{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W6GDWWTBBDAAK2GJXBICBXN6L2","short_pith_number":"pith:W6GDWWTB","schema_version":"1.0","canonical_sha256":"b78c3b5a6108c00568c9b85020ddbe5eb0b323dc71d41ed9200789b289a9b3a3","source":{"kind":"arxiv","id":"2310.10698","version":2},"attestation_state":"computed","paper":{"title":"Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shanshan Li, Xiangke Liao, Yingwei Ma, Yong Guo, Yuanliang Zhang, Yue Yu, Yu Jiang, Yutao Xie","submitted_at":"2023-10-16T05:09:58Z","abstract_excerpt":"Large language models (LLMs) have showcased remarkable prowess in code generation. However, automated code generation is still challenging since it requires a high-level semantic mapping between natural language requirements and codes. Most existing LLMs-based approaches for code generation rely on decoder-only causal language models often treate codes merely as plain text tokens, i.e., feeding the requirements as a prompt input, and outputing code as flat sequence of tokens, potentially missing the rich semantic features inherent in source code. To bridge this gap, this paper proposes the \"Se"},"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":"2310.10698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T05:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"c883268b67e75d7001bee5f5321009c4fa63696364970a1531d6504e30d3628f","abstract_canon_sha256":"bda74d1fffb4c63c1030d9f38dbb1640d7a335cadcabac6cad812314047928fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:32.513993Z","signature_b64":"QoJCeQDjlUfV8pJS+D8UwHhILUR9ktyw8MLaPo6dGIXylZz9q7Sg90FABwhQD97E+K3ZIx6MioaT188yv8u0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b78c3b5a6108c00568c9b85020ddbe5eb0b323dc71d41ed9200789b289a9b3a3","last_reissued_at":"2026-07-05T07:03:32.513535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:32.513535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shanshan Li, Xiangke Liao, Yingwei Ma, Yong Guo, Yuanliang Zhang, Yue Yu, Yu Jiang, Yutao Xie","submitted_at":"2023-10-16T05:09:58Z","abstract_excerpt":"Large language models (LLMs) have showcased remarkable prowess in code generation. However, automated code generation is still challenging since it requires a high-level semantic mapping between natural language requirements and codes. Most existing LLMs-based approaches for code generation rely on decoder-only causal language models often treate codes merely as plain text tokens, i.e., feeding the requirements as a prompt input, and outputing code as flat sequence of tokens, potentially missing the rich semantic features inherent in source code. To bridge this gap, this paper proposes the \"Se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10698","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/2310.10698/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":"2310.10698","created_at":"2026-07-05T07:03:32.513592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10698v2","created_at":"2026-07-05T07:03:32.513592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10698","created_at":"2026-07-05T07:03:32.513592+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6GDWWTBBDAA","created_at":"2026-07-05T07:03:32.513592+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6GDWWTBBDAAK2GJ","created_at":"2026-07-05T07:03:32.513592+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6GDWWTB","created_at":"2026-07-05T07:03:32.513592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2","json":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2.json","graph_json":"https://pith.science/api/pith-number/W6GDWWTBBDAAK2GJXBICBXN6L2/graph.json","events_json":"https://pith.science/api/pith-number/W6GDWWTBBDAAK2GJXBICBXN6L2/events.json","paper":"https://pith.science/paper/W6GDWWTB"},"agent_actions":{"view_html":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2","download_json":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2.json","view_paper":"https://pith.science/paper/W6GDWWTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10698&json=true","fetch_graph":"https://pith.science/api/pith-number/W6GDWWTBBDAAK2GJXBICBXN6L2/graph.json","fetch_events":"https://pith.science/api/pith-number/W6GDWWTBBDAAK2GJXBICBXN6L2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2/action/storage_attestation","attest_author":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2/action/author_attestation","sign_citation":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2/action/citation_signature","submit_replication":"https://pith.science/pith/W6GDWWTBBDAAK2GJXBICBXN6L2/action/replication_record"}},"created_at":"2026-07-05T07:03:32.513592+00:00","updated_at":"2026-07-05T07:03:32.513592+00:00"}