{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I7XTANKHLGPAOXZK3OBVG5WNJ6","short_pith_number":"pith:I7XTANKH","schema_version":"1.0","canonical_sha256":"47ef303547599e075f2adb835376cd4fbae10770bde5e791ffc7b4f54754295e","source":{"kind":"arxiv","id":"2308.01240","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junwei Liu, Mingwei Liu, Qiancheng Zi, Xin Peng, Yiling Lou, Zhiqiang Yuan","submitted_at":"2023-08-02T15:54:22Z","abstract_excerpt":"In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code comprehension and generation tasks and sometimes even better than small SOTA models specifically fine-tuned on each downstream task. We also find that larger instructed LLMs are not always better on code-related tasks. Second, for the few-shot setting, we find that adding demonstration examples substantially helps instructed LLMs perform better on most code com"},"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":"2308.01240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-02T15:54:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10d4b6cb250a9b236370d4f65ad418cd838295de4086883a784f0a7a54942bb4","abstract_canon_sha256":"819a4a013e5189e74355c46fa18285fb3f8063e16c8ce220d751558bc49136b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:07.677911Z","signature_b64":"fpr5x7l98vvK0brL9oUvIm7ztIkpRbCYfXjWzxZCVWVocHEsFCNkteqDzMiY+c6F8NowOmosLdCeVxOatLjtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47ef303547599e075f2adb835376cd4fbae10770bde5e791ffc7b4f54754295e","last_reissued_at":"2026-07-05T06:37:07.677476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:07.677476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junwei Liu, Mingwei Liu, Qiancheng Zi, Xin Peng, Yiling Lou, Zhiqiang Yuan","submitted_at":"2023-08-02T15:54:22Z","abstract_excerpt":"In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code comprehension and generation tasks and sometimes even better than small SOTA models specifically fine-tuned on each downstream task. We also find that larger instructed LLMs are not always better on code-related tasks. Second, for the few-shot setting, we find that adding demonstration examples substantially helps instructed LLMs perform better on most code com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01240","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/2308.01240/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":"2308.01240","created_at":"2026-07-05T06:37:07.677530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01240v1","created_at":"2026-07-05T06:37:07.677530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01240","created_at":"2026-07-05T06:37:07.677530+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7XTANKHLGPA","created_at":"2026-07-05T06:37:07.677530+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7XTANKHLGPAOXZK","created_at":"2026-07-05T06:37:07.677530+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7XTANKH","created_at":"2026-07-05T06:37:07.677530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07925","citing_title":"ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05384","citing_title":"Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2411.09916","citing_title":"\"Should I Give Up Now?\" Investigating LLM Pitfalls in Software Engineering","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13076","citing_title":"LLM Evaluators Recognize and Favor Their Own Generations","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08980","citing_title":"AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10956","citing_title":"Project-Level C-to-Rust Translation via Pointer Knowledge Graphs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02977","citing_title":"Large Language Model-Based Agents for Software Engineering: A Survey","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6","json":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6.json","graph_json":"https://pith.science/api/pith-number/I7XTANKHLGPAOXZK3OBVG5WNJ6/graph.json","events_json":"https://pith.science/api/pith-number/I7XTANKHLGPAOXZK3OBVG5WNJ6/events.json","paper":"https://pith.science/paper/I7XTANKH"},"agent_actions":{"view_html":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6","download_json":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6.json","view_paper":"https://pith.science/paper/I7XTANKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01240&json=true","fetch_graph":"https://pith.science/api/pith-number/I7XTANKHLGPAOXZK3OBVG5WNJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/I7XTANKHLGPAOXZK3OBVG5WNJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6/action/storage_attestation","attest_author":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6/action/author_attestation","sign_citation":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6/action/citation_signature","submit_replication":"https://pith.science/pith/I7XTANKHLGPAOXZK3OBVG5WNJ6/action/replication_record"}},"created_at":"2026-07-05T06:37:07.677530+00:00","updated_at":"2026-07-05T06:37:07.677530+00:00"}