{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RSF5QHKZIACFVNYF5CMXF4FMZK","short_pith_number":"pith:RSF5QHKZ","canonical_record":{"source":{"id":"1510.00277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2015-10-01T15:10:09Z","cross_cats_sorted":["cs.CL","physics.data-an"],"title_canon_sha256":"318dd2a8cfcc8a690c0280f78eede3ea83c8506dc042dacee8e9828d67f9a85e","abstract_canon_sha256":"bc25742590587fc1c636b33717da6634e0e0f396a2c765c4a0dd389cda0a1b1b"},"schema_version":"1.0"},"canonical_sha256":"8c8bd81d5940045ab705e89972f0acca96387f4ea67d7a011b3bf7ee11111363","source":{"kind":"arxiv","id":"1510.00277","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.00277","created_at":"2026-05-18T01:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"1510.00277v2","created_at":"2026-05-18T01:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.00277","created_at":"2026-05-18T01:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"RSF5QHKZIACF","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RSF5QHKZIACFVNYF","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RSF5QHKZ","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RSF5QHKZIACFVNYF5CMXF4FMZK","target":"record","payload":{"canonical_record":{"source":{"id":"1510.00277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2015-10-01T15:10:09Z","cross_cats_sorted":["cs.CL","physics.data-an"],"title_canon_sha256":"318dd2a8cfcc8a690c0280f78eede3ea83c8506dc042dacee8e9828d67f9a85e","abstract_canon_sha256":"bc25742590587fc1c636b33717da6634e0e0f396a2c765c4a0dd389cda0a1b1b"},"schema_version":"1.0"},"canonical_sha256":"8c8bd81d5940045ab705e89972f0acca96387f4ea67d7a011b3bf7ee11111363","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:05.062146Z","signature_b64":"FpyulHGYQJ5E9V8UUZ2w3z4X8nGbfRoC7+T3Hg9foEjZVtCcpW8ZhVG4mpjtwDxMjecmhAT4H3zkAdllcuqUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8bd81d5940045ab705e89972f0acca96387f4ea67d7a011b3bf7ee11111363","last_reissued_at":"2026-05-18T01:17:05.061411Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:05.061411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1510.00277","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M79ByLz9makKdWu5hwcx5YQgsq5VKZoAWR+kj6V5jfFX8MxtxPo6D/Hw1a9EBdezTdOgXzkVSXow6ZtcLr1kBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:40:17.564911Z"},"content_sha256":"3f4128f56b602a76eb4c6e0af143fa563376aa149b2a1b8bc056023315236357","schema_version":"1.0","event_id":"sha256:3f4128f56b602a76eb4c6e0af143fa563376aa149b2a1b8bc056023315236357"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RSF5QHKZIACFVNYF5CMXF4FMZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Similarity of symbol frequency distributions with heavy tails","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","physics.data-an"],"primary_cat":"physics.soc-ph","authors_text":"Eduardo G. Altmann, Francesc Font-Clos, Martin Gerlach","submitted_at":"2015-10-01T15:10:09Z","abstract_excerpt":"Quantifying the similarity between symbolic sequences is a traditional problem in Information Theory which requires comparing the frequencies of symbols in different sequences. In numerous modern applications, ranging from DNA over music to texts, the distribution of symbol frequencies is characterized by heavy-tailed distributions (e.g., Zipf's law). The large number of low-frequency symbols in these distributions poses major difficulties to the estimation of the similarity between sequences, e.g., they hinder an accurate finite-size estimation of entropies. Here we show analytically how the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.00277","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPW9cgxycBQiy0fkIbwigNxXuK80TWfrMslwX3rO8/Bfw+bJEZn3mhYFQ1hEf1ScoBdBWYelDCk0ksM9Qt5RBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:40:17.565254Z"},"content_sha256":"28c0767bf3d6d38dd64a760031378da97283cfa757b47f04be1a8bf0e41dba53","schema_version":"1.0","event_id":"sha256:28c0767bf3d6d38dd64a760031378da97283cfa757b47f04be1a8bf0e41dba53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSF5QHKZIACFVNYF5CMXF4FMZK/bundle.json","state_url":"https://pith.science/pith/RSF5QHKZIACFVNYF5CMXF4FMZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSF5QHKZIACFVNYF5CMXF4FMZK/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":"2026-06-01T22:40:17Z","links":{"resolver":"https://pith.science/pith/RSF5QHKZIACFVNYF5CMXF4FMZK","bundle":"https://pith.science/pith/RSF5QHKZIACFVNYF5CMXF4FMZK/bundle.json","state":"https://pith.science/pith/RSF5QHKZIACFVNYF5CMXF4FMZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSF5QHKZIACFVNYF5CMXF4FMZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RSF5QHKZIACFVNYF5CMXF4FMZK","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":"bc25742590587fc1c636b33717da6634e0e0f396a2c765c4a0dd389cda0a1b1b","cross_cats_sorted":["cs.CL","physics.data-an"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2015-10-01T15:10:09Z","title_canon_sha256":"318dd2a8cfcc8a690c0280f78eede3ea83c8506dc042dacee8e9828d67f9a85e"},"schema_version":"1.0","source":{"id":"1510.00277","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.00277","created_at":"2026-05-18T01:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"1510.00277v2","created_at":"2026-05-18T01:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.00277","created_at":"2026-05-18T01:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"RSF5QHKZIACF","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RSF5QHKZIACFVNYF","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RSF5QHKZ","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:28c0767bf3d6d38dd64a760031378da97283cfa757b47f04be1a8bf0e41dba53","target":"graph","created_at":"2026-05-18T01:17:05Z","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":"Quantifying the similarity between symbolic sequences is a traditional problem in Information Theory which requires comparing the frequencies of symbols in different sequences. In numerous modern applications, ranging from DNA over music to texts, the distribution of symbol frequencies is characterized by heavy-tailed distributions (e.g., Zipf's law). The large number of low-frequency symbols in these distributions poses major difficulties to the estimation of the similarity between sequences, e.g., they hinder an accurate finite-size estimation of entropies. Here we show analytically how the ","authors_text":"Eduardo G. Altmann, Francesc Font-Clos, Martin Gerlach","cross_cats":["cs.CL","physics.data-an"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2015-10-01T15:10:09Z","title":"Similarity of symbol frequency distributions with heavy tails"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.00277","kind":"arxiv","version":2},"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":"sha256:3f4128f56b602a76eb4c6e0af143fa563376aa149b2a1b8bc056023315236357","target":"record","created_at":"2026-05-18T01:17:05Z","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":"bc25742590587fc1c636b33717da6634e0e0f396a2c765c4a0dd389cda0a1b1b","cross_cats_sorted":["cs.CL","physics.data-an"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2015-10-01T15:10:09Z","title_canon_sha256":"318dd2a8cfcc8a690c0280f78eede3ea83c8506dc042dacee8e9828d67f9a85e"},"schema_version":"1.0","source":{"id":"1510.00277","kind":"arxiv","version":2}},"canonical_sha256":"8c8bd81d5940045ab705e89972f0acca96387f4ea67d7a011b3bf7ee11111363","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c8bd81d5940045ab705e89972f0acca96387f4ea67d7a011b3bf7ee11111363","first_computed_at":"2026-05-18T01:17:05.061411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:05.061411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FpyulHGYQJ5E9V8UUZ2w3z4X8nGbfRoC7+T3Hg9foEjZVtCcpW8ZhVG4mpjtwDxMjecmhAT4H3zkAdllcuqUAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:05.062146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.00277","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f4128f56b602a76eb4c6e0af143fa563376aa149b2a1b8bc056023315236357","sha256:28c0767bf3d6d38dd64a760031378da97283cfa757b47f04be1a8bf0e41dba53"],"state_sha256":"919a1740f97da64898a01ccbaf94b2bc5fcf7674b668ed7e79fde984a1e4321a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yobiv0vLNMUKWw74Ajs81ecZjIuuS5g2UVjs/VR6nhu/SLcWltGxnfGTLwV6f/FutqwIRUM8sRhS5x0eDVavCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T22:40:17.567387Z","bundle_sha256":"c8437bb10d13902e62d0d6f8108439d81deb1040e259c6a6bc967a34016c1104"}}