{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I64NW4XDBGNNVPXCGRMJFXD724","short_pith_number":"pith:I64NW4XD","schema_version":"1.0","canonical_sha256":"47b8db72e3099adabee2345892dc7fd70663650f6cb225de1035c8ee1b510d35","source":{"kind":"arxiv","id":"2406.00037","version":1},"attestation_state":"computed","paper":{"title":"Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongyu Yang, Jiahui Hou, Jianhui Ma, Junda Zhao, Liyang He, Min Hou, Rui Li, Shuanghong Shen","submitted_at":"2024-05-27T14:21:31Z","abstract_excerpt":"Code Community Question Answering (CCQA) seeks to tackle programming-related issues, thereby boosting productivity in both software engineering and academic research. Recent advancements in Reinforcement Learning from Human Feedback (RLHF) have transformed the fine-tuning process of Large Language Models (LLMs) to produce responses that closely mimic human behavior. Leveraging LLMs with RLHF for practical CCQA applications has thus emerged as a promising area of study. Unlike standard code question-answering tasks, CCQA involves multiple possible answers, with varying user preferences for each"},"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":"2406.00037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T14:21:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29785c7595289636da4b9e41cbfcd163141f7f199bb8783ac52453063cbb2e39","abstract_canon_sha256":"f9d67e34021c8f5dbcc7548514b25729e0068a81cfc2565187bedc6351f35077"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:55.880997Z","signature_b64":"iLO5KQrG+yfeFW1a75c6MGNpo2mOU4KlQ7r/Uot1dOVJ4XGH7AVRKw/+tdfxGqL3UWiwpjH22WvMrLf0U1XcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47b8db72e3099adabee2345892dc7fd70663650f6cb225de1035c8ee1b510d35","last_reissued_at":"2026-07-05T08:25:55.880463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:55.880463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongyu Yang, Jiahui Hou, Jianhui Ma, Junda Zhao, Liyang He, Min Hou, Rui Li, Shuanghong Shen","submitted_at":"2024-05-27T14:21:31Z","abstract_excerpt":"Code Community Question Answering (CCQA) seeks to tackle programming-related issues, thereby boosting productivity in both software engineering and academic research. Recent advancements in Reinforcement Learning from Human Feedback (RLHF) have transformed the fine-tuning process of Large Language Models (LLMs) to produce responses that closely mimic human behavior. Leveraging LLMs with RLHF for practical CCQA applications has thus emerged as a promising area of study. Unlike standard code question-answering tasks, CCQA involves multiple possible answers, with varying user preferences for each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00037","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/2406.00037/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":"2406.00037","created_at":"2026-07-05T08:25:55.880526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00037v1","created_at":"2026-07-05T08:25:55.880526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00037","created_at":"2026-07-05T08:25:55.880526+00:00"},{"alias_kind":"pith_short_12","alias_value":"I64NW4XDBGNN","created_at":"2026-07-05T08:25:55.880526+00:00"},{"alias_kind":"pith_short_16","alias_value":"I64NW4XDBGNNVPXC","created_at":"2026-07-05T08:25:55.880526+00:00"},{"alias_kind":"pith_short_8","alias_value":"I64NW4XD","created_at":"2026-07-05T08:25:55.880526+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/I64NW4XDBGNNVPXCGRMJFXD724","json":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724.json","graph_json":"https://pith.science/api/pith-number/I64NW4XDBGNNVPXCGRMJFXD724/graph.json","events_json":"https://pith.science/api/pith-number/I64NW4XDBGNNVPXCGRMJFXD724/events.json","paper":"https://pith.science/paper/I64NW4XD"},"agent_actions":{"view_html":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724","download_json":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724.json","view_paper":"https://pith.science/paper/I64NW4XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00037&json=true","fetch_graph":"https://pith.science/api/pith-number/I64NW4XDBGNNVPXCGRMJFXD724/graph.json","fetch_events":"https://pith.science/api/pith-number/I64NW4XDBGNNVPXCGRMJFXD724/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724/action/storage_attestation","attest_author":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724/action/author_attestation","sign_citation":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724/action/citation_signature","submit_replication":"https://pith.science/pith/I64NW4XDBGNNVPXCGRMJFXD724/action/replication_record"}},"created_at":"2026-07-05T08:25:55.880526+00:00","updated_at":"2026-07-05T08:25:55.880526+00:00"}