{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AR7B3DEVMOTSBRCCVXUCLYSRRE","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":"2b0354a80ba906644ad0e9b3f6df5f5f0384ddf4563f84d4fe2ad3ce8a7afd54","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-25T19:50:31Z","title_canon_sha256":"93d2e3b81af83d220120cd555e3c538adbf44cf463d598b7ba69e46ae4c866e0"},"schema_version":"1.0","source":{"id":"2401.14489","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14489","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14489v2","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14489","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"AR7B3DEVMOTS","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_16","alias_value":"AR7B3DEVMOTSBRCC","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_8","alias_value":"AR7B3DEV","created_at":"2026-07-05T07:39:34Z"}],"graph_snapshots":[{"event_id":"sha256:751bfa37964f5d6a8f1605f9bb89c6418c5f14508ea3a2963522398435e65721","target":"graph","created_at":"2026-07-05T07:39:34Z","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/2401.14489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL model to be more amenable to the target hardware can significantly improve the runtime performance of DL training and inference. In this paper, we provide a set of guidelines for users to maximize the runtime performance of their transformer models. These guidelines have been created by carefully considering the impact of various model hyperparameters control","authors_text":"Aamir Shafi, Deepak Narayanan, Dhabaleswar Panda, Hari Subramoni, Jacob Hatef, Junqi Yin, Quentin Anthony, Stas Bekman, Stella Biderman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-25T19:50:31Z","title":"The Case for Co-Designing Model Architectures with Hardware"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14489","kind":"arxiv","version":2},"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":"sha256:533aa5e212abf015ce8523e150acbc081dc4dfd0ccd3483fa22bb5694e66fc2b","target":"record","created_at":"2026-07-05T07:39:34Z","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":"2b0354a80ba906644ad0e9b3f6df5f5f0384ddf4563f84d4fe2ad3ce8a7afd54","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-25T19:50:31Z","title_canon_sha256":"93d2e3b81af83d220120cd555e3c538adbf44cf463d598b7ba69e46ae4c866e0"},"schema_version":"1.0","source":{"id":"2401.14489","kind":"arxiv","version":2}},"canonical_sha256":"047e1d8c9563a720c442ade825e25189007290160bedcc76b7e523bfd71812d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"047e1d8c9563a720c442ade825e25189007290160bedcc76b7e523bfd71812d3","first_computed_at":"2026-07-05T07:39:34.446332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:34.446332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vFpe881wbzIvvQAawnvz2cb9vbbL6c83HVzq8YXbqwVCJMN6PjIK241fJ8/g43MXcvlp8rRWW2t/0pjT9dvxDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:34.446811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14489","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:533aa5e212abf015ce8523e150acbc081dc4dfd0ccd3483fa22bb5694e66fc2b","sha256:751bfa37964f5d6a8f1605f9bb89c6418c5f14508ea3a2963522398435e65721"],"state_sha256":"3facdc2aeec0c5e2ff45dd750211a965091b49387ad1b15346dff0bb9a58c999"}