{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4D6AGN3IYYTJACEICYSA4HR7K","short_pith_number":"pith:T4D6AGN3","schema_version":"1.0","canonical_sha256":"9f07e019bb463134804440b12070f1fab345bf31bb57706e9363abd95fbdf22b","source":{"kind":"arxiv","id":"2407.15353","version":2},"attestation_state":"computed","paper":{"title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.CL","authors_text":"Bei Yu, Haoyuan Wu, Tairu Qiu, Yuan Pu, Zhuolun He","submitted_at":"2024-07-22T03:44:27Z","abstract_excerpt":"Retrieval augmented generation (RAG) enhances the accuracy and reliability of generative AI models by sourcing factual information from external databases, which is extensively employed in document-grounded question-answering (QA) tasks. Off-the-shelf RAG flows are well pretrained on general-purpose documents, yet they encounter significant challenges when being applied to knowledge-intensive vertical domains, such as electronic design automation (EDA). This paper addresses such issue by proposing a customized RAG framework along with three domain-specific techniques for EDA tool documentation"},"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":"2407.15353","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T03:44:27Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"f9caeb510e0170997f65f770e71a1ea0711cfd29b4c8d7e2c97500c8b4262b43","abstract_canon_sha256":"d44bb91d7bb3e6cf513a66d4ec46db82cc48f0b25d4c0148935d1059f071aa1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:45.872182Z","signature_b64":"uqbyurQlUsf/QZ37Zkyjw8B96DPIP7Jc6OP3qfS5b/7gVlBwElmUo67zX5Jh0LWq7oe7hmRAnWPBoxAmb5SLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f07e019bb463134804440b12070f1fab345bf31bb57706e9363abd95fbdf22b","last_reissued_at":"2026-07-05T08:48:45.871775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:45.871775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.CL","authors_text":"Bei Yu, Haoyuan Wu, Tairu Qiu, Yuan Pu, Zhuolun He","submitted_at":"2024-07-22T03:44:27Z","abstract_excerpt":"Retrieval augmented generation (RAG) enhances the accuracy and reliability of generative AI models by sourcing factual information from external databases, which is extensively employed in document-grounded question-answering (QA) tasks. Off-the-shelf RAG flows are well pretrained on general-purpose documents, yet they encounter significant challenges when being applied to knowledge-intensive vertical domains, such as electronic design automation (EDA). This paper addresses such issue by proposing a customized RAG framework along with three domain-specific techniques for EDA tool documentation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15353","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/2407.15353/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":"2407.15353","created_at":"2026-07-05T08:48:45.871833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15353v2","created_at":"2026-07-05T08:48:45.871833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15353","created_at":"2026-07-05T08:48:45.871833+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4D6AGN3IYYT","created_at":"2026-07-05T08:48:45.871833+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4D6AGN3IYYTJACE","created_at":"2026-07-05T08:48:45.871833+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4D6AGN3","created_at":"2026-07-05T08:48:45.871833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24930","citing_title":"H$^{2}$MT: Semantic Hierarchy-Aware Hierarchical Memory Transformer","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26498","citing_title":"Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27415","citing_title":"ChipLingo: A Systematic Training Framework for Large Language Models in EDA","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K","json":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K.json","graph_json":"https://pith.science/api/pith-number/T4D6AGN3IYYTJACEICYSA4HR7K/graph.json","events_json":"https://pith.science/api/pith-number/T4D6AGN3IYYTJACEICYSA4HR7K/events.json","paper":"https://pith.science/paper/T4D6AGN3"},"agent_actions":{"view_html":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K","download_json":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K.json","view_paper":"https://pith.science/paper/T4D6AGN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15353&json=true","fetch_graph":"https://pith.science/api/pith-number/T4D6AGN3IYYTJACEICYSA4HR7K/graph.json","fetch_events":"https://pith.science/api/pith-number/T4D6AGN3IYYTJACEICYSA4HR7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K/action/storage_attestation","attest_author":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K/action/author_attestation","sign_citation":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K/action/citation_signature","submit_replication":"https://pith.science/pith/T4D6AGN3IYYTJACEICYSA4HR7K/action/replication_record"}},"created_at":"2026-07-05T08:48:45.871833+00:00","updated_at":"2026-07-05T08:48:45.871833+00:00"}