{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BT2ZM5SWQQ2NGDOAPPNMP562TS","short_pith_number":"pith:BT2ZM5SW","schema_version":"1.0","canonical_sha256":"0cf59676568434d30dc07bdac7f7da9cbbc5a1e613dc12ff10d2b3e8cd35b723","source":{"kind":"arxiv","id":"2506.14046","version":1},"attestation_state":"computed","paper":{"title":"Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chloe Sophia Bellows, David Kogan, Jared Bernstein, Masanori Suzuki, Max Schumacher, Melissa Smith, Sam Nguyen","submitted_at":"2025-06-16T22:40:16Z","abstract_excerpt":"There is an unmet need to evaluate the language difficulty of short, conversational passages of text, particularly for training and filtering Large Language Models (LLMs). We introduce Ace-CEFR, a dataset of English conversational text passages expert-annotated with their corresponding level of text difficulty. We experiment with several models on Ace-CEFR, including Transformer-based models and LLMs. We show that models trained on Ace-CEFR can measure text difficulty more accurately than human experts and have latency appropriate to production environments. Finally, we release the Ace-CEFR da"},"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":"2506.14046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T22:40:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d18b8ca6d5ee280660a11ce93d4c6b738288d7ac90b1f4e1afbd5a9f156ef432","abstract_canon_sha256":"793d9deb781b1876f9aad5fbf80b01dc9cb7af9b6668731dec5a3734e4116205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:48.099552Z","signature_b64":"GwKj8JxXGhBaENkYXmuc2xvaGaaCr3eKs0ZS7K7J2SEoowU17apUorzvOXlm2iz3Ju19C43Lut8Ismc8nWYBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cf59676568434d30dc07bdac7f7da9cbbc5a1e613dc12ff10d2b3e8cd35b723","last_reissued_at":"2026-07-05T11:22:48.099094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:48.099094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chloe Sophia Bellows, David Kogan, Jared Bernstein, Masanori Suzuki, Max Schumacher, Melissa Smith, Sam Nguyen","submitted_at":"2025-06-16T22:40:16Z","abstract_excerpt":"There is an unmet need to evaluate the language difficulty of short, conversational passages of text, particularly for training and filtering Large Language Models (LLMs). We introduce Ace-CEFR, a dataset of English conversational text passages expert-annotated with their corresponding level of text difficulty. We experiment with several models on Ace-CEFR, including Transformer-based models and LLMs. We show that models trained on Ace-CEFR can measure text difficulty more accurately than human experts and have latency appropriate to production environments. Finally, we release the Ace-CEFR da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14046","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/2506.14046/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":"2506.14046","created_at":"2026-07-05T11:22:48.099154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14046v1","created_at":"2026-07-05T11:22:48.099154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14046","created_at":"2026-07-05T11:22:48.099154+00:00"},{"alias_kind":"pith_short_12","alias_value":"BT2ZM5SWQQ2N","created_at":"2026-07-05T11:22:48.099154+00:00"},{"alias_kind":"pith_short_16","alias_value":"BT2ZM5SWQQ2NGDOA","created_at":"2026-07-05T11:22:48.099154+00:00"},{"alias_kind":"pith_short_8","alias_value":"BT2ZM5SW","created_at":"2026-07-05T11:22:48.099154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27416","citing_title":"Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS","json":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS.json","graph_json":"https://pith.science/api/pith-number/BT2ZM5SWQQ2NGDOAPPNMP562TS/graph.json","events_json":"https://pith.science/api/pith-number/BT2ZM5SWQQ2NGDOAPPNMP562TS/events.json","paper":"https://pith.science/paper/BT2ZM5SW"},"agent_actions":{"view_html":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS","download_json":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS.json","view_paper":"https://pith.science/paper/BT2ZM5SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14046&json=true","fetch_graph":"https://pith.science/api/pith-number/BT2ZM5SWQQ2NGDOAPPNMP562TS/graph.json","fetch_events":"https://pith.science/api/pith-number/BT2ZM5SWQQ2NGDOAPPNMP562TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/action/storage_attestation","attest_author":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/action/author_attestation","sign_citation":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/action/citation_signature","submit_replication":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/action/replication_record"}},"created_at":"2026-07-05T11:22:48.099154+00:00","updated_at":"2026-07-05T11:22:48.099154+00:00"}