{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LDXATYL3UVLJOC6PAZ2KQWBY7K","short_pith_number":"pith:LDXATYL3","canonical_record":{"source":{"id":"1801.07083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-22T13:38:29Z","cross_cats_sorted":["cs.NA","math.IT","math.PR","math.ST","stat.TH"],"title_canon_sha256":"90a6a08c4a3f24897ddc6832c96bd4e604304423f1f55f9468d4ff57f9dc3df2","abstract_canon_sha256":"b63bdf5569adfb465aa49bfa19cf186ef39f12e1afc73ddf45dd842d46413296"},"schema_version":"1.0"},"canonical_sha256":"58ee09e17ba556970bcf0674a85838fab096616e92f1a802c0e079123a8f7dab","source":{"kind":"arxiv","id":"1801.07083","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07083","created_at":"2026-05-18T00:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07083v1","created_at":"2026-05-18T00:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07083","created_at":"2026-05-18T00:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"LDXATYL3UVLJ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LDXATYL3UVLJOC6P","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LDXATYL3","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LDXATYL3UVLJOC6PAZ2KQWBY7K","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-22T13:38:29Z","cross_cats_sorted":["cs.NA","math.IT","math.PR","math.ST","stat.TH"],"title_canon_sha256":"90a6a08c4a3f24897ddc6832c96bd4e604304423f1f55f9468d4ff57f9dc3df2","abstract_canon_sha256":"b63bdf5569adfb465aa49bfa19cf186ef39f12e1afc73ddf45dd842d46413296"},"schema_version":"1.0"},"canonical_sha256":"58ee09e17ba556970bcf0674a85838fab096616e92f1a802c0e079123a8f7dab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:22.320461Z","signature_b64":"DN8Nh50PkBshddYXLCRSPanEBIuV7iDeyeQqVogfN02EOWMeBAm/juPk3JkNwxnaSG7P49WjC1kTt+UApgsGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ee09e17ba556970bcf0674a85838fab096616e92f1a802c0e079123a8f7dab","last_reissued_at":"2026-05-18T00:25:22.319958Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:22.319958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07083","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":"2026-05-18T00:25:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5SKvde2FjiUWd3uyVJ8AcADtHngh0nRRNypZBI3Jf8h4/m+QLbsZE/yIEqbDZjHA2+sZlMMoRH9+YJ7Vj2AbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T06:55:31.878968Z"},"content_sha256":"156f252922a113cb6c4b6d89d47030a6cbe76f05b5dbf670134202973cc9f703","schema_version":"1.0","event_id":"sha256:156f252922a113cb6c4b6d89d47030a6cbe76f05b5dbf670134202973cc9f703"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LDXATYL3UVLJOC6PAZ2KQWBY7K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differential Message Importance Measure: A New Approach to the Required Sampling Number in Big Data Structure Characterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.IT","math.PR","math.ST","stat.TH"],"primary_cat":"cs.IT","authors_text":"Pingyi Fan, Rui She, Shanyun Liu","submitted_at":"2018-01-22T13:38:29Z","abstract_excerpt":"Data collection is a fundamental problem in the scenario of big data, where the size of sampling sets plays a very important role, especially in the characterization of data structure. This paper considers the information collection process by taking message importance into account, and gives a distribution-free criterion to determine how many samples are required in big data structure characterization. Similar to differential entropy, we define differential message importance measure (DMIM) as a measure of message importance for continuous random variable. The DMIM for many common densities i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07083","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":"2026-05-18T00:25:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqXXvqUv7n35pVj5E3VwEmMTNRM+IXi7orWSg1QGQpHunctyOVugQkVwlPIJIatC3UPdosfZhF8igEPFYWQfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T06:55:31.879338Z"},"content_sha256":"40ee2de58a0e701645d931a9b2bd6895e112788b799186a1a5b1dc8a9593fe79","schema_version":"1.0","event_id":"sha256:40ee2de58a0e701645d931a9b2bd6895e112788b799186a1a5b1dc8a9593fe79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K/bundle.json","state_url":"https://pith.science/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K/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":"2026-06-09T06:55:31Z","links":{"resolver":"https://pith.science/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K","bundle":"https://pith.science/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K/bundle.json","state":"https://pith.science/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDXATYL3UVLJOC6PAZ2KQWBY7K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LDXATYL3UVLJOC6PAZ2KQWBY7K","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":"b63bdf5569adfb465aa49bfa19cf186ef39f12e1afc73ddf45dd842d46413296","cross_cats_sorted":["cs.NA","math.IT","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-22T13:38:29Z","title_canon_sha256":"90a6a08c4a3f24897ddc6832c96bd4e604304423f1f55f9468d4ff57f9dc3df2"},"schema_version":"1.0","source":{"id":"1801.07083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07083","created_at":"2026-05-18T00:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07083v1","created_at":"2026-05-18T00:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07083","created_at":"2026-05-18T00:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"LDXATYL3UVLJ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LDXATYL3UVLJOC6P","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LDXATYL3","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:40ee2de58a0e701645d931a9b2bd6895e112788b799186a1a5b1dc8a9593fe79","target":"graph","created_at":"2026-05-18T00:25:22Z","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":"Data collection is a fundamental problem in the scenario of big data, where the size of sampling sets plays a very important role, especially in the characterization of data structure. This paper considers the information collection process by taking message importance into account, and gives a distribution-free criterion to determine how many samples are required in big data structure characterization. Similar to differential entropy, we define differential message importance measure (DMIM) as a measure of message importance for continuous random variable. The DMIM for many common densities i","authors_text":"Pingyi Fan, Rui She, Shanyun Liu","cross_cats":["cs.NA","math.IT","math.PR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-22T13:38:29Z","title":"Differential Message Importance Measure: A New Approach to the Required Sampling Number in Big Data Structure Characterization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07083","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":"sha256:156f252922a113cb6c4b6d89d47030a6cbe76f05b5dbf670134202973cc9f703","target":"record","created_at":"2026-05-18T00:25:22Z","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":"b63bdf5569adfb465aa49bfa19cf186ef39f12e1afc73ddf45dd842d46413296","cross_cats_sorted":["cs.NA","math.IT","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-01-22T13:38:29Z","title_canon_sha256":"90a6a08c4a3f24897ddc6832c96bd4e604304423f1f55f9468d4ff57f9dc3df2"},"schema_version":"1.0","source":{"id":"1801.07083","kind":"arxiv","version":1}},"canonical_sha256":"58ee09e17ba556970bcf0674a85838fab096616e92f1a802c0e079123a8f7dab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58ee09e17ba556970bcf0674a85838fab096616e92f1a802c0e079123a8f7dab","first_computed_at":"2026-05-18T00:25:22.319958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:22.319958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DN8Nh50PkBshddYXLCRSPanEBIuV7iDeyeQqVogfN02EOWMeBAm/juPk3JkNwxnaSG7P49WjC1kTt+UApgsGAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:22.320461Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:156f252922a113cb6c4b6d89d47030a6cbe76f05b5dbf670134202973cc9f703","sha256:40ee2de58a0e701645d931a9b2bd6895e112788b799186a1a5b1dc8a9593fe79"],"state_sha256":"669781deb94d45b95889c774a040873dccc5d030249e3f3496b148c3ceab91b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZEEpUaylRPgDWtkuw15KJjGTmjK9bSDt35eALCxdKnxMqap3ZZTe4CCmN+nALIb+L8naIkhyugD+aGhdd/FAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T06:55:31.881569Z","bundle_sha256":"67a5016afc9e6d1923c752b81d5871060b8fe4d3d270a887407b1a488e9a9aee"}}