{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:TXYFHYGRG5DNXFQVEXWPFK7DOL","short_pith_number":"pith:TXYFHYGR","schema_version":"1.0","canonical_sha256":"9df053e0d13746db961525ecf2abe372fc42a943064be16e14704551a4d68f6c","source":{"kind":"arxiv","id":"1212.1362","version":3},"attestation_state":"computed","paper":{"title":"Stochastic model for the vocabulary growth in natural languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","physics.data-an"],"primary_cat":"physics.soc-ph","authors_text":"Eduardo G. Altmann, Martin Gerlach","submitted_at":"2012-12-06T16:06:21Z","abstract_excerpt":"We propose a stochastic model for the number of different words in a given database which incorporates the dependence on the database size and historical changes. The main feature of our model is the existence of two different classes of words: (i) a finite number of core-words which have higher frequency and do not affect the probability of a new word to be used; and (ii) the remaining virtually infinite number of noncore-words which have lower frequency and once used reduce the probability of a new word to be used in the future. Our model relies on a careful analysis of the google-ngram data"},"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":"1212.1362","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2012-12-06T16:06:21Z","cross_cats_sorted":["cs.CL","physics.data-an"],"title_canon_sha256":"1b71a620a6a68785d3eb93964c08494e3f99cb8b6c4e557de48b0ad23bb706cb","abstract_canon_sha256":"fadf8a1bdb5c195c83a29ec4340f5e532650c7ef30cadecd28e4dafcaac79122"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:25:43.516765Z","signature_b64":"VzVaEr8GGeHiZKVNmWVQNNsnUjJlIq0hAwbBf0tDVjei1zG4HkrEAR4W+TtmDmUZ9cnBMlsZV2Prec9RSj4TBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df053e0d13746db961525ecf2abe372fc42a943064be16e14704551a4d68f6c","last_reissued_at":"2026-05-18T03:25:43.515933Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:25:43.515933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic model for the vocabulary growth in natural languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","physics.data-an"],"primary_cat":"physics.soc-ph","authors_text":"Eduardo G. Altmann, Martin Gerlach","submitted_at":"2012-12-06T16:06:21Z","abstract_excerpt":"We propose a stochastic model for the number of different words in a given database which incorporates the dependence on the database size and historical changes. The main feature of our model is the existence of two different classes of words: (i) a finite number of core-words which have higher frequency and do not affect the probability of a new word to be used; and (ii) the remaining virtually infinite number of noncore-words which have lower frequency and once used reduce the probability of a new word to be used in the future. Our model relies on a careful analysis of the google-ngram data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.1362","kind":"arxiv","version":3},"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":"1212.1362","created_at":"2026-05-18T03:25:43.516071+00:00"},{"alias_kind":"arxiv_version","alias_value":"1212.1362v3","created_at":"2026-05-18T03:25:43.516071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.1362","created_at":"2026-05-18T03:25:43.516071+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXYFHYGRG5DN","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXYFHYGRG5DNXFQV","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXYFHYGR","created_at":"2026-05-18T12:27:23.164592+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/TXYFHYGRG5DNXFQVEXWPFK7DOL","json":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL.json","graph_json":"https://pith.science/api/pith-number/TXYFHYGRG5DNXFQVEXWPFK7DOL/graph.json","events_json":"https://pith.science/api/pith-number/TXYFHYGRG5DNXFQVEXWPFK7DOL/events.json","paper":"https://pith.science/paper/TXYFHYGR"},"agent_actions":{"view_html":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL","download_json":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL.json","view_paper":"https://pith.science/paper/TXYFHYGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1212.1362&json=true","fetch_graph":"https://pith.science/api/pith-number/TXYFHYGRG5DNXFQVEXWPFK7DOL/graph.json","fetch_events":"https://pith.science/api/pith-number/TXYFHYGRG5DNXFQVEXWPFK7DOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL/action/storage_attestation","attest_author":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL/action/author_attestation","sign_citation":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL/action/citation_signature","submit_replication":"https://pith.science/pith/TXYFHYGRG5DNXFQVEXWPFK7DOL/action/replication_record"}},"created_at":"2026-05-18T03:25:43.516071+00:00","updated_at":"2026-05-18T03:25:43.516071+00:00"}