{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CXNZIAKMYLAEIOEKUEW5KAAGUI","short_pith_number":"pith:CXNZIAKM","canonical_record":{"source":{"id":"2311.16267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T19:17:39Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"8161039050f7f489c18be31ee84e3182c1fda3a078805697967ed246ea6d29a2","abstract_canon_sha256":"cad866895f0ec2ff36548eb1b983eb27fac6f5f62e7019094c7d41c5a2ba7741"},"schema_version":"1.0"},"canonical_sha256":"15db94014cc2c044388aa12dd50006a22335ab102f5c8e4502d040ba815dc684","source":{"kind":"arxiv","id":"2311.16267","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16267","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16267v2","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16267","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"CXNZIAKMYLAE","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"pith_short_16","alias_value":"CXNZIAKMYLAEIOEK","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"pith_short_8","alias_value":"CXNZIAKM","created_at":"2026-07-05T07:38:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CXNZIAKMYLAEIOEKUEW5KAAGUI","target":"record","payload":{"canonical_record":{"source":{"id":"2311.16267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T19:17:39Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"8161039050f7f489c18be31ee84e3182c1fda3a078805697967ed246ea6d29a2","abstract_canon_sha256":"cad866895f0ec2ff36548eb1b983eb27fac6f5f62e7019094c7d41c5a2ba7741"},"schema_version":"1.0"},"canonical_sha256":"15db94014cc2c044388aa12dd50006a22335ab102f5c8e4502d040ba815dc684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:53.325702Z","signature_b64":"st5tunl8HcoGxQlUXpmwFT/l/wNin5XrKU/xh/ICQ+0TpTLXyMsEm+ON6pyipQR0bc+1DXRBoz8P/Evv4/NwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15db94014cc2c044388aa12dd50006a22335ab102f5c8e4502d040ba815dc684","last_reissued_at":"2026-07-05T07:38:53.324824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:53.324824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.16267","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPtilMEh8Lr5wlxUeO0zsaDcKYMgv9kRw+fmFQpnRddfEmuxvmA04Pd46TjKAlox2YMD6hDZZoe/jwle2X6rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:47:21.369693Z"},"content_sha256":"1acbdc7412144672f0487d8fac6c8d89d3bef43b951392361809cfa71ecf4b68","schema_version":"1.0","event_id":"sha256:1acbdc7412144672f0487d8fac6c8d89d3bef43b951392361809cfa71ecf4b68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CXNZIAKMYLAEIOEKUEW5KAAGUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Akhilesh Kumar, Chao Wang, Haiyang He, Jyh-Shing Roger Jang, Muhammad Zakir, Norman Chang, Rucha Apte, Wenliang Zhang, Yu-Chen Lin","submitted_at":"2023-11-27T19:17:39Z","abstract_excerpt":"We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation of embeddings' space; (ii) introducing the Chain of Density for Renovation Credibility (CoDRC), driven by LLMs, and the Adaptive Text Renovation (ATR) algorithm for assessing data renovation reliability; (iii) developing the Implicit Knowledge Expansion and Contemplation (IKEC) Prompt technique; and (iv) effectively refactoring existing scripts to generate ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16267","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/2311.16267/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LqEFyrr14S5QBtlEgt5465p170m2LCRSXMLp2+FRnNv/yZfRy5s54ReZmGKmpddvfa8mD1E5TUXFCa/GFEzIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:47:21.370055Z"},"content_sha256":"a9001fdcf97083264f8dbf00fdfb33fb1cd6bbf639683f674bc255b637b712e5","schema_version":"1.0","event_id":"sha256:a9001fdcf97083264f8dbf00fdfb33fb1cd6bbf639683f674bc255b637b712e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI/bundle.json","state_url":"https://pith.science/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-10T09:47:21Z","links":{"resolver":"https://pith.science/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI","bundle":"https://pith.science/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI/bundle.json","state":"https://pith.science/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXNZIAKMYLAEIOEKUEW5KAAGUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CXNZIAKMYLAEIOEKUEW5KAAGUI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cad866895f0ec2ff36548eb1b983eb27fac6f5f62e7019094c7d41c5a2ba7741","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T19:17:39Z","title_canon_sha256":"8161039050f7f489c18be31ee84e3182c1fda3a078805697967ed246ea6d29a2"},"schema_version":"1.0","source":{"id":"2311.16267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16267","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16267v2","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16267","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"CXNZIAKMYLAE","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"pith_short_16","alias_value":"CXNZIAKMYLAEIOEK","created_at":"2026-07-05T07:38:53Z"},{"alias_kind":"pith_short_8","alias_value":"CXNZIAKM","created_at":"2026-07-05T07:38:53Z"}],"graph_snapshots":[{"event_id":"sha256:a9001fdcf97083264f8dbf00fdfb33fb1cd6bbf639683f674bc255b637b712e5","target":"graph","created_at":"2026-07-05T07:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.16267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation of embeddings' space; (ii) introducing the Chain of Density for Renovation Credibility (CoDRC), driven by LLMs, and the Adaptive Text Renovation (ATR) algorithm for assessing data renovation reliability; (iii) developing the Implicit Knowledge Expansion and Contemplation (IKEC) Prompt technique; and (iv) effectively refactoring existing scripts to generate ne","authors_text":"Akhilesh Kumar, Chao Wang, Haiyang He, Jyh-Shing Roger Jang, Muhammad Zakir, Norman Chang, Rucha Apte, Wenliang Zhang, Yu-Chen Lin","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T19:17:39Z","title":"Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16267","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1acbdc7412144672f0487d8fac6c8d89d3bef43b951392361809cfa71ecf4b68","target":"record","created_at":"2026-07-05T07:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cad866895f0ec2ff36548eb1b983eb27fac6f5f62e7019094c7d41c5a2ba7741","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T19:17:39Z","title_canon_sha256":"8161039050f7f489c18be31ee84e3182c1fda3a078805697967ed246ea6d29a2"},"schema_version":"1.0","source":{"id":"2311.16267","kind":"arxiv","version":2}},"canonical_sha256":"15db94014cc2c044388aa12dd50006a22335ab102f5c8e4502d040ba815dc684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15db94014cc2c044388aa12dd50006a22335ab102f5c8e4502d040ba815dc684","first_computed_at":"2026-07-05T07:38:53.324824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:53.324824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"st5tunl8HcoGxQlUXpmwFT/l/wNin5XrKU/xh/ICQ+0TpTLXyMsEm+ON6pyipQR0bc+1DXRBoz8P/Evv4/NwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:53.325702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1acbdc7412144672f0487d8fac6c8d89d3bef43b951392361809cfa71ecf4b68","sha256:a9001fdcf97083264f8dbf00fdfb33fb1cd6bbf639683f674bc255b637b712e5"],"state_sha256":"0854001670484c66f7e76646125b92a1369ba8127ff5abd1ebe609ac5a9d77a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dd7Ylt5YT1FoCLfB+4anHTesV6tFqLEN+OBoLADyk9lNIU8WLwa2AcvcqE/htQLSBE2iYIVsXN6ACJRf9BxLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T09:47:21.371896Z","bundle_sha256":"f852bc79f3e3918d068e98ca59f6f852a50f57ada03fa3216a3ecec2a05da8cb"}}