{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MEYWCCBWWYLVNI5OFU5ZWCG2AY","short_pith_number":"pith:MEYWCCBW","schema_version":"1.0","canonical_sha256":"6131610836b61756a3ae2d3b9b08da060f216fafb64fbbab979e910e9987b148","source":{"kind":"arxiv","id":"2503.21971","version":3},"attestation_state":"computed","paper":{"title":"RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Armin Abdollahi, Massoud Pedram, Mehdi Kamal","submitted_at":"2025-03-27T20:35:09Z","abstract_excerpt":"This paper presents RocketPPA, a novel ultra-fast power, performance (delay), and area (PPA) estimator operating directly at the code-level abstraction using HDL code as input. The key technical innovation is its LLM-based regression model, which uniquely integrates a large language model (LLM) with a mixture-of-experts (MoE) architecture composed of multilayer perceptrons (MLPs). The LLM interprets the input HDL code and then utilizes its final hidden-layer representations to predict PPA metrics. Low-rank adaptation (LoRA) is used for parameter-efficient fine-tuning to enable efficient LLM tr"},"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":"2503.21971","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-27T20:35:09Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"a14f00141352d02bab53f2bcbebbde0b79ce94ee2717a4678b5797ab22e7ee7f","abstract_canon_sha256":"df7ad72ec850f307acd08a8c9ec4cc896dad573cb1b621f02eae1c8089f53238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:26.096410Z","signature_b64":"KD0EzAjgwYVRpL43NqyudihcSflj6vgAZte4hFYFlasnw9vXFXdzLrE/z2SdJTLqIIYT2UDmzzvayW1Xz0rxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6131610836b61756a3ae2d3b9b08da060f216fafb64fbbab979e910e9987b148","last_reissued_at":"2026-07-05T11:19:26.095923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:26.095923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Armin Abdollahi, Massoud Pedram, Mehdi Kamal","submitted_at":"2025-03-27T20:35:09Z","abstract_excerpt":"This paper presents RocketPPA, a novel ultra-fast power, performance (delay), and area (PPA) estimator operating directly at the code-level abstraction using HDL code as input. The key technical innovation is its LLM-based regression model, which uniquely integrates a large language model (LLM) with a mixture-of-experts (MoE) architecture composed of multilayer perceptrons (MLPs). The LLM interprets the input HDL code and then utilizes its final hidden-layer representations to predict PPA metrics. Low-rank adaptation (LoRA) is used for parameter-efficient fine-tuning to enable efficient LLM tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21971","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/2503.21971/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":"2503.21971","created_at":"2026-07-05T11:19:26.095984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21971v3","created_at":"2026-07-05T11:19:26.095984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21971","created_at":"2026-07-05T11:19:26.095984+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEYWCCBWWYLV","created_at":"2026-07-05T11:19:26.095984+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEYWCCBWWYLVNI5O","created_at":"2026-07-05T11:19:26.095984+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEYWCCBW","created_at":"2026-07-05T11:19:26.095984+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/MEYWCCBWWYLVNI5OFU5ZWCG2AY","json":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY.json","graph_json":"https://pith.science/api/pith-number/MEYWCCBWWYLVNI5OFU5ZWCG2AY/graph.json","events_json":"https://pith.science/api/pith-number/MEYWCCBWWYLVNI5OFU5ZWCG2AY/events.json","paper":"https://pith.science/paper/MEYWCCBW"},"agent_actions":{"view_html":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY","download_json":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY.json","view_paper":"https://pith.science/paper/MEYWCCBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21971&json=true","fetch_graph":"https://pith.science/api/pith-number/MEYWCCBWWYLVNI5OFU5ZWCG2AY/graph.json","fetch_events":"https://pith.science/api/pith-number/MEYWCCBWWYLVNI5OFU5ZWCG2AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY/action/storage_attestation","attest_author":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY/action/author_attestation","sign_citation":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY/action/citation_signature","submit_replication":"https://pith.science/pith/MEYWCCBWWYLVNI5OFU5ZWCG2AY/action/replication_record"}},"created_at":"2026-07-05T11:19:26.095984+00:00","updated_at":"2026-07-05T11:19:26.095984+00:00"}