{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2Y3VB7CGND2DSASXSCHABTEO47","short_pith_number":"pith:2Y3VB7CG","schema_version":"1.0","canonical_sha256":"d63750fc4668f4390257908e00cc8ee7d475e2d11b61e7f600eb22829d479583","source":{"kind":"arxiv","id":"2510.22087","version":2},"attestation_state":"computed","paper":{"title":"QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.AR","authors_text":"Abhishek Tyagi, Alexander Ingare, Alice Guo, Amir Yazdanbakhsh, Andrea Mattia Garavagno, Andrew Cheng, Ankita Nayak, Arya Tschand, Avinash Kumar, Chandrashis Mazumdar, Chenyu Wang, Elisavet Lydia Alvanaki, Grace Hur, Ikechukwu Uchendu, Jason Yik, Jeffrey Ma, Jessica Quaye, Luca P. Carloni, Mark Mazumder, Radhika Ghosal, Sarah Gu, Shvetank Prakash, Tuhin Khare, Tushar Krishna, Varun Gohil, Vijay Janapa Reddi, Zishen Wan","submitted_at":"2025-10-24T23:54:17Z","abstract_excerpt":"The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from current large language model (LLM) evaluations. To this end, we present QuArch (pronounced 'quark'), the first benchmark designed to facilitate the development and evaluation of LLM knowledge and reasoning capabilities specifically in computer architecture. QuArch v1.0 provides a comprehensive collection of 2,671 expert-validated question-answer (QA) pairs covering various aspects of computer architecture, including processor design, memory systems, and"},"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":"2510.22087","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-10-24T23:54:17Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"323fe736db265b2f48876943024ed474704e29275f31628d57a86e2cd4c6a625","abstract_canon_sha256":"0dcc59bb815613ddd9357f36e06124b4c872b16633d5e032a062688ac686b8dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:13.973002Z","signature_b64":"zbUimXFXPoiPwT0mzuwp2frf6l/VmopiOtD1csFCt7Hi0E/F298OnCK81j3MRZWFz7epawALKx70UcBMrz6tAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d63750fc4668f4390257908e00cc8ee7d475e2d11b61e7f600eb22829d479583","last_reissued_at":"2026-07-22T00:22:13.972082Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:13.972082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.AR","authors_text":"Abhishek Tyagi, Alexander Ingare, Alice Guo, Amir Yazdanbakhsh, Andrea Mattia Garavagno, Andrew Cheng, Ankita Nayak, Arya Tschand, Avinash Kumar, Chandrashis Mazumdar, Chenyu Wang, Elisavet Lydia Alvanaki, Grace Hur, Ikechukwu Uchendu, Jason Yik, Jeffrey Ma, Jessica Quaye, Luca P. Carloni, Mark Mazumder, Radhika Ghosal, Sarah Gu, Shvetank Prakash, Tuhin Khare, Tushar Krishna, Varun Gohil, Vijay Janapa Reddi, Zishen Wan","submitted_at":"2025-10-24T23:54:17Z","abstract_excerpt":"The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from current large language model (LLM) evaluations. To this end, we present QuArch (pronounced 'quark'), the first benchmark designed to facilitate the development and evaluation of LLM knowledge and reasoning capabilities specifically in computer architecture. QuArch v1.0 provides a comprehensive collection of 2,671 expert-validated question-answer (QA) pairs covering various aspects of computer architecture, including processor design, memory systems, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.22087","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/2510.22087/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":"2510.22087","created_at":"2026-07-22T00:22:13.972513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.22087v2","created_at":"2026-07-22T00:22:13.972513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22087","created_at":"2026-07-22T00:22:13.972513+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Y3VB7CGND2D","created_at":"2026-07-22T00:22:13.972513+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Y3VB7CGND2DSASX","created_at":"2026-07-22T00:22:13.972513+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Y3VB7CG","created_at":"2026-07-22T00:22:13.972513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.21836","citing_title":"AgentDSE: Reasoning-Augmented Architectural Design Space Exploration","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02859","citing_title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47","json":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47.json","graph_json":"https://pith.science/api/pith-number/2Y3VB7CGND2DSASXSCHABTEO47/graph.json","events_json":"https://pith.science/api/pith-number/2Y3VB7CGND2DSASXSCHABTEO47/events.json","paper":"https://pith.science/paper/2Y3VB7CG"},"agent_actions":{"view_html":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47","download_json":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47.json","view_paper":"https://pith.science/paper/2Y3VB7CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.22087&json=true","fetch_graph":"https://pith.science/api/pith-number/2Y3VB7CGND2DSASXSCHABTEO47/graph.json","fetch_events":"https://pith.science/api/pith-number/2Y3VB7CGND2DSASXSCHABTEO47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47/action/storage_attestation","attest_author":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47/action/author_attestation","sign_citation":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47/action/citation_signature","submit_replication":"https://pith.science/pith/2Y3VB7CGND2DSASXSCHABTEO47/action/replication_record"}},"created_at":"2026-07-22T00:22:13.972513+00:00","updated_at":"2026-07-22T00:22:13.972513+00:00"}