{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2YWZ3OWXBW7OLHWD2UXA55K2V","short_pith_number":"pith:Q2YWZ3OW","schema_version":"1.0","canonical_sha256":"86b16cedd6b86df72cf61ea97077aad5553c48df6eba5892622c65ce210b939b","source":{"kind":"arxiv","id":"2505.09062","version":1},"attestation_state":"computed","paper":{"title":"Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Eldan Cohen, Junda Zhao, Yuliang Song","submitted_at":"2025-05-14T01:46:56Z","abstract_excerpt":"Recent advancements in source code summarization have leveraged transformer-based pre-trained models, including Large Language Models of Code (LLMCs), to automate and improve the generation of code summaries. However, existing methods often focus on generating a single high-quality summary for a given source code, neglecting scenarios where the generated summary might be inadequate and alternative options are needed. In this paper, we introduce Variational Prefix Tuning (VPT), a novel approach that enhances pre-trained models' ability to generate diverse yet accurate sets of summaries, allowin"},"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":"2505.09062","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-14T01:46:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bf6881f67b63b3984eefb52daa8dde8237344fa2fdb98c51d5ea8f7ffc7218e0","abstract_canon_sha256":"14f8b96dfd239e4faaeaae05bd84375ff34bf5258b48b1b197c1b2b908f33b28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:24.580977Z","signature_b64":"qu+AVRo+baqsMkItf8zGUqbHJakrPq34QtoLlmDk+/P1vVZk/XWEPRwIuKg01wBtQJ/Bh66lgXXGp8+M77MVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b16cedd6b86df72cf61ea97077aad5553c48df6eba5892622c65ce210b939b","last_reissued_at":"2026-07-05T11:07:24.580427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:24.580427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Eldan Cohen, Junda Zhao, Yuliang Song","submitted_at":"2025-05-14T01:46:56Z","abstract_excerpt":"Recent advancements in source code summarization have leveraged transformer-based pre-trained models, including Large Language Models of Code (LLMCs), to automate and improve the generation of code summaries. However, existing methods often focus on generating a single high-quality summary for a given source code, neglecting scenarios where the generated summary might be inadequate and alternative options are needed. In this paper, we introduce Variational Prefix Tuning (VPT), a novel approach that enhances pre-trained models' ability to generate diverse yet accurate sets of summaries, allowin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09062","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/2505.09062/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":"2505.09062","created_at":"2026-07-05T11:07:24.580486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09062v1","created_at":"2026-07-05T11:07:24.580486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09062","created_at":"2026-07-05T11:07:24.580486+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2YWZ3OWXBW7","created_at":"2026-07-05T11:07:24.580486+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2YWZ3OWXBW7OLHW","created_at":"2026-07-05T11:07:24.580486+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2YWZ3OW","created_at":"2026-07-05T11:07:24.580486+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/Q2YWZ3OWXBW7OLHWD2UXA55K2V","json":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V.json","graph_json":"https://pith.science/api/pith-number/Q2YWZ3OWXBW7OLHWD2UXA55K2V/graph.json","events_json":"https://pith.science/api/pith-number/Q2YWZ3OWXBW7OLHWD2UXA55K2V/events.json","paper":"https://pith.science/paper/Q2YWZ3OW"},"agent_actions":{"view_html":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V","download_json":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V.json","view_paper":"https://pith.science/paper/Q2YWZ3OW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09062&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2YWZ3OWXBW7OLHWD2UXA55K2V/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2YWZ3OWXBW7OLHWD2UXA55K2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V/action/storage_attestation","attest_author":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V/action/author_attestation","sign_citation":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V/action/citation_signature","submit_replication":"https://pith.science/pith/Q2YWZ3OWXBW7OLHWD2UXA55K2V/action/replication_record"}},"created_at":"2026-07-05T11:07:24.580486+00:00","updated_at":"2026-07-05T11:07:24.580486+00:00"}