{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:I24FNYD2TSJ6M5Q75H2IFZBIZW","short_pith_number":"pith:I24FNYD2","schema_version":"1.0","canonical_sha256":"46b856e07a9c93e6761fe9f482e428cdab7825cb00272b1bc8e06f812edcd375","source":{"kind":"arxiv","id":"1209.0736","version":2},"attestation_state":"computed","paper":{"title":"On Set Size Distribution Estimation and the Characterization of Large Networks via Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.SI","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Bruno Ribeiro, Don Towsley, Fabricio Murai, Pinghui Wang","submitted_at":"2012-09-04T19:04:36Z","abstract_excerpt":"In this work we study the set size distribution estimation problem, where elements are randomly sampled from a collection of non-overlapping sets and we seek to recover the original set size distribution from the samples. This problem has applications to capacity planning, network theory, among other areas. Examples of real-world applications include characterizing in-degree distributions in large graphs and uncovering TCP/IP flow size distributions on the Internet. We demonstrate that it is hard to estimate the original set size distribution. The recoverability of original set size distributi"},"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":"1209.0736","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-09-04T19:04:36Z","cross_cats_sorted":["cs.IT","cs.SI","math.IT","stat.TH"],"title_canon_sha256":"8381bbd29f745f9e2c11eba2e41fa779448faf771286fba50fee50babfbcc772","abstract_canon_sha256":"1ec55cbef5ad40ff9d8460c1e266ec8e7ab0abd1fe7bcfd39a151ca517995f4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:39:28.123980Z","signature_b64":"QTIllo7pJ/2s0t+IpbkrSW1T1yxND7PCGRGiQBl/FMTVogpfe3p2Jav1bffqd6MFzUb4fJrs0bZEgz8FBNu+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46b856e07a9c93e6761fe9f482e428cdab7825cb00272b1bc8e06f812edcd375","last_reissued_at":"2026-05-18T03:39:28.123263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:39:28.123263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Set Size Distribution Estimation and the Characterization of Large Networks via Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.SI","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Bruno Ribeiro, Don Towsley, Fabricio Murai, Pinghui Wang","submitted_at":"2012-09-04T19:04:36Z","abstract_excerpt":"In this work we study the set size distribution estimation problem, where elements are randomly sampled from a collection of non-overlapping sets and we seek to recover the original set size distribution from the samples. This problem has applications to capacity planning, network theory, among other areas. Examples of real-world applications include characterizing in-degree distributions in large graphs and uncovering TCP/IP flow size distributions on the Internet. We demonstrate that it is hard to estimate the original set size distribution. The recoverability of original set size distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1209.0736","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":"1209.0736","created_at":"2026-05-18T03:39:28.123383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1209.0736v2","created_at":"2026-05-18T03:39:28.123383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1209.0736","created_at":"2026-05-18T03:39:28.123383+00:00"},{"alias_kind":"pith_short_12","alias_value":"I24FNYD2TSJ6","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_16","alias_value":"I24FNYD2TSJ6M5Q7","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_8","alias_value":"I24FNYD2","created_at":"2026-05-18T12:27:09.501522+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/I24FNYD2TSJ6M5Q75H2IFZBIZW","json":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW.json","graph_json":"https://pith.science/api/pith-number/I24FNYD2TSJ6M5Q75H2IFZBIZW/graph.json","events_json":"https://pith.science/api/pith-number/I24FNYD2TSJ6M5Q75H2IFZBIZW/events.json","paper":"https://pith.science/paper/I24FNYD2"},"agent_actions":{"view_html":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW","download_json":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW.json","view_paper":"https://pith.science/paper/I24FNYD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1209.0736&json=true","fetch_graph":"https://pith.science/api/pith-number/I24FNYD2TSJ6M5Q75H2IFZBIZW/graph.json","fetch_events":"https://pith.science/api/pith-number/I24FNYD2TSJ6M5Q75H2IFZBIZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW/action/storage_attestation","attest_author":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW/action/author_attestation","sign_citation":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW/action/citation_signature","submit_replication":"https://pith.science/pith/I24FNYD2TSJ6M5Q75H2IFZBIZW/action/replication_record"}},"created_at":"2026-05-18T03:39:28.123383+00:00","updated_at":"2026-05-18T03:39:28.123383+00:00"}