{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CDP7BVIVQ5WS7D2FSTI6T74RKJ","short_pith_number":"pith:CDP7BVIV","schema_version":"1.0","canonical_sha256":"10dff0d515876d2f8f4594d1e9ff915244c41de46b4718fd10ea9ed2208c794d","source":{"kind":"arxiv","id":"2507.03255","version":3},"attestation_state":"computed","paper":{"title":"ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Chen Zhang, Jieru Zhao, Mingzhe Gao, Qiang Xu, Zedong Peng, Zeju Li","submitted_at":"2025-07-04T02:23:46Z","abstract_excerpt":"High-Level Synthesis (HLS) plays a crucial role in modern hardware design by transforming high-level code into optimized hardware implementations. However, progress in applying machine learning (ML) to HLS optimization has been hindered by a shortage of sufficiently large and diverse datasets. To bridge this gap, we introduce ForgeHLS, a large-scale, open-source dataset explicitly designed for ML-driven HLS research. ForgeHLS comprises over 400k diverse designs generated from 846 kernels covering a broad range of application domains, consuming over 200k CPU hours during dataset construction. E"},"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":"2507.03255","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-07-04T02:23:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4036da8977f438f7bcaa118a81700b776be9ad21f0394428144c19add2684bd6","abstract_canon_sha256":"b130f283ecd26e9b5115f8f08436d9d6be7f8b14a0796dbf6059c1d92c1dc2d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:04.969948Z","signature_b64":"DaUtHz7j5/d+ZDNxgjM2JRYhCQmsuKTIWioZ7X3OjJbH9fjBrP+1Hy6U6GUQ/n9YG+kICZwbpaN95tmcbM5oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10dff0d515876d2f8f4594d1e9ff915244c41de46b4718fd10ea9ed2208c794d","last_reissued_at":"2026-07-05T11:48:04.969418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:04.969418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Chen Zhang, Jieru Zhao, Mingzhe Gao, Qiang Xu, Zedong Peng, Zeju Li","submitted_at":"2025-07-04T02:23:46Z","abstract_excerpt":"High-Level Synthesis (HLS) plays a crucial role in modern hardware design by transforming high-level code into optimized hardware implementations. However, progress in applying machine learning (ML) to HLS optimization has been hindered by a shortage of sufficiently large and diverse datasets. To bridge this gap, we introduce ForgeHLS, a large-scale, open-source dataset explicitly designed for ML-driven HLS research. ForgeHLS comprises over 400k diverse designs generated from 846 kernels covering a broad range of application domains, consuming over 200k CPU hours during dataset construction. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03255","kind":"arxiv","version":3},"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/2507.03255/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":"2507.03255","created_at":"2026-07-05T11:48:04.969479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03255v3","created_at":"2026-07-05T11:48:04.969479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03255","created_at":"2026-07-05T11:48:04.969479+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDP7BVIVQ5WS","created_at":"2026-07-05T11:48:04.969479+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDP7BVIVQ5WS7D2F","created_at":"2026-07-05T11:48:04.969479+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDP7BVIV","created_at":"2026-07-05T11:48:04.969479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09240","citing_title":"DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ","json":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ.json","graph_json":"https://pith.science/api/pith-number/CDP7BVIVQ5WS7D2FSTI6T74RKJ/graph.json","events_json":"https://pith.science/api/pith-number/CDP7BVIVQ5WS7D2FSTI6T74RKJ/events.json","paper":"https://pith.science/paper/CDP7BVIV"},"agent_actions":{"view_html":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ","download_json":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ.json","view_paper":"https://pith.science/paper/CDP7BVIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03255&json=true","fetch_graph":"https://pith.science/api/pith-number/CDP7BVIVQ5WS7D2FSTI6T74RKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CDP7BVIVQ5WS7D2FSTI6T74RKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ/action/storage_attestation","attest_author":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ/action/author_attestation","sign_citation":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ/action/citation_signature","submit_replication":"https://pith.science/pith/CDP7BVIVQ5WS7D2FSTI6T74RKJ/action/replication_record"}},"created_at":"2026-07-05T11:48:04.969479+00:00","updated_at":"2026-07-05T11:48:04.969479+00:00"}