{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FUGL72BFYNEOJLSB5IYXYPSI5W","short_pith_number":"pith:FUGL72BF","schema_version":"1.0","canonical_sha256":"2d0cbfe825c348e4ae41ea317c3e48ed8aa7f986c6f25de46755732e58849281","source":{"kind":"arxiv","id":"1801.04063","version":1},"attestation_state":"computed","paper":{"title":"How Many Samples Required in Big Data Collection: A Differential Message Importance Measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","math.ST","stat.TH"],"primary_cat":"cs.IT","authors_text":"Pingyi Fan, Rui She, Shanyun Liu","submitted_at":"2018-01-12T05:57:11Z","abstract_excerpt":"Information collection is a fundamental problem in big data, where the size of sampling sets plays a very important role. This work considers the information collection process by taking message importance into account. Similar to differential entropy, we define differential message importance measure (DMIM) as a measure of message importance for continuous random variable. It is proved that the change of DMIM can describe the gap between the distribution of a set of sample values and a theoretical distribution. In fact, the deviation of DMIM is equivalent to Kolmogorov-Smirnov statistic, but "},"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":"1801.04063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-12T05:57:11Z","cross_cats_sorted":["math.IT","math.ST","stat.TH"],"title_canon_sha256":"de229df46c706e219d39ef46de46c739c603ba810e3ac33cab30ec9ddc9caee5","abstract_canon_sha256":"5a5331803b55a712bd63873a45a432f7d6a6c3c746d71aa54c2860f9e2428dde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:12.001426Z","signature_b64":"UBkhm6pgxoe2VrEtGDMtqEaEYzg9/EVE6Vq8qObv0G7TM0Zyes+1bYYOJhgogQb4sd5tu5YonNwc+0OKxSF0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d0cbfe825c348e4ae41ea317c3e48ed8aa7f986c6f25de46755732e58849281","last_reissued_at":"2026-05-18T00:26:12.000799Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:12.000799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Many Samples Required in Big Data Collection: A Differential Message Importance Measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","math.ST","stat.TH"],"primary_cat":"cs.IT","authors_text":"Pingyi Fan, Rui She, Shanyun Liu","submitted_at":"2018-01-12T05:57:11Z","abstract_excerpt":"Information collection is a fundamental problem in big data, where the size of sampling sets plays a very important role. This work considers the information collection process by taking message importance into account. Similar to differential entropy, we define differential message importance measure (DMIM) as a measure of message importance for continuous random variable. It is proved that the change of DMIM can describe the gap between the distribution of a set of sample values and a theoretical distribution. In fact, the deviation of DMIM is equivalent to Kolmogorov-Smirnov statistic, but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04063","kind":"arxiv","version":1},"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":"1801.04063","created_at":"2026-05-18T00:26:12.000903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.04063v1","created_at":"2026-05-18T00:26:12.000903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04063","created_at":"2026-05-18T00:26:12.000903+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUGL72BFYNEO","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUGL72BFYNEOJLSB","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUGL72BF","created_at":"2026-05-18T12:32:25.280505+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/FUGL72BFYNEOJLSB5IYXYPSI5W","json":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W.json","graph_json":"https://pith.science/api/pith-number/FUGL72BFYNEOJLSB5IYXYPSI5W/graph.json","events_json":"https://pith.science/api/pith-number/FUGL72BFYNEOJLSB5IYXYPSI5W/events.json","paper":"https://pith.science/paper/FUGL72BF"},"agent_actions":{"view_html":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W","download_json":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W.json","view_paper":"https://pith.science/paper/FUGL72BF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.04063&json=true","fetch_graph":"https://pith.science/api/pith-number/FUGL72BFYNEOJLSB5IYXYPSI5W/graph.json","fetch_events":"https://pith.science/api/pith-number/FUGL72BFYNEOJLSB5IYXYPSI5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/action/storage_attestation","attest_author":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/action/author_attestation","sign_citation":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/action/citation_signature","submit_replication":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/action/replication_record"}},"created_at":"2026-05-18T00:26:12.000903+00:00","updated_at":"2026-05-18T00:26:12.000903+00:00"}