{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LI5OT243TXLCFWX2TBEP3O7TFQ","short_pith_number":"pith:LI5OT243","schema_version":"1.0","canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","source":{"kind":"arxiv","id":"2502.11460","version":1},"attestation_state":"computed","paper":{"title":"UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Demin Song, Kai Chen, Linyang Li, Peiji Li, Qipeng Guo, Xipeng Qiu, Yichuan Ma, Yunfan Shao","submitted_at":"2025-02-17T05:37:02Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale pre-training data and (ii) synthesizing instruction data through prompt engineering with powerful models. While pre-training data faces quality consistency issues, instruction-based synthesis suffers from limited instruction diversity and inherent biases of LLMs. To address this gap, we introduce UnitCoder, a systematic pipeline leveraging model-generated unit"},"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":"2502.11460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T05:37:02Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"0e6d3747f5fec3e3be37913137bb98322675904ce30e072636b3667061e37570","abstract_canon_sha256":"90a32a2f06ab35583a37f5a927d0d888b869c0b8fe610c010d17b151f576757d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:29.141429Z","signature_b64":"9wa10BmftgqqM2P0jMnQMQynDSl8wwfoAryXcitraT8IC5BalEGP3mzPwmlC/rjGP31z7a1rSLjqECXNXGoJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","last_reissued_at":"2026-07-05T10:15:29.140941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:29.140941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Demin Song, Kai Chen, Linyang Li, Peiji Li, Qipeng Guo, Xipeng Qiu, Yichuan Ma, Yunfan Shao","submitted_at":"2025-02-17T05:37:02Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale pre-training data and (ii) synthesizing instruction data through prompt engineering with powerful models. While pre-training data faces quality consistency issues, instruction-based synthesis suffers from limited instruction diversity and inherent biases of LLMs. To address this gap, we introduce UnitCoder, a systematic pipeline leveraging model-generated unit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11460","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/2502.11460/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":"2502.11460","created_at":"2026-07-05T10:15:29.140993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11460v1","created_at":"2026-07-05T10:15:29.140993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11460","created_at":"2026-07-05T10:15:29.140993+00:00"},{"alias_kind":"pith_short_12","alias_value":"LI5OT243TXLC","created_at":"2026-07-05T10:15:29.140993+00:00"},{"alias_kind":"pith_short_16","alias_value":"LI5OT243TXLCFWX2","created_at":"2026-07-05T10:15:29.140993+00:00"},{"alias_kind":"pith_short_8","alias_value":"LI5OT243","created_at":"2026-07-05T10:15:29.140993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06462","citing_title":"Benchmark Everything Everywhere All at Once","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ","json":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ.json","graph_json":"https://pith.science/api/pith-number/LI5OT243TXLCFWX2TBEP3O7TFQ/graph.json","events_json":"https://pith.science/api/pith-number/LI5OT243TXLCFWX2TBEP3O7TFQ/events.json","paper":"https://pith.science/paper/LI5OT243"},"agent_actions":{"view_html":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ","download_json":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ.json","view_paper":"https://pith.science/paper/LI5OT243","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11460&json=true","fetch_graph":"https://pith.science/api/pith-number/LI5OT243TXLCFWX2TBEP3O7TFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LI5OT243TXLCFWX2TBEP3O7TFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/action/storage_attestation","attest_author":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/action/author_attestation","sign_citation":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/action/citation_signature","submit_replication":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/action/replication_record"}},"created_at":"2026-07-05T10:15:29.140993+00:00","updated_at":"2026-07-05T10:15:29.140993+00:00"}