{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:P2A4GJN6KZP4GQUDWPKNKL6CY2","short_pith_number":"pith:P2A4GJN6","schema_version":"1.0","canonical_sha256":"7e81c325be565fc34283b3d4d52fc2c6814442696ad8771840a3e881964149ee","source":{"kind":"arxiv","id":"2006.05405","version":5},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingkai Siow, Shangqing Liu, Xiaofei Xie, Yang Liu, Yu Chen","submitted_at":"2020-06-09T17:09:29Z","abstract_excerpt":"Source code summarization aims to generate natural language summaries from structured code snippets for better understanding code functionalities. However, automatic code summarization is challenging due to the complexity of the source code and the language gap between the source code and natural language summaries. Most previous approaches either rely on retrieval-based (which can take advantage of similar examples seen from the retrieval database, but have low generalization performance) or generation-based methods (which have better generalization performance, but cannot take advantage of s"},"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":"2006.05405","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T17:09:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e604b5b8bd683777c5674ecc48e0480ab4b2fb3d882accd54b12dea37b43f756","abstract_canon_sha256":"2fd7c522ec331345a9d6b5dc82a59511621c1e61d68a124dd6b662bb140ca54a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:56.474483Z","signature_b64":"08bUKSeyc60FGlE3XNCSqSUOLUL6Sd1PQpPmYljjs6mGc50g66V+qf5qW6Fm4vEpj2yicZKovSTBAzV9Oe4ADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e81c325be565fc34283b3d4d52fc2c6814442696ad8771840a3e881964149ee","last_reissued_at":"2026-07-05T02:39:56.474009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:56.474009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingkai Siow, Shangqing Liu, Xiaofei Xie, Yang Liu, Yu Chen","submitted_at":"2020-06-09T17:09:29Z","abstract_excerpt":"Source code summarization aims to generate natural language summaries from structured code snippets for better understanding code functionalities. However, automatic code summarization is challenging due to the complexity of the source code and the language gap between the source code and natural language summaries. Most previous approaches either rely on retrieval-based (which can take advantage of similar examples seen from the retrieval database, but have low generalization performance) or generation-based methods (which have better generalization performance, but cannot take advantage of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05405","kind":"arxiv","version":5},"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/2006.05405/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":"2006.05405","created_at":"2026-07-05T02:39:56.474063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05405v5","created_at":"2026-07-05T02:39:56.474063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05405","created_at":"2026-07-05T02:39:56.474063+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2A4GJN6KZP4","created_at":"2026-07-05T02:39:56.474063+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2A4GJN6KZP4GQUD","created_at":"2026-07-05T02:39:56.474063+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2A4GJN6","created_at":"2026-07-05T02:39:56.474063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.12138","citing_title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15385","citing_title":"Prompt-Driven Code Summarization: A Systematic Literature Review","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2","json":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2.json","graph_json":"https://pith.science/api/pith-number/P2A4GJN6KZP4GQUDWPKNKL6CY2/graph.json","events_json":"https://pith.science/api/pith-number/P2A4GJN6KZP4GQUDWPKNKL6CY2/events.json","paper":"https://pith.science/paper/P2A4GJN6"},"agent_actions":{"view_html":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2","download_json":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2.json","view_paper":"https://pith.science/paper/P2A4GJN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05405&json=true","fetch_graph":"https://pith.science/api/pith-number/P2A4GJN6KZP4GQUDWPKNKL6CY2/graph.json","fetch_events":"https://pith.science/api/pith-number/P2A4GJN6KZP4GQUDWPKNKL6CY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2/action/storage_attestation","attest_author":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2/action/author_attestation","sign_citation":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2/action/citation_signature","submit_replication":"https://pith.science/pith/P2A4GJN6KZP4GQUDWPKNKL6CY2/action/replication_record"}},"created_at":"2026-07-05T02:39:56.474063+00:00","updated_at":"2026-07-05T02:39:56.474063+00:00"}