{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FUGL72BFYNEOJLSB5IYXYPSI5W","short_pith_number":"pith:FUGL72BF","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"},"canonical_sha256":"2d0cbfe825c348e4ae41ea317c3e48ed8aa7f986c6f25de46755732e58849281","source":{"kind":"arxiv","id":"1801.04063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04063","created_at":"2026-05-18T00:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04063v1","created_at":"2026-05-18T00:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04063","created_at":"2026-05-18T00:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"FUGL72BFYNEO","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FUGL72BFYNEOJLSB","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FUGL72BF","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FUGL72BFYNEOJLSB5IYXYPSI5W","target":"record","payload":{"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"},"canonical_sha256":"2d0cbfe825c348e4ae41ea317c3e48ed8aa7f986c6f25de46755732e58849281","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"},"source_kind":"arxiv","source_id":"1801.04063","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qvBa57PCEOSnFLoTgqnY+wU9PLvbw8D6qDO7pypZahUTrzgcGu+oI+s3ddfLP1uNDwN4ekPa9Zy8h+lYaZaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:52:41.612915Z"},"content_sha256":"1f9e7c8587235951a66abade578a78bc472c7e02f96c906c52c426db29216429","schema_version":"1.0","event_id":"sha256:1f9e7c8587235951a66abade578a78bc472c7e02f96c906c52c426db29216429"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FUGL72BFYNEOJLSB5IYXYPSI5W","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glAHbUn7LJ7bHbRvTmqLg3C0m8B8QSUDdTObfl0ZZM8WID2l8SqeU14SBSPg4IyD5kM/qMB7yN/ODulh+PL+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:52:41.613653Z"},"content_sha256":"c5bf98a2604d28747294d61526d8dd1440f8fc3e34a2a41b4b8a9e546cc7fd53","schema_version":"1.0","event_id":"sha256:c5bf98a2604d28747294d61526d8dd1440f8fc3e34a2a41b4b8a9e546cc7fd53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/bundle.json","state_url":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/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":"2026-06-09T04:52:41Z","links":{"resolver":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W","bundle":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/bundle.json","state":"https://pith.science/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FUGL72BFYNEOJLSB5IYXYPSI5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FUGL72BFYNEOJLSB5IYXYPSI5W","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":"5a5331803b55a712bd63873a45a432f7d6a6c3c746d71aa54c2860f9e2428dde","cross_cats_sorted":["math.IT","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-12T05:57:11Z","title_canon_sha256":"de229df46c706e219d39ef46de46c739c603ba810e3ac33cab30ec9ddc9caee5"},"schema_version":"1.0","source":{"id":"1801.04063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04063","created_at":"2026-05-18T00:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04063v1","created_at":"2026-05-18T00:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04063","created_at":"2026-05-18T00:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"FUGL72BFYNEO","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FUGL72BFYNEOJLSB","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FUGL72BF","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:c5bf98a2604d28747294d61526d8dd1440f8fc3e34a2a41b4b8a9e546cc7fd53","target":"graph","created_at":"2026-05-18T00:26:12Z","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":"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 ","authors_text":"Pingyi Fan, Rui She, Shanyun Liu","cross_cats":["math.IT","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-12T05:57:11Z","title":"How Many Samples Required in Big Data Collection: A Differential Message Importance Measure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04063","kind":"arxiv","version":1},"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":"sha256:1f9e7c8587235951a66abade578a78bc472c7e02f96c906c52c426db29216429","target":"record","created_at":"2026-05-18T00:26:12Z","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":"5a5331803b55a712bd63873a45a432f7d6a6c3c746d71aa54c2860f9e2428dde","cross_cats_sorted":["math.IT","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-12T05:57:11Z","title_canon_sha256":"de229df46c706e219d39ef46de46c739c603ba810e3ac33cab30ec9ddc9caee5"},"schema_version":"1.0","source":{"id":"1801.04063","kind":"arxiv","version":1}},"canonical_sha256":"2d0cbfe825c348e4ae41ea317c3e48ed8aa7f986c6f25de46755732e58849281","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d0cbfe825c348e4ae41ea317c3e48ed8aa7f986c6f25de46755732e58849281","first_computed_at":"2026-05-18T00:26:12.000799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:12.000799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UBkhm6pgxoe2VrEtGDMtqEaEYzg9/EVE6Vq8qObv0G7TM0Zyes+1bYYOJhgogQb4sd5tu5YonNwc+0OKxSF0Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:12.001426Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.04063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f9e7c8587235951a66abade578a78bc472c7e02f96c906c52c426db29216429","sha256:c5bf98a2604d28747294d61526d8dd1440f8fc3e34a2a41b4b8a9e546cc7fd53"],"state_sha256":"3aa663359c65c9dec6a6c55fb0c59f42b92458f2fc4e2b8099cb874479a25dd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xnn3eIG92ICTNfIsG2RAcFTMdPgWmduit1KrSW49SvmEZc86J1LwaDRsNi7gInShWBp6Mv1LQLXLM8ByMVY7AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T04:52:41.617297Z","bundle_sha256":"4b2a33ef9815d35470c9cbb3c6bedf95baa9f388f2e1f66a9e3bf6c959e5ed63"}}