{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SG22L5F4HJZD7456YXKCAFV2JB","short_pith_number":"pith:SG22L5F4","schema_version":"1.0","canonical_sha256":"91b5a5f4bc3a723ff3bec5d42016ba485ad1d49419af43137d8e6d0fb2185e32","source":{"kind":"arxiv","id":"1502.03296","version":1},"attestation_state":"computed","paper":{"title":"Statistical laws in linguistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.data-an"],"primary_cat":"physics.soc-ph","authors_text":"Eduardo G. Altmann, Martin Gerlach","submitted_at":"2015-02-11T13:10:58Z","abstract_excerpt":"Zipf's law is just one out of many universal laws proposed to describe statistical regularities in language. Here we review and critically discuss how these laws can be statistically interpreted, fitted, and tested (falsified). The modern availability of large databases of written text allows for tests with an unprecedent statistical accuracy and also a characterization of the fluctuations around the typical behavior. We find that fluctuations are usually much larger than expected based on simplifying statistical assumptions (e.g., independence and lack of correlations between observations).Th"},"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":"1502.03296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2015-02-11T13:10:58Z","cross_cats_sorted":["cs.LG","physics.data-an"],"title_canon_sha256":"74cbd932349322a5afb5ec6ede9379bf740b033d2ebee1bb6df493acc4b1fbfb","abstract_canon_sha256":"35b1ce8f3b72c524519d51d221b7097ff99848881f8ffe85b8eeebcb1722bd88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:38.259896Z","signature_b64":"6OK73sQC+lStgmts7YlAOghjk3H9LUyYY0cP9bMJto+HPudT6z/8JA/LN0k1WzobdL4EC27SKCHRjP145GiiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91b5a5f4bc3a723ff3bec5d42016ba485ad1d49419af43137d8e6d0fb2185e32","last_reissued_at":"2026-05-18T01:13:38.259171Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:38.259171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical laws in linguistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.data-an"],"primary_cat":"physics.soc-ph","authors_text":"Eduardo G. Altmann, Martin Gerlach","submitted_at":"2015-02-11T13:10:58Z","abstract_excerpt":"Zipf's law is just one out of many universal laws proposed to describe statistical regularities in language. Here we review and critically discuss how these laws can be statistically interpreted, fitted, and tested (falsified). The modern availability of large databases of written text allows for tests with an unprecedent statistical accuracy and also a characterization of the fluctuations around the typical behavior. We find that fluctuations are usually much larger than expected based on simplifying statistical assumptions (e.g., independence and lack of correlations between observations).Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03296","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":"1502.03296","created_at":"2026-05-18T01:13:38.259290+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.03296v1","created_at":"2026-05-18T01:13:38.259290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03296","created_at":"2026-05-18T01:13:38.259290+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG22L5F4HJZD","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG22L5F4HJZD7456","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG22L5F4","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28021","citing_title":"Universal statistical laws governing culinary design","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB","json":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB.json","graph_json":"https://pith.science/api/pith-number/SG22L5F4HJZD7456YXKCAFV2JB/graph.json","events_json":"https://pith.science/api/pith-number/SG22L5F4HJZD7456YXKCAFV2JB/events.json","paper":"https://pith.science/paper/SG22L5F4"},"agent_actions":{"view_html":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB","download_json":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB.json","view_paper":"https://pith.science/paper/SG22L5F4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.03296&json=true","fetch_graph":"https://pith.science/api/pith-number/SG22L5F4HJZD7456YXKCAFV2JB/graph.json","fetch_events":"https://pith.science/api/pith-number/SG22L5F4HJZD7456YXKCAFV2JB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB/action/storage_attestation","attest_author":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB/action/author_attestation","sign_citation":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB/action/citation_signature","submit_replication":"https://pith.science/pith/SG22L5F4HJZD7456YXKCAFV2JB/action/replication_record"}},"created_at":"2026-05-18T01:13:38.259290+00:00","updated_at":"2026-05-18T01:13:38.259290+00:00"}