{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:RT65OWT23V7CCPJER5WNZGYF2H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2f6eb5fe7a8eb51dab4b99a63a3825d14343484004dbc2007fc88fb7f81a3a8","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2013-05-02T02:41:04Z","title_canon_sha256":"68c6743bcfbf3751fc308a459cf289b847fde92e1260278b91321e6d0160eb04"},"schema_version":"1.0","source":{"id":"1305.0328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.0328","created_at":"2026-05-18T02:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"1305.0328v2","created_at":"2026-05-18T02:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.0328","created_at":"2026-05-18T02:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"RT65OWT23V7C","created_at":"2026-05-18T12:27:59Z"},{"alias_kind":"pith_short_16","alias_value":"RT65OWT23V7CCPJE","created_at":"2026-05-18T12:27:59Z"},{"alias_kind":"pith_short_8","alias_value":"RT65OWT2","created_at":"2026-05-18T12:27:59Z"}],"graph_snapshots":[{"event_id":"sha256:bd1071eb1aa403dde4ae75a75416ffb9feadaa6232dd75ff0fad4937ab6342bf","target":"graph","created_at":"2026-05-18T02:49:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We consider the problem of estimating the number of types in a corpus using the number of types observed in a sample of tokens from that corpus. We derive exact and asymptotic distributions for the number of observed types, conditioned upon the number of tokens and the latent type distribution. We use the asymptotic distributions to derive an estimator of the latent number of types and we validate this estimator numerically.","authors_text":"Shohei Hidaka","cross_cats":["math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2013-05-02T02:41:04Z","title":"General Type Token Distribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.0328","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9d169f0d3ff2dcf682e14644ff254eb2c57aafe96333efc73ec54cd15640fe83","target":"record","created_at":"2026-05-18T02:49:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2f6eb5fe7a8eb51dab4b99a63a3825d14343484004dbc2007fc88fb7f81a3a8","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2013-05-02T02:41:04Z","title_canon_sha256":"68c6743bcfbf3751fc308a459cf289b847fde92e1260278b91321e6d0160eb04"},"schema_version":"1.0","source":{"id":"1305.0328","kind":"arxiv","version":2}},"canonical_sha256":"8cfdd75a7add7e213d248f6cdc9b05d1f6a8589907ab21bedd422037f639a08d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cfdd75a7add7e213d248f6cdc9b05d1f6a8589907ab21bedd422037f639a08d","first_computed_at":"2026-05-18T02:49:02.041789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:49:02.041789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"72e2cs43pbsyvbVImZGVHU1EISy/b8ap+0UveYrirnOfc8WwN6LOddkDm62lwCKlNAc9b9iJsKtuI0zdF3HaDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:49:02.042332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1305.0328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d169f0d3ff2dcf682e14644ff254eb2c57aafe96333efc73ec54cd15640fe83","sha256:bd1071eb1aa403dde4ae75a75416ffb9feadaa6232dd75ff0fad4937ab6342bf"],"state_sha256":"384677e3eff6d50ccaeb05158615d2bc4750279e85837eeb9440d848d84275b3"}