{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2EOUK7ZEFYGA4QNKROX3LHQFOH","short_pith_number":"pith:2EOUK7ZE","canonical_record":{"source":{"id":"1805.08929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-23T01:44:29Z","cross_cats_sorted":["math.IT","math.ST","physics.data-an","stat.TH"],"title_canon_sha256":"fd5e95fc658fbafd9e4fbfebd4b0fe65a041cd2e2d92e7b23b44f61f7ef9007a","abstract_canon_sha256":"eacd1eefc3dc413cdd04460c917fb032423c04ec675d3dad23250cb8c751fe3b"},"schema_version":"1.0"},"canonical_sha256":"d11d457f242e0c0e41aa8bafb59e0571c6751d2cda6a72e091417c6bb234ef5d","source":{"kind":"arxiv","id":"1805.08929","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08929","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08929v1","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08929","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"2EOUK7ZEFYGA","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2EOUK7ZEFYGA4QNK","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2EOUK7ZE","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2EOUK7ZEFYGA4QNKROX3LHQFOH","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-23T01:44:29Z","cross_cats_sorted":["math.IT","math.ST","physics.data-an","stat.TH"],"title_canon_sha256":"fd5e95fc658fbafd9e4fbfebd4b0fe65a041cd2e2d92e7b23b44f61f7ef9007a","abstract_canon_sha256":"eacd1eefc3dc413cdd04460c917fb032423c04ec675d3dad23250cb8c751fe3b"},"schema_version":"1.0"},"canonical_sha256":"d11d457f242e0c0e41aa8bafb59e0571c6751d2cda6a72e091417c6bb234ef5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.065479Z","signature_b64":"3Y6ypL4OIrWKwpXKTgGHWlZF1Aw5e90v2MhzHKhXsXlDYNYxOPrcC+zyTApLhSjTcR8JMsTqBOdLoCSL6y++Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d11d457f242e0c0e41aa8bafb59e0571c6751d2cda6a72e091417c6bb234ef5d","last_reissued_at":"2026-05-18T00:15:09.065007Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.065007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08929","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":"2026-05-18T00:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqAVpNQQnyHMlisI+ny+yJuTnXNsF8ELXDZ1muJnPiR7ziA7kPALFHfUlq5md/m6SF7JBtT7SnXhIJKjIOqKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:00:39.442515Z"},"content_sha256":"e90d5138a9be21b47fdb246f67f3c31795aa4fc27a924a3b2bbd07012f0aacae","schema_version":"1.0","event_id":"sha256:e90d5138a9be21b47fdb246f67f3c31795aa4fc27a924a3b2bbd07012f0aacae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2EOUK7ZEFYGA4QNKROX3LHQFOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Determining the Number of Samples Required to Estimate Entropy in Natural Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","math.ST","physics.data-an","stat.TH"],"primary_cat":"cs.IT","authors_text":"Andrew D. Back, Daniel Angus, Janet Wiles","submitted_at":"2018-05-23T01:44:29Z","abstract_excerpt":"Calculating the Shannon entropy for symbolic sequences has been widely considered in many fields. For descriptive statistical problems such as estimating the N-gram entropy of English language text, a common approach is to use as much data as possible to obtain progressively more accurate estimates. However in some instances, only short sequences may be available. This gives rise to the question of how many samples are needed to compute entropy. In this paper, we examine this problem and propose a method for estimating the number of samples required to compute Shannon entropy for a set of rank"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08929","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":"2026-05-18T00:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V1XH2eyjqH3ws5OHv0tk9kevnJV7fmM8DlfQt0dg0H1fxUEdFFdhMC5qMNmiCz0aBnpX6hwIFBDBkXC+DMwzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:00:39.442870Z"},"content_sha256":"e627bee923cd979909f992c017cc81a7a2cc4f8d40862ed21760cfde08b88edb","schema_version":"1.0","event_id":"sha256:e627bee923cd979909f992c017cc81a7a2cc4f8d40862ed21760cfde08b88edb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH/bundle.json","state_url":"https://pith.science/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH/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":"2026-05-28T15:00:39Z","links":{"resolver":"https://pith.science/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH","bundle":"https://pith.science/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH/bundle.json","state":"https://pith.science/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2EOUK7ZEFYGA4QNKROX3LHQFOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2EOUK7ZEFYGA4QNKROX3LHQFOH","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":"eacd1eefc3dc413cdd04460c917fb032423c04ec675d3dad23250cb8c751fe3b","cross_cats_sorted":["math.IT","math.ST","physics.data-an","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-23T01:44:29Z","title_canon_sha256":"fd5e95fc658fbafd9e4fbfebd4b0fe65a041cd2e2d92e7b23b44f61f7ef9007a"},"schema_version":"1.0","source":{"id":"1805.08929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08929","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08929v1","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08929","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"2EOUK7ZEFYGA","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2EOUK7ZEFYGA4QNK","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2EOUK7ZE","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:e627bee923cd979909f992c017cc81a7a2cc4f8d40862ed21760cfde08b88edb","target":"graph","created_at":"2026-05-18T00:15:09Z","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":"Calculating the Shannon entropy for symbolic sequences has been widely considered in many fields. For descriptive statistical problems such as estimating the N-gram entropy of English language text, a common approach is to use as much data as possible to obtain progressively more accurate estimates. However in some instances, only short sequences may be available. This gives rise to the question of how many samples are needed to compute entropy. In this paper, we examine this problem and propose a method for estimating the number of samples required to compute Shannon entropy for a set of rank","authors_text":"Andrew D. Back, Daniel Angus, Janet Wiles","cross_cats":["math.IT","math.ST","physics.data-an","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-23T01:44:29Z","title":"Determining the Number of Samples Required to Estimate Entropy in Natural Sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08929","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:e90d5138a9be21b47fdb246f67f3c31795aa4fc27a924a3b2bbd07012f0aacae","target":"record","created_at":"2026-05-18T00:15:09Z","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":"eacd1eefc3dc413cdd04460c917fb032423c04ec675d3dad23250cb8c751fe3b","cross_cats_sorted":["math.IT","math.ST","physics.data-an","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-23T01:44:29Z","title_canon_sha256":"fd5e95fc658fbafd9e4fbfebd4b0fe65a041cd2e2d92e7b23b44f61f7ef9007a"},"schema_version":"1.0","source":{"id":"1805.08929","kind":"arxiv","version":1}},"canonical_sha256":"d11d457f242e0c0e41aa8bafb59e0571c6751d2cda6a72e091417c6bb234ef5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d11d457f242e0c0e41aa8bafb59e0571c6751d2cda6a72e091417c6bb234ef5d","first_computed_at":"2026-05-18T00:15:09.065007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:09.065007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Y6ypL4OIrWKwpXKTgGHWlZF1Aw5e90v2MhzHKhXsXlDYNYxOPrcC+zyTApLhSjTcR8JMsTqBOdLoCSL6y++Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:09.065479Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e90d5138a9be21b47fdb246f67f3c31795aa4fc27a924a3b2bbd07012f0aacae","sha256:e627bee923cd979909f992c017cc81a7a2cc4f8d40862ed21760cfde08b88edb"],"state_sha256":"bef12d5e92255df7364fb095ec75af1577b6215127a7027f3bd2b7bc65a6dd31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3DWIfAQNE6f+BxGsY/5ak0YoljS0I2kUG9i7M/yTUoKtacW8nFjmI44oosUbA6qNwzz7G7ATGdFxe6PdjchDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:00:39.444795Z","bundle_sha256":"766015e4f8feb2d34e126fdbc5f2225e88df0ac067f0040d37bc21e3868904e4"}}