{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KCWGZGWSXHUYBMINDUKWFN7REO","short_pith_number":"pith:KCWGZGWS","schema_version":"1.0","canonical_sha256":"50ac6c9ad2b9e980b10d1d1562b7f12385aa4ccc75e16902562bf7049f9f69ce","source":{"kind":"arxiv","id":"2405.16072","version":4},"attestation_state":"computed","paper":{"title":"SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andre Ivanov, Seyed Arash Sheikholeslam","submitted_at":"2024-05-25T05:45:55Z","abstract_excerpt":"In this paper, we introduce SynthAI, a new method for the automated creation of High-Level Synthesis (HLS) designs. SynthAI integrates ReAct agents, Chain-of-Thought (CoT) prompting, web search technologies, and the Retrieval-Augmented Generation (RAG) framework within a structured decision graph. This innovative approach enables the systematic decomposition of complex hardware design tasks into multiple stages and smaller, manageable modules. As a result, SynthAI produces synthesizable designs that closely adhere to user-specified design objectives and functional requirements. We further vali"},"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":"2405.16072","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-25T05:45:55Z","cross_cats_sorted":[],"title_canon_sha256":"d4fa8650407ef3db87dff6c11719de6538de3e68941d836374b4613e4b3aafe4","abstract_canon_sha256":"ed8dedb22becfc2d6f7219c99820a9420ced12a303a23f80024e5aff359a3182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:31.103810Z","signature_b64":"kqhFjuV47HA1x1B/JRkaYd9jpx9xzKyDx1ly3UQ4NfQ1pjnaXH+VyildfWsuBIZSf5CxTno/Vnknh3OboBW7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50ac6c9ad2b9e980b10d1d1562b7f12385aa4ccc75e16902562bf7049f9f69ce","last_reissued_at":"2026-07-05T09:10:31.103358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:31.103358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andre Ivanov, Seyed Arash Sheikholeslam","submitted_at":"2024-05-25T05:45:55Z","abstract_excerpt":"In this paper, we introduce SynthAI, a new method for the automated creation of High-Level Synthesis (HLS) designs. SynthAI integrates ReAct agents, Chain-of-Thought (CoT) prompting, web search technologies, and the Retrieval-Augmented Generation (RAG) framework within a structured decision graph. This innovative approach enables the systematic decomposition of complex hardware design tasks into multiple stages and smaller, manageable modules. As a result, SynthAI produces synthesizable designs that closely adhere to user-specified design objectives and functional requirements. We further vali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16072","kind":"arxiv","version":4},"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/2405.16072/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":"2405.16072","created_at":"2026-07-05T09:10:31.103414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16072v4","created_at":"2026-07-05T09:10:31.103414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16072","created_at":"2026-07-05T09:10:31.103414+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCWGZGWSXHUY","created_at":"2026-07-05T09:10:31.103414+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCWGZGWSXHUYBMIN","created_at":"2026-07-05T09:10:31.103414+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCWGZGWS","created_at":"2026-07-05T09:10:31.103414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17128","citing_title":"Shift-Left High-Level Synthesis Verification via Knowledge-Augmented LLM Agent","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28409","citing_title":"Evidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and Verification","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13536","citing_title":"HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO","json":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO.json","graph_json":"https://pith.science/api/pith-number/KCWGZGWSXHUYBMINDUKWFN7REO/graph.json","events_json":"https://pith.science/api/pith-number/KCWGZGWSXHUYBMINDUKWFN7REO/events.json","paper":"https://pith.science/paper/KCWGZGWS"},"agent_actions":{"view_html":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO","download_json":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO.json","view_paper":"https://pith.science/paper/KCWGZGWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16072&json=true","fetch_graph":"https://pith.science/api/pith-number/KCWGZGWSXHUYBMINDUKWFN7REO/graph.json","fetch_events":"https://pith.science/api/pith-number/KCWGZGWSXHUYBMINDUKWFN7REO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO/action/storage_attestation","attest_author":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO/action/author_attestation","sign_citation":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO/action/citation_signature","submit_replication":"https://pith.science/pith/KCWGZGWSXHUYBMINDUKWFN7REO/action/replication_record"}},"created_at":"2026-07-05T09:10:31.103414+00:00","updated_at":"2026-07-05T09:10:31.103414+00:00"}