{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PXTUU57EZSCVZNVYNSHQI6AAKI","short_pith_number":"pith:PXTUU57E","canonical_record":{"source":{"id":"2402.02255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T20:22:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bcdda8337f87785b2cc7ec61b124b643e7ff4ed399a5851e4c7e69132072e6a9","abstract_canon_sha256":"fb058769ffca3a839714e77c4b175d88721a9f0e9851aba712088037746d182a"},"schema_version":"1.0"},"canonical_sha256":"7de74a77e4cc855cb6b86c8f047800521f3cff97122e29c9f2be839198fc48d0","source":{"kind":"arxiv","id":"2402.02255","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02255","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02255v1","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02255","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"pith_short_12","alias_value":"PXTUU57EZSCV","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"pith_short_16","alias_value":"PXTUU57EZSCVZNVY","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"pith_short_8","alias_value":"PXTUU57E","created_at":"2026-07-05T07:41:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PXTUU57EZSCVZNVYNSHQI6AAKI","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T20:22:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bcdda8337f87785b2cc7ec61b124b643e7ff4ed399a5851e4c7e69132072e6a9","abstract_canon_sha256":"fb058769ffca3a839714e77c4b175d88721a9f0e9851aba712088037746d182a"},"schema_version":"1.0"},"canonical_sha256":"7de74a77e4cc855cb6b86c8f047800521f3cff97122e29c9f2be839198fc48d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:12.596798Z","signature_b64":"FrRb+c+G7DqJC1wu0lqTSFLku0VCDqNZaQF0S9L9k91x6WdzFSeuxoLLBoNhGY2JZ03SXz5weswXJGyOZp+MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de74a77e4cc855cb6b86c8f047800521f3cff97122e29c9f2be839198fc48d0","last_reissued_at":"2026-07-05T07:41:12.596227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:12.596227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02255","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:41:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH3KJjA/NzkI+boC98xRqejNDwkIUdFAzld69ChIJmQJAJbh0imXiX0sXmTs/o+6f6r+5+lgvl3jnv5Dib/QCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:04:38.360515Z"},"content_sha256":"13d3c0e19594bdd827e644a7166e0b7d1d9fc6d1515a6f9ada5f4a11557d3d32","schema_version":"1.0","event_id":"sha256:13d3c0e19594bdd827e644a7166e0b7d1d9fc6d1515a6f9ada5f4a11557d3d32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PXTUU57EZSCVZNVYNSHQI6AAKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Byung-Doh Oh, Shisen Yue, William Schuler","submitted_at":"2024-02-03T20:22:54Z","abstract_excerpt":"Recent studies have shown that as Transformer-based language models become larger and are trained on very large amounts of data, the fit of their surprisal estimates to naturalistic human reading times degrades. The current work presents a series of analyses showing that word frequency is a key explanatory factor underlying these two trends. First, residual errors from four language model families on four corpora show that the inverse correlation between model size and fit to reading times is the strongest on the subset of least frequent words, which is driven by excessively accurate predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02255","kind":"arxiv","version":1},"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/2402.02255/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:41:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRawSEdfrIHWabB9a2Xmw3Bq8JRaaQeGcSjKSWx2ivXO3pt4NxHvkhx6lqgUDMKTeN5jV+QXg7jG+ncGAtq8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:04:38.361030Z"},"content_sha256":"cd4a3b846a1340e5e6e68ed01c32caaebf62c80ee215c05a0dd652211e4880b3","schema_version":"1.0","event_id":"sha256:cd4a3b846a1340e5e6e68ed01c32caaebf62c80ee215c05a0dd652211e4880b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXTUU57EZSCVZNVYNSHQI6AAKI/bundle.json","state_url":"https://pith.science/pith/PXTUU57EZSCVZNVYNSHQI6AAKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXTUU57EZSCVZNVYNSHQI6AAKI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T04:04:38Z","links":{"resolver":"https://pith.science/pith/PXTUU57EZSCVZNVYNSHQI6AAKI","bundle":"https://pith.science/pith/PXTUU57EZSCVZNVYNSHQI6AAKI/bundle.json","state":"https://pith.science/pith/PXTUU57EZSCVZNVYNSHQI6AAKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXTUU57EZSCVZNVYNSHQI6AAKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PXTUU57EZSCVZNVYNSHQI6AAKI","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":"fb058769ffca3a839714e77c4b175d88721a9f0e9851aba712088037746d182a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T20:22:54Z","title_canon_sha256":"bcdda8337f87785b2cc7ec61b124b643e7ff4ed399a5851e4c7e69132072e6a9"},"schema_version":"1.0","source":{"id":"2402.02255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02255","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02255v1","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02255","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"pith_short_12","alias_value":"PXTUU57EZSCV","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"pith_short_16","alias_value":"PXTUU57EZSCVZNVY","created_at":"2026-07-05T07:41:12Z"},{"alias_kind":"pith_short_8","alias_value":"PXTUU57E","created_at":"2026-07-05T07:41:12Z"}],"graph_snapshots":[{"event_id":"sha256:cd4a3b846a1340e5e6e68ed01c32caaebf62c80ee215c05a0dd652211e4880b3","target":"graph","created_at":"2026-07-05T07:41:12Z","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/2402.02255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown that as Transformer-based language models become larger and are trained on very large amounts of data, the fit of their surprisal estimates to naturalistic human reading times degrades. The current work presents a series of analyses showing that word frequency is a key explanatory factor underlying these two trends. First, residual errors from four language model families on four corpora show that the inverse correlation between model size and fit to reading times is the strongest on the subset of least frequent words, which is driven by excessively accurate predictio","authors_text":"Byung-Doh Oh, Shisen Yue, William Schuler","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T20:22:54Z","title":"Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02255","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":"sha256:13d3c0e19594bdd827e644a7166e0b7d1d9fc6d1515a6f9ada5f4a11557d3d32","target":"record","created_at":"2026-07-05T07:41:12Z","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":"fb058769ffca3a839714e77c4b175d88721a9f0e9851aba712088037746d182a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T20:22:54Z","title_canon_sha256":"bcdda8337f87785b2cc7ec61b124b643e7ff4ed399a5851e4c7e69132072e6a9"},"schema_version":"1.0","source":{"id":"2402.02255","kind":"arxiv","version":1}},"canonical_sha256":"7de74a77e4cc855cb6b86c8f047800521f3cff97122e29c9f2be839198fc48d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7de74a77e4cc855cb6b86c8f047800521f3cff97122e29c9f2be839198fc48d0","first_computed_at":"2026-07-05T07:41:12.596227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:12.596227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FrRb+c+G7DqJC1wu0lqTSFLku0VCDqNZaQF0S9L9k91x6WdzFSeuxoLLBoNhGY2JZ03SXz5weswXJGyOZp+MBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:12.596798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13d3c0e19594bdd827e644a7166e0b7d1d9fc6d1515a6f9ada5f4a11557d3d32","sha256:cd4a3b846a1340e5e6e68ed01c32caaebf62c80ee215c05a0dd652211e4880b3"],"state_sha256":"56546cde5cc7f0f01e16f96947e7f8e33a42ccbf40347856dc8713b465713a98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ifSMjC8EtJTJeob/JEW/jrQm8C9wxM1SExxkhnezxOP0xrP/Q1d/ftx/tjNVMB+2CZVlWiZ0KdghASqJuvOpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:04:38.364508Z","bundle_sha256":"0d98208c3c577f69cbda6efbaca3de54167db89daabfb83e54ab1da4e9b8164c"}}