{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEKF6QCOMBTC7CLNMTJMUVYMH4","short_pith_number":"pith:YEKF6QCO","schema_version":"1.0","canonical_sha256":"c1145f404e60662f896d64d2ca570c3f114b83da96602829902d9aa36bd7a8b1","source":{"kind":"arxiv","id":"2408.09006","version":1},"attestation_state":"computed","paper":{"title":"Context-aware Code Summary Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aakash Bansal, Chia-Yi Su, Collin McMillan, Toby Jia-Jun Li, Yu Huang","submitted_at":"2024-08-16T20:15:34Z","abstract_excerpt":"Code summary generation is the task of writing natural language descriptions of a section of source code. Recent advances in Large Language Models (LLMs) and other AI-based technologies have helped make automatic code summarization a reality. However, the summaries these approaches write tend to focus on a narrow area of code. The results are summaries that explain what that function does internally, but lack a description of why the function exists or its purpose in the broader context of the program. In this paper, we present an approach for including this context in recent LLM-based code su"},"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":"2408.09006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-08-16T20:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"399e72dea20b039237a808b86a13d821fe0f52a3376a3c0e6024e54a47ae00da","abstract_canon_sha256":"5b8827264bfd81c10386de9c6330b126c6871d7db9d059abb71bb0195cb6ad14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:26.622454Z","signature_b64":"QniHB5BprYxgt9UT5EtXklwnrSZd4efNGb1tEm2XfFPiKL/6DNkTbnAqkORKMBlgOJZgqhISp9dQvLasAA2EAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1145f404e60662f896d64d2ca570c3f114b83da96602829902d9aa36bd7a8b1","last_reissued_at":"2026-07-05T08:56:26.622010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:26.622010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-aware Code Summary Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aakash Bansal, Chia-Yi Su, Collin McMillan, Toby Jia-Jun Li, Yu Huang","submitted_at":"2024-08-16T20:15:34Z","abstract_excerpt":"Code summary generation is the task of writing natural language descriptions of a section of source code. Recent advances in Large Language Models (LLMs) and other AI-based technologies have helped make automatic code summarization a reality. However, the summaries these approaches write tend to focus on a narrow area of code. The results are summaries that explain what that function does internally, but lack a description of why the function exists or its purpose in the broader context of the program. In this paper, we present an approach for including this context in recent LLM-based code su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09006","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/2408.09006/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":"2408.09006","created_at":"2026-07-05T08:56:26.622069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09006v1","created_at":"2026-07-05T08:56:26.622069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09006","created_at":"2026-07-05T08:56:26.622069+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEKF6QCOMBTC","created_at":"2026-07-05T08:56:26.622069+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEKF6QCOMBTC7CLN","created_at":"2026-07-05T08:56:26.622069+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEKF6QCO","created_at":"2026-07-05T08:56:26.622069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30524","citing_title":"The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30524","citing_title":"The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4","json":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4.json","graph_json":"https://pith.science/api/pith-number/YEKF6QCOMBTC7CLNMTJMUVYMH4/graph.json","events_json":"https://pith.science/api/pith-number/YEKF6QCOMBTC7CLNMTJMUVYMH4/events.json","paper":"https://pith.science/paper/YEKF6QCO"},"agent_actions":{"view_html":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4","download_json":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4.json","view_paper":"https://pith.science/paper/YEKF6QCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09006&json=true","fetch_graph":"https://pith.science/api/pith-number/YEKF6QCOMBTC7CLNMTJMUVYMH4/graph.json","fetch_events":"https://pith.science/api/pith-number/YEKF6QCOMBTC7CLNMTJMUVYMH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4/action/storage_attestation","attest_author":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4/action/author_attestation","sign_citation":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4/action/citation_signature","submit_replication":"https://pith.science/pith/YEKF6QCOMBTC7CLNMTJMUVYMH4/action/replication_record"}},"created_at":"2026-07-05T08:56:26.622069+00:00","updated_at":"2026-07-05T08:56:26.622069+00:00"}