{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T3BM574GUCDVWWQ4OLXBNPN5FM","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":"f32b8e0f77179d7160064de78585be9848f4ad5cfd18d635385ad8731c98c1c0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T02:10:43Z","title_canon_sha256":"1f414d1f293c1e891b61e4850b6cf3b6d6a096ee9b7d69f97d513e8223dd09bc"},"schema_version":"1.0","source":{"id":"2203.02094","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02094","created_at":"2026-07-05T05:07:21Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02094v2","created_at":"2026-07-05T05:07:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02094","created_at":"2026-07-05T05:07:21Z"},{"alias_kind":"pith_short_12","alias_value":"T3BM574GUCDV","created_at":"2026-07-05T05:07:21Z"},{"alias_kind":"pith_short_16","alias_value":"T3BM574GUCDVWWQ4","created_at":"2026-07-05T05:07:21Z"},{"alias_kind":"pith_short_8","alias_value":"T3BM574G","created_at":"2026-07-05T05:07:21Z"}],"graph_snapshots":[{"event_id":"sha256:81742bf309fff26a95b268dfd9e52870d15ff3e10d1dfcd47ca310054ef31059","target":"graph","created_at":"2026-07-05T05:07:21Z","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/2203.02094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak memory utilization and latency is non-trivial. This is exacerbated by the proliferation of various hardware. We leverage the somewhat surprising empirical observation that the number of decoder parameters in autoregressive Transformers has a high rank correlation with task performance, irrespective of the architecture topology. This observation org","authors_text":"Caio C. T. Mendes, Debadeepta Dey, Farinaz Koushanfar, Gustavo H. de Rosa, Mojan Javaheripi, Sebastien Bubeck, Shital Shah, Subhabrata Mukherjee, Tomasz L. Religa","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T02:10:43Z","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02094","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:aeb148cefbf2daf79d1787a7bb06baeee2f4d5e97571a7cc5c738f80f9bd3892","target":"record","created_at":"2026-07-05T05:07:21Z","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":"f32b8e0f77179d7160064de78585be9848f4ad5cfd18d635385ad8731c98c1c0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T02:10:43Z","title_canon_sha256":"1f414d1f293c1e891b61e4850b6cf3b6d6a096ee9b7d69f97d513e8223dd09bc"},"schema_version":"1.0","source":{"id":"2203.02094","kind":"arxiv","version":2}},"canonical_sha256":"9ec2ceff86a0875b5a1c72ee16bdbd2b2b3a9673d5bcec115e0793d155feb151","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ec2ceff86a0875b5a1c72ee16bdbd2b2b3a9673d5bcec115e0793d155feb151","first_computed_at":"2026-07-05T05:07:21.871768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:21.871768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRlKAAtPPNfMwqxONRbKe/7DttshI9HWQQ0zly+f47wRSVDn/sdtwpuH5iW+g8c8BLpSMEnxjN8QD+FoiRIBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:21.872214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02094","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aeb148cefbf2daf79d1787a7bb06baeee2f4d5e97571a7cc5c738f80f9bd3892","sha256:81742bf309fff26a95b268dfd9e52870d15ff3e10d1dfcd47ca310054ef31059"],"state_sha256":"9ddb6bbcaeab8e83a81fba7b09f75ff180113239322f59185a67638e14943be3"}