyu Zhang, Xin Zhou, Yu Zhou","submitted_at":"2024-10-30T08:17:10Z","abstract_excerpt":"The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature and DocString to executable code. DocStrings which capture user re quirements for the code and used as the prompt for LLMs, often contains redundant information. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. Our empirical study show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22793","kind":"arxiv","version":3},"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/2410.22793/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":"2410.22793","created_at":"2026-07-05T11:19:22.255765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22793v3","created_at":"2026-07-05T11:19:22.255765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22793","created_at":"2026-07-05T11:19:22.255765+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVQ6XJFDUEBO","created_at":"2026-07-05T11:19:22.255765+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVQ6XJFDUEBONKSI","created_at":"2026-07-05T11:19:22.255765+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVQ6XJFD","created_at":"2026-07-05T11:19:22.255765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.14925","citing_title":"CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01785","citing_title":"Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C","json":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C.json","graph_json":"https://pith.science/api/pith-number/GVQ6XJFDUEBONKSIJQSF4FEG2C/graph.json","events_json":"https://pith.science/api/pith-number/GVQ6XJFDUEBONKSIJQSF4FEG2C/events.json","paper":"https://pith.science/paper/GVQ6XJFD"},"agent_actions":{"view_html":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C","download_json":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C.json","view_paper":"https://pith.science/paper/GVQ6XJFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22793&json=true","fetch_graph":"https://pith.science/api/pith-number/GVQ6XJFDUEBONKSIJQSF4FEG2C/graph.json","fetch_events":"https://pith.science/api/pith-number/GVQ6XJFDUEBONKSIJQSF4FEG2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C/action/storage_attestation","attest_author":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C/action/author_attestation","sign_citation":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C/action/citation_signature","submit_replication":"https://pith.science/pith/GVQ6XJFDUEBONKSIJQSF4FEG2C/action/replication_record"}},"created_at":"2026-07-05T11:19:22.255765+00:00","updated_at":"2026-07-05T11:19:22.255765+00:00"}