{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BT2ZM5SWQQ2NGDOAPPNMP562TS","short_pith_number":"pith:BT2ZM5SW","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"},"canonical_sha256":"0cf59676568434d30dc07bdac7f7da9cbbc5a1e613dc12ff10d2b3e8cd35b723","source":{"kind":"arxiv","id":"2506.14046","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BT2ZM5SWQQ2NGDOAPPNMP562TS","target":"record","payload":{"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"},"canonical_sha256":"0cf59676568434d30dc07bdac7f7da9cbbc5a1e613dc12ff10d2b3e8cd35b723","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"},"source_kind":"arxiv","source_id":"2506.14046","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":"2026-07-05T11:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKAfvHAJ+rVJ0rTb1uWvQwZiJYHPNyfzCMyzHaDQK4IcVzC6uy/MtPOtf8TF19hWMY3b3l33ch/+g/LOzB78Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:16:26.034801Z"},"content_sha256":"920a7f9ae3adaa1e2c73accdd0529c59ea364051453a6ffc06bcb0982931c627","schema_version":"1.0","event_id":"sha256:920a7f9ae3adaa1e2c73accdd0529c59ea364051453a6ffc06bcb0982931c627"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BT2ZM5SWQQ2NGDOAPPNMP562TS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H37d960zeJgoJLtgN2nUI6xxphDNrGbcXfjyXJ5XoqJ29ivZN9x4R51bl0kgk6Y7iQCAYI1Rx4rTAXuNrX6fDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:16:26.035805Z"},"content_sha256":"4afe924c34d341e5082f5a52bb66f085f88218bed652d0feb242f6aa2ea3d32a","schema_version":"1.0","event_id":"sha256:4afe924c34d341e5082f5a52bb66f085f88218bed652d0feb242f6aa2ea3d32a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/bundle.json","state_url":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/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":"2026-08-04T14:16:26Z","links":{"resolver":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS","bundle":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/bundle.json","state":"https://pith.science/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BT2ZM5SWQQ2NGDOAPPNMP562TS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RezhSHlnQSTQ9Yh78Qt9thZkt+YxCn+m2kE03LGyvIJA5I2gvhFvxkogzqo/WzYBo2grdx2zYltsgotyboOXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:16:26.117335Z","bundle_sha256":"8088eca9e15141ef579558fd89f6a73d84ed4e1c58d9ee93b9bcaff4b893fdcf"}}