{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QY742VBWWHI2QTGMP3CBVDVGJY","short_pith_number":"pith:QY742VBW","canonical_record":{"source":{"id":"2109.12258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T01:48:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b28016954490bb4eddf13e082894c642ace97a8126ab1e906559fe7073c7430","abstract_canon_sha256":"86e3a32e10c81ad3279df0a1a31b10e6ec5fc6889db9697188542d910cd6c94c"},"schema_version":"1.0"},"canonical_sha256":"863fcd5436b1d1a84ccc7ec41a8ea64e1a04f4fe24292fb1d08b85312269b19e","source":{"kind":"arxiv","id":"2109.12258","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12258","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12258v2","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12258","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"QY742VBWWHI2","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"pith_short_16","alias_value":"QY742VBWWHI2QTGM","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"pith_short_8","alias_value":"QY742VBW","created_at":"2026-07-05T08:32:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QY742VBWWHI2QTGMP3CBVDVGJY","target":"record","payload":{"canonical_record":{"source":{"id":"2109.12258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T01:48:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b28016954490bb4eddf13e082894c642ace97a8126ab1e906559fe7073c7430","abstract_canon_sha256":"86e3a32e10c81ad3279df0a1a31b10e6ec5fc6889db9697188542d910cd6c94c"},"schema_version":"1.0"},"canonical_sha256":"863fcd5436b1d1a84ccc7ec41a8ea64e1a04f4fe24292fb1d08b85312269b19e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:27.000734Z","signature_b64":"7ChCfV5M8oUH+INQxuPKJ148Ew+Nj+pGm5lBShp4kdCpt5Z/vODSinB65vGR/JYuK5mRwfUNzfiLdQED3jVACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"863fcd5436b1d1a84ccc7ec41a8ea64e1a04f4fe24292fb1d08b85312269b19e","last_reissued_at":"2026-07-05T08:32:27.000272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:27.000272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.12258","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuB64wFaz9kGO5kxy7skbUNZ9eEoefzh4+uFQIPOs2Hnfxv597fa9gUVDJiSclo1SWitxVYihMMljYpJlhZTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:37:48.308479Z"},"content_sha256":"6100a00089480cff8a37fce5974d3f2af1fcb151ff6ded076551cbd30341f37c","schema_version":"1.0","event_id":"sha256:6100a00089480cff8a37fce5974d3f2af1fcb151ff6ded076551cbd30341f37c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QY742VBWWHI2QTGMP3CBVDVGJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bruce W. Lee, Jason Hyung-Jong Lee, Yoo Sung Jang","submitted_at":"2021-09-25T01:48:22Z","abstract_excerpt":"We report two essential improvements in readability assessment: 1. three novel features in advanced semantics and 2. the timely evidence that traditional ML models (e.g. Random Forest, using handcrafted features) can combine with transformers (e.g. RoBERTa) to augment model performance. First, we explore suitable transformers and traditional ML models. Then, we extract 255 handcrafted linguistic features using self-developed extraction software. Finally, we assemble those to create several hybrid models, achieving state-of-the-art (SOTA) accuracy on popular datasets in readability assessment. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12258","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/2109.12258/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":"2026-07-05T08:32:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dM4u7KhD9BkyTKIl7mZXsFTy88++a/K3cdKuOgvTshiyA9HlHQR4+1wY5eKi0OLNSHJIcjsWT+zZt3E6jxsDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:37:48.308986Z"},"content_sha256":"0ede451f4df2b872e13042d4b56b6df61dc69570fc19142b152e082e8bf67c81","schema_version":"1.0","event_id":"sha256:0ede451f4df2b872e13042d4b56b6df61dc69570fc19142b152e082e8bf67c81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QY742VBWWHI2QTGMP3CBVDVGJY/bundle.json","state_url":"https://pith.science/pith/QY742VBWWHI2QTGMP3CBVDVGJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QY742VBWWHI2QTGMP3CBVDVGJY/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":"2026-08-13T04:37:48Z","links":{"resolver":"https://pith.science/pith/QY742VBWWHI2QTGMP3CBVDVGJY","bundle":"https://pith.science/pith/QY742VBWWHI2QTGMP3CBVDVGJY/bundle.json","state":"https://pith.science/pith/QY742VBWWHI2QTGMP3CBVDVGJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QY742VBWWHI2QTGMP3CBVDVGJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QY742VBWWHI2QTGMP3CBVDVGJY","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":"86e3a32e10c81ad3279df0a1a31b10e6ec5fc6889db9697188542d910cd6c94c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T01:48:22Z","title_canon_sha256":"8b28016954490bb4eddf13e082894c642ace97a8126ab1e906559fe7073c7430"},"schema_version":"1.0","source":{"id":"2109.12258","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12258","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12258v2","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12258","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"QY742VBWWHI2","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"pith_short_16","alias_value":"QY742VBWWHI2QTGM","created_at":"2026-07-05T08:32:27Z"},{"alias_kind":"pith_short_8","alias_value":"QY742VBW","created_at":"2026-07-05T08:32:27Z"}],"graph_snapshots":[{"event_id":"sha256:0ede451f4df2b872e13042d4b56b6df61dc69570fc19142b152e082e8bf67c81","target":"graph","created_at":"2026-07-05T08:32:27Z","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/2109.12258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We report two essential improvements in readability assessment: 1. three novel features in advanced semantics and 2. the timely evidence that traditional ML models (e.g. Random Forest, using handcrafted features) can combine with transformers (e.g. RoBERTa) to augment model performance. First, we explore suitable transformers and traditional ML models. Then, we extract 255 handcrafted linguistic features using self-developed extraction software. Finally, we assemble those to create several hybrid models, achieving state-of-the-art (SOTA) accuracy on popular datasets in readability assessment. ","authors_text":"Bruce W. Lee, Jason Hyung-Jong Lee, Yoo Sung Jang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T01:48:22Z","title":"Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12258","kind":"arxiv","version":2},"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":"sha256:6100a00089480cff8a37fce5974d3f2af1fcb151ff6ded076551cbd30341f37c","target":"record","created_at":"2026-07-05T08:32:27Z","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":"86e3a32e10c81ad3279df0a1a31b10e6ec5fc6889db9697188542d910cd6c94c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T01:48:22Z","title_canon_sha256":"8b28016954490bb4eddf13e082894c642ace97a8126ab1e906559fe7073c7430"},"schema_version":"1.0","source":{"id":"2109.12258","kind":"arxiv","version":2}},"canonical_sha256":"863fcd5436b1d1a84ccc7ec41a8ea64e1a04f4fe24292fb1d08b85312269b19e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"863fcd5436b1d1a84ccc7ec41a8ea64e1a04f4fe24292fb1d08b85312269b19e","first_computed_at":"2026-07-05T08:32:27.000272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:27.000272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ChCfV5M8oUH+INQxuPKJ148Ew+Nj+pGm5lBShp4kdCpt5Z/vODSinB65vGR/JYuK5mRwfUNzfiLdQED3jVACw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:27.000734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.12258","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6100a00089480cff8a37fce5974d3f2af1fcb151ff6ded076551cbd30341f37c","sha256:0ede451f4df2b872e13042d4b56b6df61dc69570fc19142b152e082e8bf67c81"],"state_sha256":"0a46fde08bcd29f68efd157566a292bcb354c8151e021af257d0c7cdcd317be7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dao/QwwR+wdln3QI8RTF2sMcMlB0Ii6bN4tcPS6AYrnH90kmfcYt6DN5Q2ZhyjARY/i71QUBsqHuf+a+w1nHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:37:48.314022Z","bundle_sha256":"8f9015fa8914e55e40694d0da6dcb0428bf5c3a0c479537bd42f49f5c7567be9"}}