{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AWMZB5326M4STHFK3PFOCT6H6L","short_pith_number":"pith:AWMZB532","canonical_record":{"source":{"id":"2303.04851","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T19:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"3d3e33b7f48851f5289e8d1dc076a567fc86b7449c927614d32f6e2fdb53c546","abstract_canon_sha256":"52ee9bb5a69883b5ce5133c399868c7c732c7ca11d1e4b47a9df0c15af160375"},"schema_version":"1.0"},"canonical_sha256":"059990f77af339299caadbcae14fc7f2f50acaa760b1592ca24f75a00176f9fc","source":{"kind":"arxiv","id":"2303.04851","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04851","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04851v1","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04851","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"AWMZB5326M4S","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"pith_short_16","alias_value":"AWMZB5326M4STHFK","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"pith_short_8","alias_value":"AWMZB532","created_at":"2026-07-05T05:49:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AWMZB5326M4STHFK3PFOCT6H6L","target":"record","payload":{"canonical_record":{"source":{"id":"2303.04851","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T19:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"3d3e33b7f48851f5289e8d1dc076a567fc86b7449c927614d32f6e2fdb53c546","abstract_canon_sha256":"52ee9bb5a69883b5ce5133c399868c7c732c7ca11d1e4b47a9df0c15af160375"},"schema_version":"1.0"},"canonical_sha256":"059990f77af339299caadbcae14fc7f2f50acaa760b1592ca24f75a00176f9fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:34.560377Z","signature_b64":"7w0DiSt5VIrMtvqKFI9YHISZiRWn8Tp2qTiHCD0Jah06nvAcpmOMotsSc2c+D/jePp0AgZEn5m6oQigiaLXMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"059990f77af339299caadbcae14fc7f2f50acaa760b1592ca24f75a00176f9fc","last_reissued_at":"2026-07-05T05:49:34.559897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:34.559897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.04851","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":"2026-07-05T05:49:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgDDYuv4WRR7ZBZIsFqHknu5KOe4ZZvzSAGYRD3yKBf+MLAgtTZtceist7E2tZuSIrcfYUft5Youz/IgIK2xCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:08:05.927028Z"},"content_sha256":"392f8dd732e96e4a113f7cd8c2c0d1ae966bdcd7233c2d503d406abf477c0151","schema_version":"1.0","event_id":"sha256:392f8dd732e96e4a113f7cd8c2c0d1ae966bdcd7233c2d503d406abf477c0151"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AWMZB5326M4STHFK3PFOCT6H6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lexical Complexity Prediction: An Overview","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai North, Marcos Zampieri, Matthew Shardlow","submitted_at":"2023-03-08T19:35:08Z","abstract_excerpt":"The occurrence of unknown words in texts significantly hinders reading comprehension. To improve accessibility for specific target populations, computational modelling has been applied to identify complex words in texts and substitute them for simpler alternatives. In this paper, we present an overview of computational approaches to lexical complexity prediction focusing on the work carried out on English data. We survey relevant approaches to this problem which include traditional machine learning classifiers (e.g. SVMs, logistic regression) and deep neural networks as well as a variety of fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04851","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/2303.04851/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":"2026-07-05T05:49:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5SBHyTvyihUiy8GZ1LlDkUfdXL9nSBP1RiLbi6EgejLhx3f5KAsdB5Efe6xtP3/DfqpQtxIpZh1+VLbFlokCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:08:05.927417Z"},"content_sha256":"5a024babc261a494460743e13c792b0451db20d7d1ddecc438cc382db78f8e85","schema_version":"1.0","event_id":"sha256:5a024babc261a494460743e13c792b0451db20d7d1ddecc438cc382db78f8e85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWMZB5326M4STHFK3PFOCT6H6L/bundle.json","state_url":"https://pith.science/pith/AWMZB5326M4STHFK3PFOCT6H6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWMZB5326M4STHFK3PFOCT6H6L/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":"2026-07-07T08:08:05Z","links":{"resolver":"https://pith.science/pith/AWMZB5326M4STHFK3PFOCT6H6L","bundle":"https://pith.science/pith/AWMZB5326M4STHFK3PFOCT6H6L/bundle.json","state":"https://pith.science/pith/AWMZB5326M4STHFK3PFOCT6H6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWMZB5326M4STHFK3PFOCT6H6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AWMZB5326M4STHFK3PFOCT6H6L","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":"52ee9bb5a69883b5ce5133c399868c7c732c7ca11d1e4b47a9df0c15af160375","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T19:35:08Z","title_canon_sha256":"3d3e33b7f48851f5289e8d1dc076a567fc86b7449c927614d32f6e2fdb53c546"},"schema_version":"1.0","source":{"id":"2303.04851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04851","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04851v1","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04851","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"AWMZB5326M4S","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"pith_short_16","alias_value":"AWMZB5326M4STHFK","created_at":"2026-07-05T05:49:34Z"},{"alias_kind":"pith_short_8","alias_value":"AWMZB532","created_at":"2026-07-05T05:49:34Z"}],"graph_snapshots":[{"event_id":"sha256:5a024babc261a494460743e13c792b0451db20d7d1ddecc438cc382db78f8e85","target":"graph","created_at":"2026-07-05T05:49:34Z","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/2303.04851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The occurrence of unknown words in texts significantly hinders reading comprehension. To improve accessibility for specific target populations, computational modelling has been applied to identify complex words in texts and substitute them for simpler alternatives. In this paper, we present an overview of computational approaches to lexical complexity prediction focusing on the work carried out on English data. We survey relevant approaches to this problem which include traditional machine learning classifiers (e.g. SVMs, logistic regression) and deep neural networks as well as a variety of fe","authors_text":"Kai North, Marcos Zampieri, Matthew Shardlow","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T19:35:08Z","title":"Lexical Complexity Prediction: An Overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04851","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":"sha256:392f8dd732e96e4a113f7cd8c2c0d1ae966bdcd7233c2d503d406abf477c0151","target":"record","created_at":"2026-07-05T05:49:34Z","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":"52ee9bb5a69883b5ce5133c399868c7c732c7ca11d1e4b47a9df0c15af160375","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T19:35:08Z","title_canon_sha256":"3d3e33b7f48851f5289e8d1dc076a567fc86b7449c927614d32f6e2fdb53c546"},"schema_version":"1.0","source":{"id":"2303.04851","kind":"arxiv","version":1}},"canonical_sha256":"059990f77af339299caadbcae14fc7f2f50acaa760b1592ca24f75a00176f9fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"059990f77af339299caadbcae14fc7f2f50acaa760b1592ca24f75a00176f9fc","first_computed_at":"2026-07-05T05:49:34.559897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:34.559897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7w0DiSt5VIrMtvqKFI9YHISZiRWn8Tp2qTiHCD0Jah06nvAcpmOMotsSc2c+D/jePp0AgZEn5m6oQigiaLXMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:34.560377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:392f8dd732e96e4a113f7cd8c2c0d1ae966bdcd7233c2d503d406abf477c0151","sha256:5a024babc261a494460743e13c792b0451db20d7d1ddecc438cc382db78f8e85"],"state_sha256":"6a6676644f4dbfe62458a41f84096cfc12aae00f4fc7573168ddc12bde4df1eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJP5regENfd9pbyhWP7JwDkKwEnTSL4tgEhMP/oZklAQ7QFgi5IGE2xpmm8czcMbgcJ/wmPj7hmiLTF+SBAlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:08:05.929363Z","bundle_sha256":"5d95c96381e65ab3025d38f5051ffea4719ab66110b8ac3d827ae08f306d2c0a"}}