{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GFOSUESMB5NYUQSZOJUUJHFSFJ","short_pith_number":"pith:GFOSUESM","canonical_record":{"source":{"id":"2507.13369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-07-09T17:06:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6a0cd547678c8feb85c543171cfb52029838355ee4e0bca55bb21f0d991f8c9","abstract_canon_sha256":"4c00f21155f816d86ceefec792588dab76e10091ec4873f8306a5089565256f4"},"schema_version":"1.0"},"canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","source":{"kind":"arxiv","id":"2507.13369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13369","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13369v1","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13369","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"GFOSUESMB5NY","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_16","alias_value":"GFOSUESMB5NYUQSZ","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_8","alias_value":"GFOSUESM","created_at":"2026-07-05T11:39:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GFOSUESMB5NYUQSZOJUUJHFSFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-07-09T17:06:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6a0cd547678c8feb85c543171cfb52029838355ee4e0bca55bb21f0d991f8c9","abstract_canon_sha256":"4c00f21155f816d86ceefec792588dab76e10091ec4873f8306a5089565256f4"},"schema_version":"1.0"},"canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:16.101193Z","signature_b64":"LpNZUeOqdk1AkHIu42gHF7Bya3nnaOmsLPAilGWVc8GhWWYr2ziXkFN+QiK96pQ4CkWv2SLXYNPXh4IyzsoOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","last_reissued_at":"2026-07-05T11:39:16.100738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:16.100738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13369","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DMgA0tvu+UMIQTSOrOvNTyvQWJHmzhikCfRH6ZaK9qfQfMc5sv5HswS6gB3192fhtZEygrlFJbigNGQCUmTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:16:25.056556Z"},"content_sha256":"77b633e09182aba8a82bd5f7a370f083afecc95a0d3a82e143b38dc11939b023","schema_version":"1.0","event_id":"sha256:77b633e09182aba8a82bd5f7a370f083afecc95a0d3a82e143b38dc11939b023"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GFOSUESMB5NYUQSZOJUUJHFSFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Danyu Lu, Farimah Farahmandi, Kamal Kandula, Mark Tehranipoor, Paul E. Calzada, Sujan Kumar Saha, Tanvir Rahman, Zahin Ibnat","submitted_at":"2025-07-09T17:06:54Z","abstract_excerpt":"Large Language Models (LLMs) are gaining popularity for hardware design automation, particularly through Register Transfer Level (RTL) code generation. In this work, we examine the current literature on RTL generation using LLMs and identify key requirements for training and fine-tuning datasets. We construct a robust Verilog dataset through an automated three-pronged process involving database (DB) creation and management with PostgreSQL, data collection from code hosting sites like OpenCores and GitHub, and data preprocessing to verify the codes' syntax, run logic synthesis, and extract rele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13369","kind":"arxiv","version":1},"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/2507.13369/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":"2026-07-05T11:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TAE4izrDxaD8MN+Z6peKtyR5naT7RynfpbcWVLZHF0AvnM5K1B6jqbuf/uovdRlKZDcmYFVAVn4AdMtFrbl0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:16:25.057055Z"},"content_sha256":"92ae5e5feee8b473f85131206e9f102b23b71c624b5accc97d53bf1ea3fae33f","schema_version":"1.0","event_id":"sha256:92ae5e5feee8b473f85131206e9f102b23b71c624b5accc97d53bf1ea3fae33f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/bundle.json","state_url":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/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":"2026-08-08T00:16:25Z","links":{"resolver":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ","bundle":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/bundle.json","state":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GFOSUESMB5NYUQSZOJUUJHFSFJ","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":"4c00f21155f816d86ceefec792588dab76e10091ec4873f8306a5089565256f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-07-09T17:06:54Z","title_canon_sha256":"e6a0cd547678c8feb85c543171cfb52029838355ee4e0bca55bb21f0d991f8c9"},"schema_version":"1.0","source":{"id":"2507.13369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13369","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13369v1","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13369","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"GFOSUESMB5NY","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_16","alias_value":"GFOSUESMB5NYUQSZ","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_8","alias_value":"GFOSUESM","created_at":"2026-07-05T11:39:16Z"}],"graph_snapshots":[{"event_id":"sha256:92ae5e5feee8b473f85131206e9f102b23b71c624b5accc97d53bf1ea3fae33f","target":"graph","created_at":"2026-07-05T11:39:16Z","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/2507.13369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are gaining popularity for hardware design automation, particularly through Register Transfer Level (RTL) code generation. In this work, we examine the current literature on RTL generation using LLMs and identify key requirements for training and fine-tuning datasets. We construct a robust Verilog dataset through an automated three-pronged process involving database (DB) creation and management with PostgreSQL, data collection from code hosting sites like OpenCores and GitHub, and data preprocessing to verify the codes' syntax, run logic synthesis, and extract rele","authors_text":"Danyu Lu, Farimah Farahmandi, Kamal Kandula, Mark Tehranipoor, Paul E. Calzada, Sujan Kumar Saha, Tanvir Rahman, Zahin Ibnat","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-07-09T17:06:54Z","title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13369","kind":"arxiv","version":1},"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":"sha256:77b633e09182aba8a82bd5f7a370f083afecc95a0d3a82e143b38dc11939b023","target":"record","created_at":"2026-07-05T11:39:16Z","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":"4c00f21155f816d86ceefec792588dab76e10091ec4873f8306a5089565256f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-07-09T17:06:54Z","title_canon_sha256":"e6a0cd547678c8feb85c543171cfb52029838355ee4e0bca55bb21f0d991f8c9"},"schema_version":"1.0","source":{"id":"2507.13369","kind":"arxiv","version":1}},"canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","first_computed_at":"2026-07-05T11:39:16.100738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:16.100738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LpNZUeOqdk1AkHIu42gHF7Bya3nnaOmsLPAilGWVc8GhWWYr2ziXkFN+QiK96pQ4CkWv2SLXYNPXh4IyzsoOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:16.101193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77b633e09182aba8a82bd5f7a370f083afecc95a0d3a82e143b38dc11939b023","sha256:92ae5e5feee8b473f85131206e9f102b23b71c624b5accc97d53bf1ea3fae33f"],"state_sha256":"b542178988f4043958360e797d59f16db7f77fd4ffcb6b8a93757494534e74d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwToe20NfCqcfR3rtSD5L0KofnSgflTEojKqTfscy46zXrmSLSiaphmHxeZtA6E/h5HPX35YaqYsvXo6ykGPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:16:25.061905Z","bundle_sha256":"ec6083ad17d61c702e29e0de3811bb5b906726844a9ce07fcadfae8f87f7df0d"}}