{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3SLUUZKN6GFBNHSMRVD42TOYSQ","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":"d86509263ebba250ada6b55f4b636249a3843298f9281ae81ebd8b072a986675","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T20:06:24Z","title_canon_sha256":"df79ce92d94301ff976bc6296fb3839244a0a20c382ed83bffd9223cc8d696be"},"schema_version":"1.0","source":{"id":"2105.03484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03484","created_at":"2026-07-05T06:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03484v1","created_at":"2026-07-05T06:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03484","created_at":"2026-07-05T06:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"3SLUUZKN6GFB","created_at":"2026-07-05T06:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"3SLUUZKN6GFBNHSM","created_at":"2026-07-05T06:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"3SLUUZKN","created_at":"2026-07-05T06:16:34Z"}],"graph_snapshots":[{"event_id":"sha256:548618ea3a7c853ff10dcdce52c935bfe4ae1a892e14e44209dbae6aa8e2610d","target":"graph","created_at":"2026-07-05T06:16:34Z","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/2105.03484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models, limiting the ability to effectively leverage transformers. Here, we provide a systematic study on the role of dimension reduction methods (principal components analysis, factorization techniques, or multi-layer auto-encoders) as well as the dimensionality of embedding vectors and sample sizes as a function of predictive performance. We first find that fine-tu","authors_text":"Adithya V Ganesan, Aravind Reddy Ravula, H. Andrew Schwartz, Huy Vu, Matthew Matero","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T20:06:24Z","title":"Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03484","kind":"arxiv","version":1},"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":"sha256:0741caa87a7918aa0dfad0e6c68227b5067868e4994d26c000f38e119759dde5","target":"record","created_at":"2026-07-05T06:16:34Z","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":"d86509263ebba250ada6b55f4b636249a3843298f9281ae81ebd8b072a986675","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T20:06:24Z","title_canon_sha256":"df79ce92d94301ff976bc6296fb3839244a0a20c382ed83bffd9223cc8d696be"},"schema_version":"1.0","source":{"id":"2105.03484","kind":"arxiv","version":1}},"canonical_sha256":"dc974a654df18a169e4c8d47cd4dd894047ddcc4cd3117a654fb37cf36c2073e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc974a654df18a169e4c8d47cd4dd894047ddcc4cd3117a654fb37cf36c2073e","first_computed_at":"2026-07-05T06:16:34.501195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:34.501195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VTgivuAbUxFlmRabb7MQf6VKFBEQjpvWl5gGdhwNXirlUyboG7h8zOTEHSatJlwz6S9HfR9Lsp8iSZePGN9vDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:34.501658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0741caa87a7918aa0dfad0e6c68227b5067868e4994d26c000f38e119759dde5","sha256:548618ea3a7c853ff10dcdce52c935bfe4ae1a892e14e44209dbae6aa8e2610d"],"state_sha256":"117dae1fd33763c5fba7422eecdcf8385876ba7b43251560378bd3a3bd9b5e2d"}