{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5IABA4LE7QQXYJKXXPIUB33FQ7","short_pith_number":"pith:5IABA4LE","canonical_record":{"source":{"id":"2307.04626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T15:10:56Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"3a9044ecc5d9a1edc00916284c8ef08b7c0e692c56ca792e559cbf6112d2bed0","abstract_canon_sha256":"88680574d82bb0520f4486b4335836c82bead1a495277134bd507153aa01f8f7"},"schema_version":"1.0"},"canonical_sha256":"ea00107164fc217c2557bbd140ef6587d0ed5d187691063b0bbab816b458f359","source":{"kind":"arxiv","id":"2307.04626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04626","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04626v2","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04626","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"5IABA4LE7QQX","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"5IABA4LE7QQXYJKX","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"5IABA4LE","created_at":"2026-07-05T06:35:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5IABA4LE7QQXYJKXXPIUB33FQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T15:10:56Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"3a9044ecc5d9a1edc00916284c8ef08b7c0e692c56ca792e559cbf6112d2bed0","abstract_canon_sha256":"88680574d82bb0520f4486b4335836c82bead1a495277134bd507153aa01f8f7"},"schema_version":"1.0"},"canonical_sha256":"ea00107164fc217c2557bbd140ef6587d0ed5d187691063b0bbab816b458f359","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:52.824789Z","signature_b64":"snKrEqLl1cMjpjMKJ15qKjM88s/tiB3Tbj9nNJdgmrTGLB2bv+p7F2L7F3iMtankehFG62aHKbpk+kn6hywYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea00107164fc217c2557bbd140ef6587d0ed5d187691063b0bbab816b458f359","last_reissued_at":"2026-07-05T06:35:52.824374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:52.824374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04626","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":"2026-07-05T06:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sHWaPG7V9FRtcYEXPs6jaEvgxyqSvq/2yJUG2ceLX55IPegBl8+OSk8ecv78tFn10B4Dpjs519McP1BVCor3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:41:57.964364Z"},"content_sha256":"70282f6b10a050959434a9b2fa596109e1e6ad7204c2f92e40ae0b6e62eb6854","schema_version":"1.0","event_id":"sha256:70282f6b10a050959434a9b2fa596109e1e6ad7204c2f92e40ae0b6e62eb6854"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5IABA4LE7QQXYJKXXPIUB33FQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring Lexical Diversity in Texts: The Twofold Length Problem","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CL","authors_text":"Yves Bestgen","submitted_at":"2023-07-10T15:10:56Z","abstract_excerpt":"The impact of text length on the estimation of lexical diversity has captured the attention of the scientific community for more than a century. Numerous indices have been proposed, and many studies have been conducted to evaluate them, but the problem remains. This methodological review provides a critical analysis not only of the most commonly used indices in language learning studies, but also of the length problem itself, as well as of the methodology for evaluating the proposed solutions. The analysis of three datasets of English language-learners' texts revealed that indices that reduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04626","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/2307.04626/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":"2026-07-05T06:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IMD5I5UxRrR6wgziY2CLXLWYmh/gqilI+TyjolpaTH1kSVg6b2JxF0ornPMb6dguwvWVf5ZtTpUJ+TpihpfFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:41:57.964876Z"},"content_sha256":"e45945128e49b275e6423eabf026654d7ed7e2a4f2a9b187142687841102fa3b","schema_version":"1.0","event_id":"sha256:e45945128e49b275e6423eabf026654d7ed7e2a4f2a9b187142687841102fa3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IABA4LE7QQXYJKXXPIUB33FQ7/bundle.json","state_url":"https://pith.science/pith/5IABA4LE7QQXYJKXXPIUB33FQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IABA4LE7QQXYJKXXPIUB33FQ7/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":"2026-08-07T15:41:57Z","links":{"resolver":"https://pith.science/pith/5IABA4LE7QQXYJKXXPIUB33FQ7","bundle":"https://pith.science/pith/5IABA4LE7QQXYJKXXPIUB33FQ7/bundle.json","state":"https://pith.science/pith/5IABA4LE7QQXYJKXXPIUB33FQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IABA4LE7QQXYJKXXPIUB33FQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5IABA4LE7QQXYJKXXPIUB33FQ7","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":"88680574d82bb0520f4486b4335836c82bead1a495277134bd507153aa01f8f7","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T15:10:56Z","title_canon_sha256":"3a9044ecc5d9a1edc00916284c8ef08b7c0e692c56ca792e559cbf6112d2bed0"},"schema_version":"1.0","source":{"id":"2307.04626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04626","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04626v2","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04626","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"5IABA4LE7QQX","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"5IABA4LE7QQXYJKX","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"5IABA4LE","created_at":"2026-07-05T06:35:52Z"}],"graph_snapshots":[{"event_id":"sha256:e45945128e49b275e6423eabf026654d7ed7e2a4f2a9b187142687841102fa3b","target":"graph","created_at":"2026-07-05T06:35:52Z","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/2307.04626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The impact of text length on the estimation of lexical diversity has captured the attention of the scientific community for more than a century. Numerous indices have been proposed, and many studies have been conducted to evaluate them, but the problem remains. This methodological review provides a critical analysis not only of the most commonly used indices in language learning studies, but also of the length problem itself, as well as of the methodology for evaluating the proposed solutions. The analysis of three datasets of English language-learners' texts revealed that indices that reduce ","authors_text":"Yves Bestgen","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T15:10:56Z","title":"Measuring Lexical Diversity in Texts: The Twofold Length Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04626","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":"sha256:70282f6b10a050959434a9b2fa596109e1e6ad7204c2f92e40ae0b6e62eb6854","target":"record","created_at":"2026-07-05T06:35:52Z","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":"88680574d82bb0520f4486b4335836c82bead1a495277134bd507153aa01f8f7","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T15:10:56Z","title_canon_sha256":"3a9044ecc5d9a1edc00916284c8ef08b7c0e692c56ca792e559cbf6112d2bed0"},"schema_version":"1.0","source":{"id":"2307.04626","kind":"arxiv","version":2}},"canonical_sha256":"ea00107164fc217c2557bbd140ef6587d0ed5d187691063b0bbab816b458f359","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea00107164fc217c2557bbd140ef6587d0ed5d187691063b0bbab816b458f359","first_computed_at":"2026-07-05T06:35:52.824374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:52.824374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snKrEqLl1cMjpjMKJ15qKjM88s/tiB3Tbj9nNJdgmrTGLB2bv+p7F2L7F3iMtankehFG62aHKbpk+kn6hywYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:52.824789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70282f6b10a050959434a9b2fa596109e1e6ad7204c2f92e40ae0b6e62eb6854","sha256:e45945128e49b275e6423eabf026654d7ed7e2a4f2a9b187142687841102fa3b"],"state_sha256":"f3bfe81d0374d9598e10da4e872c41c3af901464df4662f0018fcfbbb930486c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RRTO4m5znw10ahzenXY8X32vzZmjxeYjVMYSQgbNRqHQ15wjRooJzn7XXMZCV7HRfnDQDpnHXmsldFa2OIDJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:41:57.968897Z","bundle_sha256":"33a383372c605b27892ac5239c4137d46ffcc70f754336adf203a4fe93cbb222"}}