{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NAOWHN2JUVKCFLVN27LLLM6FV7","short_pith_number":"pith:NAOWHN2J","canonical_record":{"source":{"id":"2310.17774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T20:55:29Z","cross_cats_sorted":[],"title_canon_sha256":"1f8b40728b816ba1e09227e6b181c2b87bd4afcb80d879a93f838f82d0086d9f","abstract_canon_sha256":"11acd75b0a8341ae4618390aa01ec10731fc427b132403743eb53c80e3193b96"},"schema_version":"1.0"},"canonical_sha256":"681d63b749a55422aeadd7d6b5b3c5afe002c71b54bcf5ae2594dc0deb8a3b4f","source":{"kind":"arxiv","id":"2310.17774","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17774","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17774v1","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17774","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"NAOWHN2JUVKC","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"NAOWHN2JUVKCFLVN","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"NAOWHN2J","created_at":"2026-07-05T07:05:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NAOWHN2JUVKCFLVN27LLLM6FV7","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T20:55:29Z","cross_cats_sorted":[],"title_canon_sha256":"1f8b40728b816ba1e09227e6b181c2b87bd4afcb80d879a93f838f82d0086d9f","abstract_canon_sha256":"11acd75b0a8341ae4618390aa01ec10731fc427b132403743eb53c80e3193b96"},"schema_version":"1.0"},"canonical_sha256":"681d63b749a55422aeadd7d6b5b3c5afe002c71b54bcf5ae2594dc0deb8a3b4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:52.409187Z","signature_b64":"wAJZZIquUY7v/rYSvgBSEnS3eOzV6HOdkCiVF+v3Kv2ufByID/WqctnlmmWs+i0tqQonp0WdyHpycR1boV9jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681d63b749a55422aeadd7d6b5b3c5afe002c71b54bcf5ae2594dc0deb8a3b4f","last_reissued_at":"2026-07-05T07:05:52.408794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:52.408794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17774","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":"2026-07-05T07:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zbh5mV9fUdU0JgYRvumVj+9IYIk5LU/BUIjSug7hhD6+5yjw6m8vbTa2ohtwTdp+HX2TW1gRh14B6+1ATmojCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:50:37.668136Z"},"content_sha256":"45db3c31240eca8c74cc483b6199fa8435f7a3f33d8b213fc1c564841fe635dc","schema_version":"1.0","event_id":"sha256:45db3c31240eca8c74cc483b6199fa8435f7a3f33d8b213fc1c564841fe635dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NAOWHN2JUVKCFLVN27LLLM6FV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Philip Resnik, Sathvik Nair","submitted_at":"2023-10-26T20:55:29Z","abstract_excerpt":"An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words into morphemes. Does that matter? We carefully test this by comparing surprisal estimates using orthographic, morphological, and BPE tokenization against reading time data. Our results replicate previous findings and provide evidence that in the aggregate, predictions using BPE tokenization do not suffer relative to morphological and orthographic segmentation. However, a finer-grained analysis points to potential is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17774","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/2310.17774/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":"2026-07-05T07:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8AZoePG+rUjj0Uwb9ITUuM/Zixn/oYGui+E64UPGLFo8+uAm/MFfZ/0eO7EdwMDEGvPYS7wmdYCxNFKTMoe9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:50:37.668716Z"},"content_sha256":"3c3eaf9ab652702710e10f6921f51a429765254ca29b1fd6742866c2605434d6","schema_version":"1.0","event_id":"sha256:3c3eaf9ab652702710e10f6921f51a429765254ca29b1fd6742866c2605434d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NAOWHN2JUVKCFLVN27LLLM6FV7/bundle.json","state_url":"https://pith.science/pith/NAOWHN2JUVKCFLVN27LLLM6FV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NAOWHN2JUVKCFLVN27LLLM6FV7/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":"2026-08-10T07:50:37Z","links":{"resolver":"https://pith.science/pith/NAOWHN2JUVKCFLVN27LLLM6FV7","bundle":"https://pith.science/pith/NAOWHN2JUVKCFLVN27LLLM6FV7/bundle.json","state":"https://pith.science/pith/NAOWHN2JUVKCFLVN27LLLM6FV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NAOWHN2JUVKCFLVN27LLLM6FV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NAOWHN2JUVKCFLVN27LLLM6FV7","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":"11acd75b0a8341ae4618390aa01ec10731fc427b132403743eb53c80e3193b96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T20:55:29Z","title_canon_sha256":"1f8b40728b816ba1e09227e6b181c2b87bd4afcb80d879a93f838f82d0086d9f"},"schema_version":"1.0","source":{"id":"2310.17774","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17774","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17774v1","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17774","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"NAOWHN2JUVKC","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"NAOWHN2JUVKCFLVN","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"NAOWHN2J","created_at":"2026-07-05T07:05:52Z"}],"graph_snapshots":[{"event_id":"sha256:3c3eaf9ab652702710e10f6921f51a429765254ca29b1fd6742866c2605434d6","target":"graph","created_at":"2026-07-05T07:05:52Z","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/2310.17774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words into morphemes. Does that matter? We carefully test this by comparing surprisal estimates using orthographic, morphological, and BPE tokenization against reading time data. Our results replicate previous findings and provide evidence that in the aggregate, predictions using BPE tokenization do not suffer relative to morphological and orthographic segmentation. However, a finer-grained analysis points to potential is","authors_text":"Philip Resnik, Sathvik Nair","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T20:55:29Z","title":"Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17774","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":"sha256:45db3c31240eca8c74cc483b6199fa8435f7a3f33d8b213fc1c564841fe635dc","target":"record","created_at":"2026-07-05T07:05:52Z","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":"11acd75b0a8341ae4618390aa01ec10731fc427b132403743eb53c80e3193b96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T20:55:29Z","title_canon_sha256":"1f8b40728b816ba1e09227e6b181c2b87bd4afcb80d879a93f838f82d0086d9f"},"schema_version":"1.0","source":{"id":"2310.17774","kind":"arxiv","version":1}},"canonical_sha256":"681d63b749a55422aeadd7d6b5b3c5afe002c71b54bcf5ae2594dc0deb8a3b4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"681d63b749a55422aeadd7d6b5b3c5afe002c71b54bcf5ae2594dc0deb8a3b4f","first_computed_at":"2026-07-05T07:05:52.408794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:52.408794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAJZZIquUY7v/rYSvgBSEnS3eOzV6HOdkCiVF+v3Kv2ufByID/WqctnlmmWs+i0tqQonp0WdyHpycR1boV9jCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:52.409187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17774","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45db3c31240eca8c74cc483b6199fa8435f7a3f33d8b213fc1c564841fe635dc","sha256:3c3eaf9ab652702710e10f6921f51a429765254ca29b1fd6742866c2605434d6"],"state_sha256":"15de27845a4c6c61978e62a5bbff0b016c6b11e633fc054c522cb339216ef0cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JsdCe9lzAGgJP4UZEAujtlxJwBkDsiLF1k59SLQr0GTFM5iJRSAseLcUg8b+TZRg6prQoGgkNMI6RX97Gd7tAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:50:37.674831Z","bundle_sha256":"e6ac70ce99c2108b591f1e8319571cf413b170d2d801906c4066dc6ec933e4fa"}}