{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JI7YKMHMYHATWRHUBHWF3KGZNZ","short_pith_number":"pith:JI7YKMHM","schema_version":"1.0","canonical_sha256":"4a3f8530ecc1c13b44f409ec5da8d96e7fe01fe17e729fb424101264c56b465f","source":{"kind":"arxiv","id":"2405.10299","version":3},"attestation_state":"computed","paper":{"title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Arber Zela, Benedikt Staffler, Frank Hutter, Joerg K.H. Franke, Lennart Purucker, Rhea Sanjay Sukthanker","submitted_at":"2024-05-16T17:53:32Z","abstract_excerpt":"The increasing size of language models necessitates a thorough analysis across multiple dimensions to assess trade-offs among crucial hardware metrics such as latency, energy consumption, GPU memory usage, and performance. Identifying optimal model configurations under specific hardware constraints is becoming essential but remains challenging due to the computational load of exhaustive training and evaluation on multiple devices. To address this, we introduce HW-GPT-Bench, a hardware-aware benchmark that utilizes surrogate predictions to approximate various hardware metrics across 13 devices "},"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":"2405.10299","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T17:53:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e77ab55678aa2765a6910728c22f3855d658aefe7011ca10f92fcae85a15eb1","abstract_canon_sha256":"1863584e2e44c3cedf773c91442f3551a74a67009ace0d8ef7f2de04e0c7b781"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:14.066587Z","signature_b64":"CfF2IOGaRk6W/3XLm+MoIfQ1BSARIz1PoU9DFqOAVTxIUcSNPCSOzHL69lYUgY14JIHm5zJ6KG0eKmiysyMKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3f8530ecc1c13b44f409ec5da8d96e7fe01fe17e729fb424101264c56b465f","last_reissued_at":"2026-07-05T09:30:14.066062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:14.066062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Arber Zela, Benedikt Staffler, Frank Hutter, Joerg K.H. Franke, Lennart Purucker, Rhea Sanjay Sukthanker","submitted_at":"2024-05-16T17:53:32Z","abstract_excerpt":"The increasing size of language models necessitates a thorough analysis across multiple dimensions to assess trade-offs among crucial hardware metrics such as latency, energy consumption, GPU memory usage, and performance. Identifying optimal model configurations under specific hardware constraints is becoming essential but remains challenging due to the computational load of exhaustive training and evaluation on multiple devices. To address this, we introduce HW-GPT-Bench, a hardware-aware benchmark that utilizes surrogate predictions to approximate various hardware metrics across 13 devices "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10299","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/2405.10299/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":"2405.10299","created_at":"2026-07-05T09:30:14.066125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10299v3","created_at":"2026-07-05T09:30:14.066125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10299","created_at":"2026-07-05T09:30:14.066125+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI7YKMHMYHAT","created_at":"2026-07-05T09:30:14.066125+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI7YKMHMYHATWRHU","created_at":"2026-07-05T09:30:14.066125+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI7YKMHM","created_at":"2026-07-05T09:30:14.066125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17653","citing_title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ","json":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ.json","graph_json":"https://pith.science/api/pith-number/JI7YKMHMYHATWRHUBHWF3KGZNZ/graph.json","events_json":"https://pith.science/api/pith-number/JI7YKMHMYHATWRHUBHWF3KGZNZ/events.json","paper":"https://pith.science/paper/JI7YKMHM"},"agent_actions":{"view_html":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ","download_json":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ.json","view_paper":"https://pith.science/paper/JI7YKMHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10299&json=true","fetch_graph":"https://pith.science/api/pith-number/JI7YKMHMYHATWRHUBHWF3KGZNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JI7YKMHMYHATWRHUBHWF3KGZNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ/action/storage_attestation","attest_author":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ/action/author_attestation","sign_citation":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ/action/citation_signature","submit_replication":"https://pith.science/pith/JI7YKMHMYHATWRHUBHWF3KGZNZ/action/replication_record"}},"created_at":"2026-07-05T09:30:14.066125+00:00","updated_at":"2026-07-05T09:30:14.066125+00:00"}