{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5A5Z43WO4L2HEQF5L6WSGVPJT","short_pith_number":"pith:F5A5Z43W","schema_version":"1.0","canonical_sha256":"2f41dcf3767717a39205eafd691aaf4cdbac93dd0c7f36a9fad4cff05d31f9f0","source":{"kind":"arxiv","id":"2601.09886","version":2},"attestation_state":"computed","paper":{"title":"Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byung-Doh Oh, Sathvik Nair","submitted_at":"2026-01-14T21:38:54Z","abstract_excerpt":"How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities derived from cloze data. However, it is important to establish that LM probabilities do so for the right reasons, since different predictors can lead to different scientific conclusions about the role of prediction in language comprehension. We present evidence for three hypotheses about the advantage of LM probabilities: not suffering from low resolution, distin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.09886","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-14T21:38:54Z","cross_cats_sorted":[],"title_canon_sha256":"d8f9ebf7ef85fb11ec507aed9392d44b55d9d5d5013d78b9b156cdb79ef91ece","abstract_canon_sha256":"3bcac7df003c4899770f814084179d0bf654cb6246171ff07f6a7e26a4a13e66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:13.529084Z","signature_b64":"X8tkIDep9E6HDtmw7opoWuBB51W6acZLSz+jqVCFpKJ9h37k8yBUwBez5hK0PMUqQCi6v9louXC1hmjQ28cnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f41dcf3767717a39205eafd691aaf4cdbac93dd0c7f36a9fad4cff05d31f9f0","last_reissued_at":"2026-05-27T02:06:13.528217Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:13.528217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byung-Doh Oh, Sathvik Nair","submitted_at":"2026-01-14T21:38:54Z","abstract_excerpt":"How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities derived from cloze data. However, it is important to establish that LM probabilities do so for the right reasons, since different predictors can lead to different scientific conclusions about the role of prediction in language comprehension. We present evidence for three hypotheses about the advantage of LM probabilities: not suffering from low resolution, distin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09886","kind":"arxiv","version":2},"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/2601.09886/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.09886","created_at":"2026-05-27T02:06:13.528348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.09886v2","created_at":"2026-05-27T02:06:13.528348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09886","created_at":"2026-05-27T02:06:13.528348+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5A5Z43WO4L2","created_at":"2026-05-27T02:06:13.528348+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5A5Z43WO4L2HEQF","created_at":"2026-05-27T02:06:13.528348+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5A5Z43W","created_at":"2026-05-27T02:06:13.528348+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT","json":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT.json","graph_json":"https://pith.science/api/pith-number/F5A5Z43WO4L2HEQF5L6WSGVPJT/graph.json","events_json":"https://pith.science/api/pith-number/F5A5Z43WO4L2HEQF5L6WSGVPJT/events.json","paper":"https://pith.science/paper/F5A5Z43W"},"agent_actions":{"view_html":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT","download_json":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT.json","view_paper":"https://pith.science/paper/F5A5Z43W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.09886&json=true","fetch_graph":"https://pith.science/api/pith-number/F5A5Z43WO4L2HEQF5L6WSGVPJT/graph.json","fetch_events":"https://pith.science/api/pith-number/F5A5Z43WO4L2HEQF5L6WSGVPJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT/action/storage_attestation","attest_author":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT/action/author_attestation","sign_citation":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT/action/citation_signature","submit_replication":"https://pith.science/pith/F5A5Z43WO4L2HEQF5L6WSGVPJT/action/replication_record"}},"created_at":"2026-05-27T02:06:13.528348+00:00","updated_at":"2026-05-27T02:06:13.528348+00:00"}