{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TKP776UGPP32JP2MBCOSFQ3ZXQ","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":"9136f7a4084afddcfc208adb62acd4778d31cdc6d7468484e5dfe0c9be39bf25","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-06-26T18:29:07Z","title_canon_sha256":"342147686c430e648aa1f216d522af43474a55eee139d293f6c404a026629d62"},"schema_version":"1.0","source":{"id":"2306.14998","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14998","created_at":"2026-07-05T08:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14998v2","created_at":"2026-07-05T08:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14998","created_at":"2026-07-05T08:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"TKP776UGPP32","created_at":"2026-07-05T08:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"TKP776UGPP32JP2M","created_at":"2026-07-05T08:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"TKP776UG","created_at":"2026-07-05T08:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:77cd4c6f7641dda444f5f29454c8cd59dccf9100b78ce5c33dc4bbdf57bc1136","target":"graph","created_at":"2026-07-05T08:42:29Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.14998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider a random sample $(X_{1},\\ldots,X_{n})$ from an unknown discrete distribution $P=\\sum_{j\\geq1}p_{j}\\delta_{s_{j}}$ on a countable alphabet $\\mathbb{S}$, and let $(Y_{n,j})_{j\\geq1}$ be the empirical frequencies of distinct symbols $s_{j}$'s in the sample. We consider the problem of estimating the $r$-order missing mass, which is a discrete functional of $P$ defined as $$\\theta_{r}(P;\\mathbf{X}_{n})=\\sum_{j\\geq1}p^{r}_{j}I(Y_{n,j}=0).$$ This is generalization of the missing mass whose estimation is a classical problem in statistics, being the subject of numerous studies both in theory a","authors_text":"Stefano Favaro, Zacharie Naulet","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-06-26T18:29:07Z","title":"Optimal estimation of high-order missing masses, and the rare-type match problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14998","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":"sha256:190e26c75384122d14cb34fcc63146d90ae3d3dce72e3b2d7c804f8af66a0b4a","target":"record","created_at":"2026-07-05T08:42:29Z","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":"9136f7a4084afddcfc208adb62acd4778d31cdc6d7468484e5dfe0c9be39bf25","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-06-26T18:29:07Z","title_canon_sha256":"342147686c430e648aa1f216d522af43474a55eee139d293f6c404a026629d62"},"schema_version":"1.0","source":{"id":"2306.14998","kind":"arxiv","version":2}},"canonical_sha256":"9a9ffffa867bf7a4bf4c089d22c379bc119ca5fb680b7f7bb644b0fd6e2d9ce0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a9ffffa867bf7a4bf4c089d22c379bc119ca5fb680b7f7bb644b0fd6e2d9ce0","first_computed_at":"2026-07-05T08:42:29.565490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:29.565490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yhUb10h+5ENVo/hFWu/r1Aitle3zd4gCmxmUAoVOCWpsn3S2nuxSZmglJOro/A7HlhcvxaBJdJ0JRcWspfNTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:29.565951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14998","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:190e26c75384122d14cb34fcc63146d90ae3d3dce72e3b2d7c804f8af66a0b4a","sha256:77cd4c6f7641dda444f5f29454c8cd59dccf9100b78ce5c33dc4bbdf57bc1136"],"state_sha256":"29b14281192bf2693d575b1f0da6e4aca008e57e057d38131450e4e4c7dc5690"}