{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:GHMZOTF7LCBVQVVHNBS3GLH2XY","short_pith_number":"pith:GHMZOTF7","schema_version":"1.0","canonical_sha256":"31d9974cbf58835856a76865b32cfabe0fa2768c429189c11b44e5c2f090c7b0","source":{"kind":"arxiv","id":"1407.4610","version":2},"attestation_state":"computed","paper":{"title":"Understanding Zipf's law of word frequencies through sample-space collapse in sentence formation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"physics.soc-ph","authors_text":"Bernat Corominas-Murtra, Bo Liu, Rudolf Hanel, Stefan Thurner","submitted_at":"2014-07-17T09:38:07Z","abstract_excerpt":"The formation of sentences is a highly structured and history-dependent process. The probability of using a specific word in a sentence strongly depends on the 'history' of word-usage earlier in that sentence. We study a simple history-dependent model of text generation assuming that the sample-space of word usage reduces along sentence formation, on average. We first show that the model explains the approximate Zipf law found in word frequencies as a direct consequence of sample-space reduction. We then empirically quantify the amount of sample-space reduction in the sentences of ten famous E"},"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":"1407.4610","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2014-07-17T09:38:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2f0d19f4dd0f872572a6dba352f7095a13c8e4a947ae4bdc0704e0552a8152b7","abstract_canon_sha256":"aff0ed164d05836af66c2e6c8f1ef91d98447b83f0592d52dac2f31ebec5e9ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:02:08.351004Z","signature_b64":"x3bllfaw6SfL9ySfixOgIV3atzrrFQjFPml+aCuuij8QafKKxuRBOcT6bHTdnuru2I3ILxep0ANxdClSFO43Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d9974cbf58835856a76865b32cfabe0fa2768c429189c11b44e5c2f090c7b0","last_reissued_at":"2026-05-18T02:02:08.350495Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:02:08.350495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Zipf's law of word frequencies through sample-space collapse in sentence formation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"physics.soc-ph","authors_text":"Bernat Corominas-Murtra, Bo Liu, Rudolf Hanel, Stefan Thurner","submitted_at":"2014-07-17T09:38:07Z","abstract_excerpt":"The formation of sentences is a highly structured and history-dependent process. The probability of using a specific word in a sentence strongly depends on the 'history' of word-usage earlier in that sentence. We study a simple history-dependent model of text generation assuming that the sample-space of word usage reduces along sentence formation, on average. We first show that the model explains the approximate Zipf law found in word frequencies as a direct consequence of sample-space reduction. We then empirically quantify the amount of sample-space reduction in the sentences of ten famous E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.4610","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":"1407.4610","created_at":"2026-05-18T02:02:08.350569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1407.4610v2","created_at":"2026-05-18T02:02:08.350569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.4610","created_at":"2026-05-18T02:02:08.350569+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHMZOTF7LCBV","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHMZOTF7LCBVQVVH","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHMZOTF7","created_at":"2026-05-18T12:28:30.664211+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/GHMZOTF7LCBVQVVHNBS3GLH2XY","json":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY.json","graph_json":"https://pith.science/api/pith-number/GHMZOTF7LCBVQVVHNBS3GLH2XY/graph.json","events_json":"https://pith.science/api/pith-number/GHMZOTF7LCBVQVVHNBS3GLH2XY/events.json","paper":"https://pith.science/paper/GHMZOTF7"},"agent_actions":{"view_html":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY","download_json":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY.json","view_paper":"https://pith.science/paper/GHMZOTF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1407.4610&json=true","fetch_graph":"https://pith.science/api/pith-number/GHMZOTF7LCBVQVVHNBS3GLH2XY/graph.json","fetch_events":"https://pith.science/api/pith-number/GHMZOTF7LCBVQVVHNBS3GLH2XY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY/action/storage_attestation","attest_author":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY/action/author_attestation","sign_citation":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY/action/citation_signature","submit_replication":"https://pith.science/pith/GHMZOTF7LCBVQVVHNBS3GLH2XY/action/replication_record"}},"created_at":"2026-05-18T02:02:08.350569+00:00","updated_at":"2026-05-18T02:02:08.350569+00:00"}