{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ER2RRTEPI3USWXUQ56JKOCSXWL","short_pith_number":"pith:ER2RRTEP","schema_version":"1.0","canonical_sha256":"247518cc8f46e92b5e90ef92a70a57b2c90c370818172362f7153c84613b25ed","source":{"kind":"arxiv","id":"2506.04544","version":2},"attestation_state":"computed","paper":{"title":"hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PL"],"primary_cat":"cs.AR","authors_text":"Advay Ratan, Alex Um, Brendan Roberts, Charles Hong, Huijae An, Yakun Sophia Shao","submitted_at":"2025-06-05T01:29:18Z","abstract_excerpt":"Large language models (LLMs) are playing an increasingly large role in domains such as code generation, including hardware code generation, where Verilog is the key language. However, the amount of publicly available Verilog code pales in comparison to the amount of code available for software languages like Python. In this work, we present hdl2v (\"HDL-to-Verilog\"), a dataset which seeks to increase the amount of available human-written Verilog data by translating or compiling three other hardware description languages - VHDL, Chisel, and PyMTL3 - to Verilog. Furthermore, we demonstrate the va"},"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":"2506.04544","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-06-05T01:29:18Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PL"],"title_canon_sha256":"249e6d46d31048435693ebe56f4f9cd50e5e45a151594e7fc847dcfd63db1bab","abstract_canon_sha256":"13a1c64a7d20792f046083bd84e34ffd66113377e5342914be9b9cfd9a34103c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:09.005977Z","signature_b64":"plTfEg4pyGMN8IY8UmdnH33Gw+wQQxgsq6Xj38bxi5NfvTukknQoNDt/atDL075sgBpMxZWGeVL/rrbtIzkABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"247518cc8f46e92b5e90ef92a70a57b2c90c370818172362f7153c84613b25ed","last_reissued_at":"2026-07-05T11:34:09.005437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:09.005437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PL"],"primary_cat":"cs.AR","authors_text":"Advay Ratan, Alex Um, Brendan Roberts, Charles Hong, Huijae An, Yakun Sophia Shao","submitted_at":"2025-06-05T01:29:18Z","abstract_excerpt":"Large language models (LLMs) are playing an increasingly large role in domains such as code generation, including hardware code generation, where Verilog is the key language. However, the amount of publicly available Verilog code pales in comparison to the amount of code available for software languages like Python. In this work, we present hdl2v (\"HDL-to-Verilog\"), a dataset which seeks to increase the amount of available human-written Verilog data by translating or compiling three other hardware description languages - VHDL, Chisel, and PyMTL3 - to Verilog. Furthermore, we demonstrate the va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04544","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/2506.04544/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":"2506.04544","created_at":"2026-07-05T11:34:09.005509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04544v2","created_at":"2026-07-05T11:34:09.005509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04544","created_at":"2026-07-05T11:34:09.005509+00:00"},{"alias_kind":"pith_short_12","alias_value":"ER2RRTEPI3US","created_at":"2026-07-05T11:34:09.005509+00:00"},{"alias_kind":"pith_short_16","alias_value":"ER2RRTEPI3USWXUQ","created_at":"2026-07-05T11:34:09.005509+00:00"},{"alias_kind":"pith_short_8","alias_value":"ER2RRTEP","created_at":"2026-07-05T11:34:09.005509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23759","citing_title":"VeriPilot: An LLM-Powered Verilog Debugging Framework","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL","json":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL.json","graph_json":"https://pith.science/api/pith-number/ER2RRTEPI3USWXUQ56JKOCSXWL/graph.json","events_json":"https://pith.science/api/pith-number/ER2RRTEPI3USWXUQ56JKOCSXWL/events.json","paper":"https://pith.science/paper/ER2RRTEP"},"agent_actions":{"view_html":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL","download_json":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL.json","view_paper":"https://pith.science/paper/ER2RRTEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04544&json=true","fetch_graph":"https://pith.science/api/pith-number/ER2RRTEPI3USWXUQ56JKOCSXWL/graph.json","fetch_events":"https://pith.science/api/pith-number/ER2RRTEPI3USWXUQ56JKOCSXWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL/action/storage_attestation","attest_author":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL/action/author_attestation","sign_citation":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL/action/citation_signature","submit_replication":"https://pith.science/pith/ER2RRTEPI3USWXUQ56JKOCSXWL/action/replication_record"}},"created_at":"2026-07-05T11:34:09.005509+00:00","updated_at":"2026-07-05T11:34:09.005509+00:00"}