{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZMQVBSMOUGJWMDHQYZSOILOG5","short_pith_number":"pith:DZMQVBSM","schema_version":"1.0","canonical_sha256":"1e590a864c750c9b3067863327216e37545e15ebf5ca5dbdfcb12efccf1126ac","source":{"kind":"arxiv","id":"2412.08109","version":2},"attestation_state":"computed","paper":{"title":"Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chaopeng Luo, Chong Wang, Jie Song, Ke Liu, Rulin Xu, Shanshan Li, Si Zheng, Xiangbing Huang, Xiangke Liao, Yifan Xie, Yitong Liu, Yuanliang Zhang, Zhizheng Zheng, Zhouyang Jia","submitted_at":"2024-12-11T05:31:39Z","abstract_excerpt":"Recently, large language models (LLMs) have shown strong potential in code generation tasks. However, there are still gaps before they can be fully applied in actual software development processes. Accurately assessing the code generation capabilities of large language models has become an important basis for evaluating and improving the models. Some existing works have constructed datasets to evaluate the capabilities of these models. However, the current evaluation process may encounter the illusion of \"Specialist in Familiarity\", primarily due to three gaps: the exposure of target code, cas"},"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":"2412.08109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-11T05:31:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3cc1bf6b7225c5e99144f8576d4420d19021cd4227afe0b7a2a2c45b46848419","abstract_canon_sha256":"00e056fd46cdf7c12e05175eeb5693d31aa2bc40ba852ec2c1ee3573c2dc4c51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:18.306438Z","signature_b64":"Ho7tNrNNwglBlN3rJkDUG9PHxloqodzoLlGg0IWIzJMJCeX574hD2evS8xyRZ9Aflr6xsQtdcfKCi3csVkGpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e590a864c750c9b3067863327216e37545e15ebf5ca5dbdfcb12efccf1126ac","last_reissued_at":"2026-07-05T10:01:18.305784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:18.305784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chaopeng Luo, Chong Wang, Jie Song, Ke Liu, Rulin Xu, Shanshan Li, Si Zheng, Xiangbing Huang, Xiangke Liao, Yifan Xie, Yitong Liu, Yuanliang Zhang, Zhizheng Zheng, Zhouyang Jia","submitted_at":"2024-12-11T05:31:39Z","abstract_excerpt":"Recently, large language models (LLMs) have shown strong potential in code generation tasks. However, there are still gaps before they can be fully applied in actual software development processes. Accurately assessing the code generation capabilities of large language models has become an important basis for evaluating and improving the models. Some existing works have constructed datasets to evaluate the capabilities of these models. However, the current evaluation process may encounter the illusion of \"Specialist in Familiarity\", primarily due to three gaps: the exposure of target code, cas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08109","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/2412.08109/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":"2412.08109","created_at":"2026-07-05T10:01:18.305859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08109v2","created_at":"2026-07-05T10:01:18.305859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08109","created_at":"2026-07-05T10:01:18.305859+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZMQVBSMOUGJ","created_at":"2026-07-05T10:01:18.305859+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZMQVBSMOUGJWMDH","created_at":"2026-07-05T10:01:18.305859+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZMQVBSM","created_at":"2026-07-05T10:01:18.305859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":151,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5","json":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5.json","graph_json":"https://pith.science/api/pith-number/DZMQVBSMOUGJWMDHQYZSOILOG5/graph.json","events_json":"https://pith.science/api/pith-number/DZMQVBSMOUGJWMDHQYZSOILOG5/events.json","paper":"https://pith.science/paper/DZMQVBSM"},"agent_actions":{"view_html":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5","download_json":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5.json","view_paper":"https://pith.science/paper/DZMQVBSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08109&json=true","fetch_graph":"https://pith.science/api/pith-number/DZMQVBSMOUGJWMDHQYZSOILOG5/graph.json","fetch_events":"https://pith.science/api/pith-number/DZMQVBSMOUGJWMDHQYZSOILOG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5/action/storage_attestation","attest_author":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5/action/author_attestation","sign_citation":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5/action/citation_signature","submit_replication":"https://pith.science/pith/DZMQVBSMOUGJWMDHQYZSOILOG5/action/replication_record"}},"created_at":"2026-07-05T10:01:18.305859+00:00","updated_at":"2026-07-05T10:01:18.305859+00:00"}