{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AEFKDG3RC7URJGQQSFMIKWD44O","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":"517ad3ec74353988e0606326b8e139667f4e48486490984ec2e6166019df3498","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-22T12:50:49Z","title_canon_sha256":"f40ea463470fae3427b4791d53e38e3df022b6725baf21baeab57dce8750b7db"},"schema_version":"1.0","source":{"id":"2304.11389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11389","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11389v2","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11389","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"AEFKDG3RC7UR","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"AEFKDG3RC7URJGQQ","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"AEFKDG3R","created_at":"2026-07-05T07:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:7f2b7f6ac964f68678d1bf082004abb43da4a7aeef713bf78b89e8e57d90f5fb","target":"graph","created_at":"2026-07-05T07:03:23Z","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/2304.11389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent psycholinguistic studies have drawn conflicting conclusions about the relationship between the quality of a language model and the ability of its surprisal estimates to predict human reading times, which has been speculated to be due to the large gap in both the amount of training data and model capacity across studies. The current work aims to consolidate these findings by evaluating surprisal estimates from Transformer-based language model variants that vary systematically in the amount of training data and model capacity on their ability to predict human reading times. The results sh","authors_text":"Byung-Doh Oh, William Schuler","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-22T12:50:49Z","title":"Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11389","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":"sha256:424b4ae407079cff8c0c93408663529f87b83b3c39d54fd772f810c2430255b1","target":"record","created_at":"2026-07-05T07:03:23Z","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":"517ad3ec74353988e0606326b8e139667f4e48486490984ec2e6166019df3498","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-22T12:50:49Z","title_canon_sha256":"f40ea463470fae3427b4791d53e38e3df022b6725baf21baeab57dce8750b7db"},"schema_version":"1.0","source":{"id":"2304.11389","kind":"arxiv","version":2}},"canonical_sha256":"010aa19b7117e9149a10915885587ce3adaabcfc00ba21579f37aa5a1ebc69f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"010aa19b7117e9149a10915885587ce3adaabcfc00ba21579f37aa5a1ebc69f1","first_computed_at":"2026-07-05T07:03:23.457283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:23.457283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fcIWzmyhS7qsIioOdFQmbAm5o1BSAlRpSGkfDwUY+uxNoqKdCTKFPLMFP68wKLBM7tt/35gmZr1x3+94qA9uDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:23.457755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:424b4ae407079cff8c0c93408663529f87b83b3c39d54fd772f810c2430255b1","sha256:7f2b7f6ac964f68678d1bf082004abb43da4a7aeef713bf78b89e8e57d90f5fb"],"state_sha256":"c261fff384b92f51dfc7d76db3df2c4496c17fbb3827d0f16c11ad572dbb69d0"}