{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IGQ4SMZP5BT3TFUILG7P55NOPO","short_pith_number":"pith:IGQ4SMZP","schema_version":"1.0","canonical_sha256":"41a1c9332fe867b9968859befef5ae7bb7586befd14f976823233519f53818ae","source":{"kind":"arxiv","id":"2311.07957","version":2},"attestation_state":"computed","paper":{"title":"Language Models are Better Bug Detector Through Code-Pair Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Ahmed Binjahlan, Kamel Alrashedy","submitted_at":"2023-11-14T07:20:57Z","abstract_excerpt":"Large language models (LLMs) such as GPT-3.5 and CodeLlama are powerful models for code generation and understanding. Fine-tuning these models comes with a high computational cost and requires a large labeled dataset. Alternatively, in-context learning techniques allow models to learn downstream tasks with only a few examples. Recently, researchers have shown how in-context learning performs well in bug detection and repair. In this paper, we propose code-pair classification task in which both the buggy and non-buggy versions are given to the model, and the model identifies the buggy ones. We "},"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":"2311.07957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-11-14T07:20:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e59e8784c8f5d736cc9aafc4dfe32862068fc8d18d3a2440857d8bd7ef71e1d1","abstract_canon_sha256":"a05a2f863acfa847c04dfc34165762721d000635c1a5c6f785b61de869cffb6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:32.511194Z","signature_b64":"+nvbz1ShZ9BpWVZVhcy0sOYXl46Uw7XToASCYfDd8/vQKNE2bmrDoASjPl9sJYivnx/wtKF6A64W50nmPIf+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41a1c9332fe867b9968859befef5ae7bb7586befd14f976823233519f53818ae","last_reissued_at":"2026-07-05T07:38:32.510781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:32.510781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models are Better Bug Detector Through Code-Pair Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Ahmed Binjahlan, Kamel Alrashedy","submitted_at":"2023-11-14T07:20:57Z","abstract_excerpt":"Large language models (LLMs) such as GPT-3.5 and CodeLlama are powerful models for code generation and understanding. Fine-tuning these models comes with a high computational cost and requires a large labeled dataset. Alternatively, in-context learning techniques allow models to learn downstream tasks with only a few examples. Recently, researchers have shown how in-context learning performs well in bug detection and repair. In this paper, we propose code-pair classification task in which both the buggy and non-buggy versions are given to the model, and the model identifies the buggy ones. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07957","kind":"arxiv","version":2},"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/2311.07957/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":"2311.07957","created_at":"2026-07-05T07:38:32.510836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07957v2","created_at":"2026-07-05T07:38:32.510836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07957","created_at":"2026-07-05T07:38:32.510836+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGQ4SMZP5BT3","created_at":"2026-07-05T07:38:32.510836+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGQ4SMZP5BT3TFUI","created_at":"2026-07-05T07:38:32.510836+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGQ4SMZP","created_at":"2026-07-05T07:38:32.510836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18245","citing_title":"Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO","json":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO.json","graph_json":"https://pith.science/api/pith-number/IGQ4SMZP5BT3TFUILG7P55NOPO/graph.json","events_json":"https://pith.science/api/pith-number/IGQ4SMZP5BT3TFUILG7P55NOPO/events.json","paper":"https://pith.science/paper/IGQ4SMZP"},"agent_actions":{"view_html":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO","download_json":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO.json","view_paper":"https://pith.science/paper/IGQ4SMZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07957&json=true","fetch_graph":"https://pith.science/api/pith-number/IGQ4SMZP5BT3TFUILG7P55NOPO/graph.json","fetch_events":"https://pith.science/api/pith-number/IGQ4SMZP5BT3TFUILG7P55NOPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO/action/storage_attestation","attest_author":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO/action/author_attestation","sign_citation":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO/action/citation_signature","submit_replication":"https://pith.science/pith/IGQ4SMZP5BT3TFUILG7P55NOPO/action/replication_record"}},"created_at":"2026-07-05T07:38:32.510836+00:00","updated_at":"2026-07-05T07:38:32.510836+00:00"}