{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:4LCPTOBY2DL2ETGEOQZS5P5JSK","short_pith_number":"pith:4LCPTOBY","schema_version":"1.0","canonical_sha256":"e2c4f9b838d0d7a24cc474332ebfa992b88cef701cfbee82b7c5a3f98c80aa4b","source":{"kind":"arxiv","id":"1402.1939","version":2},"attestation_state":"computed","paper":{"title":"Maximum Entropy, Word-Frequency, Chinese Characters, and Multiple Meanings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"physics.soc-ph","authors_text":"Petter Minnhagen, Xiao-Yong Yan","submitted_at":"2014-02-09T11:47:15Z","abstract_excerpt":"The word-frequency distribution of a text written by an author is well accounted for by a maximum entropy distribution, the RGF (random group formation)-prediction. The RGF-distribution is completely determined by the a priori values of the total number of words in the text (M), the number of distinct words (N) and the number of repetitions of the most common word (k_max). It is here shown that this maximum entropy prediction also describes a text written in Chinese characters. In particular it is shown that although the same Chinese text written in words and Chinese characters have quite diff"},"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":"1402.1939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2014-02-09T11:47:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"99535cd77794b7dce36b70921af5473e2eb25d1eff5f66ca6cf2fcf6db18c526","abstract_canon_sha256":"9f8565d566c7b6eccf148d1f89fc231901bbc12641399649fe8b163da7fb32ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:00.585798Z","signature_b64":"rOSeP2kspNc2HTQxrsXU1gc0MA41fFelLHTEmpnC3cx4vD1j6AqACaq1R+d1Qc2gppVNstFk2bY+BhfBkXOACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2c4f9b838d0d7a24cc474332ebfa992b88cef701cfbee82b7c5a3f98c80aa4b","last_reissued_at":"2026-05-18T00:34:00.584855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:00.584855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Entropy, Word-Frequency, Chinese Characters, and Multiple Meanings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"physics.soc-ph","authors_text":"Petter Minnhagen, Xiao-Yong Yan","submitted_at":"2014-02-09T11:47:15Z","abstract_excerpt":"The word-frequency distribution of a text written by an author is well accounted for by a maximum entropy distribution, the RGF (random group formation)-prediction. The RGF-distribution is completely determined by the a priori values of the total number of words in the text (M), the number of distinct words (N) and the number of repetitions of the most common word (k_max). It is here shown that this maximum entropy prediction also describes a text written in Chinese characters. In particular it is shown that although the same Chinese text written in words and Chinese characters have quite diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.1939","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":""},"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":"1402.1939","created_at":"2026-05-18T00:34:00.584990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.1939v2","created_at":"2026-05-18T00:34:00.584990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.1939","created_at":"2026-05-18T00:34:00.584990+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LCPTOBY2DL2","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LCPTOBY2DL2ETGE","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LCPTOBY","created_at":"2026-05-18T12:28:14.216126+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/4LCPTOBY2DL2ETGEOQZS5P5JSK","json":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK.json","graph_json":"https://pith.science/api/pith-number/4LCPTOBY2DL2ETGEOQZS5P5JSK/graph.json","events_json":"https://pith.science/api/pith-number/4LCPTOBY2DL2ETGEOQZS5P5JSK/events.json","paper":"https://pith.science/paper/4LCPTOBY"},"agent_actions":{"view_html":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK","download_json":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK.json","view_paper":"https://pith.science/paper/4LCPTOBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.1939&json=true","fetch_graph":"https://pith.science/api/pith-number/4LCPTOBY2DL2ETGEOQZS5P5JSK/graph.json","fetch_events":"https://pith.science/api/pith-number/4LCPTOBY2DL2ETGEOQZS5P5JSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK/action/storage_attestation","attest_author":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK/action/author_attestation","sign_citation":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK/action/citation_signature","submit_replication":"https://pith.science/pith/4LCPTOBY2DL2ETGEOQZS5P5JSK/action/replication_record"}},"created_at":"2026-05-18T00:34:00.584990+00:00","updated_at":"2026-05-18T00:34:00.584990+00:00"}