{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2VSVJRBM7LTKTDR2EZUW2MKUJG","short_pith_number":"pith:2VSVJRBM","schema_version":"1.0","canonical_sha256":"d56554c42cfae6a98e3a26696d3154499c3382cf6159fa81a5ade39ac42b3094","source":{"kind":"arxiv","id":"2508.19221","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Evaluators: Are readability metrics good measures of readability?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Khashabi, Isabel Cachola, Mark Dredze","submitted_at":"2025-08-26T17:38:42Z","abstract_excerpt":"Plain Language Summarization (PLS) aims to distill complex documents into accessible summaries for non-expert audiences. In this paper, we conduct a thorough survey of PLS literature, and identify that the current standard practice for readability evaluation is to use traditional readability metrics, such as Flesch-Kincaid Grade Level (FKGL). However, despite proven utility in other fields, these metrics have not been compared to human readability judgments in PLS. We evaluate 8 readability metrics and show that most correlate poorly with human judgments, including the most popular metric, FKG"},"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":"2508.19221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T17:38:42Z","cross_cats_sorted":[],"title_canon_sha256":"69496fd68f5dcb83a364ad6babdfb933ae367b02d5507fd15a44da94729a5f38","abstract_canon_sha256":"c8e1e7f7e9e971ecf38bef2fd3505dce5b53f376cc7cb4f351902230ccfcc201"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:40.073294Z","signature_b64":"6dxUzVm/BXzqueX9C/Vi/1GyvdBxDglpo3ObcJIx6EvA0JF85Yf0sEZ4WImGvKyi8WBEEZIZxAdCmG1efP95DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d56554c42cfae6a98e3a26696d3154499c3382cf6159fa81a5ade39ac42b3094","last_reissued_at":"2026-07-05T11:59:40.072867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:40.072867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Evaluators: Are readability metrics good measures of readability?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Khashabi, Isabel Cachola, Mark Dredze","submitted_at":"2025-08-26T17:38:42Z","abstract_excerpt":"Plain Language Summarization (PLS) aims to distill complex documents into accessible summaries for non-expert audiences. In this paper, we conduct a thorough survey of PLS literature, and identify that the current standard practice for readability evaluation is to use traditional readability metrics, such as Flesch-Kincaid Grade Level (FKGL). However, despite proven utility in other fields, these metrics have not been compared to human readability judgments in PLS. We evaluate 8 readability metrics and show that most correlate poorly with human judgments, including the most popular metric, FKG"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19221","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/2508.19221/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":"2508.19221","created_at":"2026-07-05T11:59:40.072924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19221v1","created_at":"2026-07-05T11:59:40.072924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19221","created_at":"2026-07-05T11:59:40.072924+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VSVJRBM7LTK","created_at":"2026-07-05T11:59:40.072924+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VSVJRBM7LTKTDR2","created_at":"2026-07-05T11:59:40.072924+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VSVJRBM","created_at":"2026-07-05T11:59:40.072924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.04377","citing_title":"Disco-RAG: Discourse-Aware Retrieval-Augmented Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08889","citing_title":"Machine Learning Research Has Outpaced Its Communication Norms and NeurIPS Should Act","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG","json":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG.json","graph_json":"https://pith.science/api/pith-number/2VSVJRBM7LTKTDR2EZUW2MKUJG/graph.json","events_json":"https://pith.science/api/pith-number/2VSVJRBM7LTKTDR2EZUW2MKUJG/events.json","paper":"https://pith.science/paper/2VSVJRBM"},"agent_actions":{"view_html":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG","download_json":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG.json","view_paper":"https://pith.science/paper/2VSVJRBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19221&json=true","fetch_graph":"https://pith.science/api/pith-number/2VSVJRBM7LTKTDR2EZUW2MKUJG/graph.json","fetch_events":"https://pith.science/api/pith-number/2VSVJRBM7LTKTDR2EZUW2MKUJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG/action/storage_attestation","attest_author":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG/action/author_attestation","sign_citation":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG/action/citation_signature","submit_replication":"https://pith.science/pith/2VSVJRBM7LTKTDR2EZUW2MKUJG/action/replication_record"}},"created_at":"2026-07-05T11:59:40.072924+00:00","updated_at":"2026-07-05T11:59:40.072924+00:00"}