{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BT2ZM5SWQQ2NGDOAPPNMP562TS","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":"793d9deb781b1876f9aad5fbf80b01dc9cb7af9b6668731dec5a3734e4116205","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T22:40:16Z","title_canon_sha256":"d18b8ca6d5ee280660a11ce93d4c6b738288d7ac90b1f4e1afbd5a9f156ef432"},"schema_version":"1.0","source":{"id":"2506.14046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14046","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14046v1","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14046","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"BT2ZM5SWQQ2N","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"BT2ZM5SWQQ2NGDOA","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"BT2ZM5SW","created_at":"2026-07-05T11:22:48Z"}],"graph_snapshots":[{"event_id":"sha256:4afe924c34d341e5082f5a52bb66f085f88218bed652d0feb242f6aa2ea3d32a","target":"graph","created_at":"2026-07-05T11:22:48Z","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/2506.14046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chloe Sophia Bellows, David Kogan, Jared Bernstein, Masanori Suzuki, Max Schumacher, Melissa Smith, Sam Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T22:40:16Z","title":"Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14046","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":"sha256:920a7f9ae3adaa1e2c73accdd0529c59ea364051453a6ffc06bcb0982931c627","target":"record","created_at":"2026-07-05T11:22:48Z","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":"793d9deb781b1876f9aad5fbf80b01dc9cb7af9b6668731dec5a3734e4116205","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T22:40:16Z","title_canon_sha256":"d18b8ca6d5ee280660a11ce93d4c6b738288d7ac90b1f4e1afbd5a9f156ef432"},"schema_version":"1.0","source":{"id":"2506.14046","kind":"arxiv","version":1}},"canonical_sha256":"0cf59676568434d30dc07bdac7f7da9cbbc5a1e613dc12ff10d2b3e8cd35b723","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cf59676568434d30dc07bdac7f7da9cbbc5a1e613dc12ff10d2b3e8cd35b723","first_computed_at":"2026-07-05T11:22:48.099094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:48.099094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GwKj8JxXGhBaENkYXmuc2xvaGaaCr3eKs0ZS7K7J2SEoowU17apUorzvOXlm2iz3Ju19C43Lut8Ismc8nWYBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:48.099552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:920a7f9ae3adaa1e2c73accdd0529c59ea364051453a6ffc06bcb0982931c627","sha256:4afe924c34d341e5082f5a52bb66f085f88218bed652d0feb242f6aa2ea3d32a"],"state_sha256":"537a02ecacbff1d4831288fbc9f65d0a9ec18daf8f28fae97913fd81d0f66cc7"}