{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YMCQCRTAMN2SJG5TTZLAY4UPBI","short_pith_number":"pith:YMCQCRTA","schema_version":"1.0","canonical_sha256":"c3050146606375249bb39e560c728f0a10e0db70e2672981b4a5374cdb5056ec","source":{"kind":"arxiv","id":"2601.19072","version":3},"attestation_state":"computed","paper":{"title":"HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hong Yi Lin, Kla Tantithamthavorn, Ming Wu, Minwoo Jeong, Patanamon Thongtanunam, Wachiraphan Charoenwet","submitted_at":"2026-01-27T01:16:45Z","abstract_excerpt":"Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations -- where the generated review comments are ungrounded in the actual code -- poses a significant challenge to the adoption of LLMs in code review workflows. To address this, we explore effective and scalable methods for a hallucination detection in LLM-generated code review comments without the reference. In this work, we design HalluJudge that aims to assess the grounding of generated review comments based on the context alignment. HalluJ"},"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":"2601.19072","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-01-27T01:16:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57566f1a2f7eb74c7e1c985eaf62e0187c7f970aeb8b67553c4dc1614db83b52","abstract_canon_sha256":"db7b31ab3bef765c172f968ffcdc81a153e3e31a27eee310166a2ef8e92168b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:21.633269Z","signature_b64":"aarS+L0EvY4ZL4vmoFknBETAyRH6wFFzIL2WofeiMC5/jWcRtDtELgmZqbbeTpe32i6aERNI/4qyMNiefLziDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3050146606375249bb39e560c728f0a10e0db70e2672981b4a5374cdb5056ec","last_reissued_at":"2026-06-12T01:08:21.632101Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:21.632101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hong Yi Lin, Kla Tantithamthavorn, Ming Wu, Minwoo Jeong, Patanamon Thongtanunam, Wachiraphan Charoenwet","submitted_at":"2026-01-27T01:16:45Z","abstract_excerpt":"Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations -- where the generated review comments are ungrounded in the actual code -- poses a significant challenge to the adoption of LLMs in code review workflows. To address this, we explore effective and scalable methods for a hallucination detection in LLM-generated code review comments without the reference. In this work, we design HalluJudge that aims to assess the grounding of generated review comments based on the context alignment. HalluJ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.19072","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/2601.19072/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":"2601.19072","created_at":"2026-06-12T01:08:21.632272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.19072v3","created_at":"2026-06-12T01:08:21.632272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19072","created_at":"2026-06-12T01:08:21.632272+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMCQCRTAMN2S","created_at":"2026-06-12T01:08:21.632272+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMCQCRTAMN2SJG5T","created_at":"2026-06-12T01:08:21.632272+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMCQCRTA","created_at":"2026-06-12T01:08:21.632272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.28500","citing_title":"Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24525","citing_title":"Understanding the Limits of Automated Evaluation for Code Review Bots in Practice","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI","json":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI.json","graph_json":"https://pith.science/api/pith-number/YMCQCRTAMN2SJG5TTZLAY4UPBI/graph.json","events_json":"https://pith.science/api/pith-number/YMCQCRTAMN2SJG5TTZLAY4UPBI/events.json","paper":"https://pith.science/paper/YMCQCRTA"},"agent_actions":{"view_html":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI","download_json":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI.json","view_paper":"https://pith.science/paper/YMCQCRTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.19072&json=true","fetch_graph":"https://pith.science/api/pith-number/YMCQCRTAMN2SJG5TTZLAY4UPBI/graph.json","fetch_events":"https://pith.science/api/pith-number/YMCQCRTAMN2SJG5TTZLAY4UPBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI/action/storage_attestation","attest_author":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI/action/author_attestation","sign_citation":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI/action/citation_signature","submit_replication":"https://pith.science/pith/YMCQCRTAMN2SJG5TTZLAY4UPBI/action/replication_record"}},"created_at":"2026-06-12T01:08:21.632272+00:00","updated_at":"2026-06-12T01:08:21.632272+00:00"}