{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DSR22LTVCHBOZIHY24MROU3RCA","short_pith_number":"pith:DSR22LTV","schema_version":"1.0","canonical_sha256":"1ca3ad2e7511c2eca0f8d71917537110106c97369a121b7addd74957dd177296","source":{"kind":"arxiv","id":"1505.03783","version":1},"attestation_state":"computed","paper":{"title":"Rank diversity of languages: Generic behavior in computational linguistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Gershenson, Carlos Pineda, Germinal Cocho, Jorge Flores, Sergio S\\'anchez","submitted_at":"2015-05-14T16:21:02Z","abstract_excerpt":"Statistical studies of languages have focused on the rank-frequency distribution of words. Instead, we introduce here a measure of how word ranks change in time and call this distribution \\emph{rank diversity}. We calculate this diversity for books published in six European languages since 1800, and find that it follows a universal lognormal distribution. Based on the mean and standard deviation associated with the lognormal distribution, we define three different word regimes of languages: \"heads\" consist of words which almost do not change their rank in time, \"bodies\" are words of general us"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1505.03783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-14T16:21:02Z","cross_cats_sorted":[],"title_canon_sha256":"d1e61a6191e43e400f87f63ea11adff988cb7420ae31660c00357c67da7c9315","abstract_canon_sha256":"6f4ab8c4f4ca69c7bee757a2bff20d40078677742d15b15a6bc226ab5ecd7fff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:09:53.091848Z","signature_b64":"hgm59yO8lnm7CL9ajmWsDbsfnZXE1c/zziZpcnPlldt1o8fIlP+T5zNcqZcT6C0CQ3eCUwkCvndP+Bzw1GHsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca3ad2e7511c2eca0f8d71917537110106c97369a121b7addd74957dd177296","last_reissued_at":"2026-05-18T02:09:53.091157Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:09:53.091157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rank diversity of languages: Generic behavior in computational linguistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Gershenson, Carlos Pineda, Germinal Cocho, Jorge Flores, Sergio S\\'anchez","submitted_at":"2015-05-14T16:21:02Z","abstract_excerpt":"Statistical studies of languages have focused on the rank-frequency distribution of words. Instead, we introduce here a measure of how word ranks change in time and call this distribution \\emph{rank diversity}. We calculate this diversity for books published in six European languages since 1800, and find that it follows a universal lognormal distribution. Based on the mean and standard deviation associated with the lognormal distribution, we define three different word regimes of languages: \"heads\" consist of words which almost do not change their rank in time, \"bodies\" are words of general us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.03783","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1505.03783","created_at":"2026-05-18T02:09:53.091249+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.03783v1","created_at":"2026-05-18T02:09:53.091249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.03783","created_at":"2026-05-18T02:09:53.091249+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSR22LTVCHBO","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSR22LTVCHBOZIHY","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSR22LTV","created_at":"2026-05-18T12:29:17.054201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA","json":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA.json","graph_json":"https://pith.science/api/pith-number/DSR22LTVCHBOZIHY24MROU3RCA/graph.json","events_json":"https://pith.science/api/pith-number/DSR22LTVCHBOZIHY24MROU3RCA/events.json","paper":"https://pith.science/paper/DSR22LTV"},"agent_actions":{"view_html":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA","download_json":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA.json","view_paper":"https://pith.science/paper/DSR22LTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.03783&json=true","fetch_graph":"https://pith.science/api/pith-number/DSR22LTVCHBOZIHY24MROU3RCA/graph.json","fetch_events":"https://pith.science/api/pith-number/DSR22LTVCHBOZIHY24MROU3RCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA/action/storage_attestation","attest_author":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA/action/author_attestation","sign_citation":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA/action/citation_signature","submit_replication":"https://pith.science/pith/DSR22LTVCHBOZIHY24MROU3RCA/action/replication_record"}},"created_at":"2026-05-18T02:09:53.091249+00:00","updated_at":"2026-05-18T02:09:53.091249+00:00"}