{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:725EVWZY253EISECEQ5TAQAM33","short_pith_number":"pith:725EVWZY","schema_version":"1.0","canonical_sha256":"feba4adb38d776444882243b30400cdeeb3ab4a5bca08622f18c63915ef25a1e","source":{"kind":"arxiv","id":"2503.05951","version":1},"attestation_state":"computed","paper":{"title":"TPU-Gen: LLM-Driven Custom Tensor Processing Unit Generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Arnob Ghosh, Deepak Vungarala, Kartik Pandit, Mohammed E. Elbtity, Ramtin Zand, Sakila Alam, Shaahin Angizi, Sumiya Syed","submitted_at":"2025-03-07T21:41:42Z","abstract_excerpt":"The increasing complexity and scale of Deep Neural Networks (DNNs) necessitate specialized tensor accelerators, such as Tensor Processing Units (TPUs), to meet various computational and energy efficiency requirements. Nevertheless, designing optimal TPU remains challenging due to the high domain expertise level, considerable manual design time, and lack of high-quality, domain-specific datasets. This paper introduces TPU-Gen, the first Large Language Model (LLM) based framework designed to automate the exact and approximate TPU generation process, focusing on systolic array architectures. TPU-"},"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":"2503.05951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-03-07T21:41:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"beabde5e05f14c4894fdf88dd1c9176968efa9b505af8f80fe1e526800a3c6e8","abstract_canon_sha256":"750a2585ff39fd5abd45a886b81fbb8d5dc89490515ba09f915cf2b1c992c1b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:49.916521Z","signature_b64":"fYWrrX6nOKdkc0etalakeL7xJLhmfMcuT9aCQaIoIUIS6QCnNyLSTyAePJ67e0VTvLKCWscSeWzPGcdNKk/WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feba4adb38d776444882243b30400cdeeb3ab4a5bca08622f18c63915ef25a1e","last_reissued_at":"2026-07-05T10:26:49.915591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:49.915591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TPU-Gen: LLM-Driven Custom Tensor Processing Unit Generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Arnob Ghosh, Deepak Vungarala, Kartik Pandit, Mohammed E. Elbtity, Ramtin Zand, Sakila Alam, Shaahin Angizi, Sumiya Syed","submitted_at":"2025-03-07T21:41:42Z","abstract_excerpt":"The increasing complexity and scale of Deep Neural Networks (DNNs) necessitate specialized tensor accelerators, such as Tensor Processing Units (TPUs), to meet various computational and energy efficiency requirements. Nevertheless, designing optimal TPU remains challenging due to the high domain expertise level, considerable manual design time, and lack of high-quality, domain-specific datasets. This paper introduces TPU-Gen, the first Large Language Model (LLM) based framework designed to automate the exact and approximate TPU generation process, focusing on systolic array architectures. TPU-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05951","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/2503.05951/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":"2503.05951","created_at":"2026-07-05T10:26:49.915706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05951v1","created_at":"2026-07-05T10:26:49.915706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05951","created_at":"2026-07-05T10:26:49.915706+00:00"},{"alias_kind":"pith_short_12","alias_value":"725EVWZY253E","created_at":"2026-07-05T10:26:49.915706+00:00"},{"alias_kind":"pith_short_16","alias_value":"725EVWZY253EISEC","created_at":"2026-07-05T10:26:49.915706+00:00"},{"alias_kind":"pith_short_8","alias_value":"725EVWZY","created_at":"2026-07-05T10:26:49.915706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33","json":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33.json","graph_json":"https://pith.science/api/pith-number/725EVWZY253EISECEQ5TAQAM33/graph.json","events_json":"https://pith.science/api/pith-number/725EVWZY253EISECEQ5TAQAM33/events.json","paper":"https://pith.science/paper/725EVWZY"},"agent_actions":{"view_html":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33","download_json":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33.json","view_paper":"https://pith.science/paper/725EVWZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05951&json=true","fetch_graph":"https://pith.science/api/pith-number/725EVWZY253EISECEQ5TAQAM33/graph.json","fetch_events":"https://pith.science/api/pith-number/725EVWZY253EISECEQ5TAQAM33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33/action/storage_attestation","attest_author":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33/action/author_attestation","sign_citation":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33/action/citation_signature","submit_replication":"https://pith.science/pith/725EVWZY253EISECEQ5TAQAM33/action/replication_record"}},"created_at":"2026-07-05T10:26:49.915706+00:00","updated_at":"2026-07-05T10:26:49.915706+00:00"}