{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:2YMCOWJO46BEDX7QTFLEY2TU3S","short_pith_number":"pith:2YMCOWJO","canonical_record":{"source":{"id":"1612.03375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-12-11T06:17:40Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"5b97ed75c1b81bcc31256789f574e03fef1f28b816c708b2c2f47965cec66e1a","abstract_canon_sha256":"65d15938bd954218e4d1b7661d5ee2ef4adcf2f8acd6d01f56c0249e913b80d3"},"schema_version":"1.0"},"canonical_sha256":"d61827592ee78241dff099564c6a74dc9e2afee0427d671ddb2ca389f1960a4c","source":{"kind":"arxiv","id":"1612.03375","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03375","created_at":"2026-05-18T00:26:08Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03375v2","created_at":"2026-05-18T00:26:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03375","created_at":"2026-05-18T00:26:08Z"},{"alias_kind":"pith_short_12","alias_value":"2YMCOWJO46BE","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"2YMCOWJO46BEDX7Q","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"2YMCOWJO","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:2YMCOWJO46BEDX7QTFLEY2TU3S","target":"record","payload":{"canonical_record":{"source":{"id":"1612.03375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-12-11T06:17:40Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"5b97ed75c1b81bcc31256789f574e03fef1f28b816c708b2c2f47965cec66e1a","abstract_canon_sha256":"65d15938bd954218e4d1b7661d5ee2ef4adcf2f8acd6d01f56c0249e913b80d3"},"schema_version":"1.0"},"canonical_sha256":"d61827592ee78241dff099564c6a74dc9e2afee0427d671ddb2ca389f1960a4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:08.483448Z","signature_b64":"JbuP+aJ7Tg08b9FxIiyIGBVvpEnUyy3BOOkooieH9vfHlX9KjwX3DlnHMfrrHO62iIDDqsdHZHrl04WH1qh2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d61827592ee78241dff099564c6a74dc9e2afee0427d671ddb2ca389f1960a4c","last_reissued_at":"2026-05-18T00:26:08.482894Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:08.482894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.03375","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKwyK7MBeVfg+kvPSqdVYbrjH8CNNDfxI+9/Fr9H0MH78h7tGobBilFjBLoUZXlF+XrALKNsyFqvtQhnAn9ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:52:43.409380Z"},"content_sha256":"22bc0f92a924cb22980b9aea6ad1c97b567e16a4109fe1078b33ea15394cf07b","schema_version":"1.0","event_id":"sha256:22bc0f92a924cb22980b9aea6ad1c97b567e16a4109fe1078b33ea15394cf07b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:2YMCOWJO46BEDX7QTFLEY2TU3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample complexity of the distinct elements problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Pengkun Yang, Yihong Wu","submitted_at":"2016-12-11T06:17:40Z","abstract_excerpt":"We consider the distinct elements problem, where the goal is to estimate the number of distinct colors in an urn containing $ k $ balls based on $n$ samples drawn with replacements. Based on discrete polynomial approximation and interpolation, we propose an estimator with additive error guarantee that achieves the optimal sample complexity within $O(\\log\\log k)$ factors, and in fact within constant factors for most cases. The estimator can be computed in $O(n)$ time for an accurate estimation. The result also applies to sampling without replacement provided the sample size is a vanishing fract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03375","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yfRaNuv0sxtfPo6cj0Ezc6f4i7bN//J8+POXnfc+4BX0xhodi689WwIlYSyqHI6DZV3DTDhw0MOQDsdN9F/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:52:43.409872Z"},"content_sha256":"72a57e8fbea5f1a3fb24ad60f3677e644630499af28af864fdcb70572d6070f3","schema_version":"1.0","event_id":"sha256:72a57e8fbea5f1a3fb24ad60f3677e644630499af28af864fdcb70572d6070f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YMCOWJO46BEDX7QTFLEY2TU3S/bundle.json","state_url":"https://pith.science/pith/2YMCOWJO46BEDX7QTFLEY2TU3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YMCOWJO46BEDX7QTFLEY2TU3S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T05:52:43Z","links":{"resolver":"https://pith.science/pith/2YMCOWJO46BEDX7QTFLEY2TU3S","bundle":"https://pith.science/pith/2YMCOWJO46BEDX7QTFLEY2TU3S/bundle.json","state":"https://pith.science/pith/2YMCOWJO46BEDX7QTFLEY2TU3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YMCOWJO46BEDX7QTFLEY2TU3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:2YMCOWJO46BEDX7QTFLEY2TU3S","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":"65d15938bd954218e4d1b7661d5ee2ef4adcf2f8acd6d01f56c0249e913b80d3","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-12-11T06:17:40Z","title_canon_sha256":"5b97ed75c1b81bcc31256789f574e03fef1f28b816c708b2c2f47965cec66e1a"},"schema_version":"1.0","source":{"id":"1612.03375","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03375","created_at":"2026-05-18T00:26:08Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03375v2","created_at":"2026-05-18T00:26:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03375","created_at":"2026-05-18T00:26:08Z"},{"alias_kind":"pith_short_12","alias_value":"2YMCOWJO46BE","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"2YMCOWJO46BEDX7Q","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"2YMCOWJO","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:72a57e8fbea5f1a3fb24ad60f3677e644630499af28af864fdcb70572d6070f3","target":"graph","created_at":"2026-05-18T00:26:08Z","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 distinct elements problem, where the goal is to estimate the number of distinct colors in an urn containing $ k $ balls based on $n$ samples drawn with replacements. Based on discrete polynomial approximation and interpolation, we propose an estimator with additive error guarantee that achieves the optimal sample complexity within $O(\\log\\log k)$ factors, and in fact within constant factors for most cases. The estimator can be computed in $O(n)$ time for an accurate estimation. The result also applies to sampling without replacement provided the sample size is a vanishing fract","authors_text":"Pengkun Yang, Yihong Wu","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-12-11T06:17:40Z","title":"Sample complexity of the distinct elements problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03375","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":"sha256:22bc0f92a924cb22980b9aea6ad1c97b567e16a4109fe1078b33ea15394cf07b","target":"record","created_at":"2026-05-18T00:26:08Z","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":"65d15938bd954218e4d1b7661d5ee2ef4adcf2f8acd6d01f56c0249e913b80d3","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-12-11T06:17:40Z","title_canon_sha256":"5b97ed75c1b81bcc31256789f574e03fef1f28b816c708b2c2f47965cec66e1a"},"schema_version":"1.0","source":{"id":"1612.03375","kind":"arxiv","version":2}},"canonical_sha256":"d61827592ee78241dff099564c6a74dc9e2afee0427d671ddb2ca389f1960a4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d61827592ee78241dff099564c6a74dc9e2afee0427d671ddb2ca389f1960a4c","first_computed_at":"2026-05-18T00:26:08.482894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:08.482894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JbuP+aJ7Tg08b9FxIiyIGBVvpEnUyy3BOOkooieH9vfHlX9KjwX3DlnHMfrrHO62iIDDqsdHZHrl04WH1qh2Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:08.483448Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.03375","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22bc0f92a924cb22980b9aea6ad1c97b567e16a4109fe1078b33ea15394cf07b","sha256:72a57e8fbea5f1a3fb24ad60f3677e644630499af28af864fdcb70572d6070f3"],"state_sha256":"07e3d0d40a5887d1e0c6a7db3dd761210015a561851320799f7d06c151f82d45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ki9iyN0LCNMEp+is4804CFKVIo14aHV2j2cpaBGCcDTXwmbeVD62T7wzj4QYztiXo0LvC/cmKV4856CTEqZ7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:52:43.412725Z","bundle_sha256":"d203fbafaae045194445ccfc710fcac591489be019115f8ac53ee96f3474a2e2"}}