{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RB7KGYJKYP5AV36PXNWWCPWNSW","short_pith_number":"pith:RB7KGYJK","canonical_record":{"source":{"id":"2411.10227","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:40:59Z","cross_cats_sorted":["cs.IR","physics.soc-ph"],"title_canon_sha256":"699bf52c73df5ade281aafb1885a9b4efafd64954cb17d1513a5412fddf4aaa7","abstract_canon_sha256":"5d184811c33a6318660fb46137089343bc7637bd50594dc3edfeb110d74be558"},"schema_version":"1.0"},"canonical_sha256":"887ea3612ac3fa0aefcfbb6d613ecd9584017ddb6c39e90a60ce016dc9abc343","source":{"kind":"arxiv","id":"2411.10227","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10227","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10227v3","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10227","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"pith_short_12","alias_value":"RB7KGYJKYP5A","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"pith_short_16","alias_value":"RB7KGYJKYP5AV36P","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"pith_short_8","alias_value":"RB7KGYJK","created_at":"2026-07-05T11:37:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RB7KGYJKYP5AV36PXNWWCPWNSW","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10227","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:40:59Z","cross_cats_sorted":["cs.IR","physics.soc-ph"],"title_canon_sha256":"699bf52c73df5ade281aafb1885a9b4efafd64954cb17d1513a5412fddf4aaa7","abstract_canon_sha256":"5d184811c33a6318660fb46137089343bc7637bd50594dc3edfeb110d74be558"},"schema_version":"1.0"},"canonical_sha256":"887ea3612ac3fa0aefcfbb6d613ecd9584017ddb6c39e90a60ce016dc9abc343","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:12.170099Z","signature_b64":"tcB8Yf6cxbkBAK0AV7vL8p9H6e33KNFD21+XbwJGsGopKyM40+Ez8rAlGahBSGTmAx4WepejcN6Rr84XOm43DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"887ea3612ac3fa0aefcfbb6d613ecd9584017ddb6c39e90a60ce016dc9abc343","last_reissued_at":"2026-07-05T11:37:12.169678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:12.169678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10227","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:37:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"96MEXKhp/cWxKVvYZUrxvMLXJOvBFtZgL0O/qs+hGuybGF4w62LGgHMZGfhahE9arPJhysHKXvjkkmnZvEsZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:59:04.932209Z"},"content_sha256":"5e784ad47a1fe82abca5615f290bb0c4dfcf6d3304fedf155759a2b8fb2f61b8","schema_version":"1.0","event_id":"sha256:5e784ad47a1fe82abca5615f290bb0c4dfcf6d3304fedf155759a2b8fb2f61b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RB7KGYJKYP5AV36PXNWWCPWNSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy and type-token ratio in gigaword corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","physics.soc-ph"],"primary_cat":"cs.CL","authors_text":"David Sanchez, Maxi San Miguel, Pablo Rosillo-Rodes","submitted_at":"2024-11-15T14:40:59Z","abstract_excerpt":"There are different ways of measuring diversity in complex systems. In particular, in language, lexical diversity is characterized in terms of the type-token ratio and the word entropy. We here investigate both diversity metrics in six massive linguistic datasets in English, Spanish, and Turkish, consisting of books, news articles, and tweets. These gigaword corpora correspond to languages with distinct morphological features and differ in registers and genres, thus constituting a varied testbed for a quantitative approach to lexical diversity. We unveil an empirical functional relation betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10227","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.10227/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:37:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V4k5uiArbMSV/DtOwF7I0eaJjpTAGLxsEw2HiKcxbX+gm7o2Iw98K2wMWX5j69gxtSF269zm1pMCdk18sxQiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:59:04.932798Z"},"content_sha256":"35c1fbeb76d2cf1c74c3fa15d89ee18420563565b0bdff94a3e9a90c9c7d5a03","schema_version":"1.0","event_id":"sha256:35c1fbeb76d2cf1c74c3fa15d89ee18420563565b0bdff94a3e9a90c9c7d5a03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RB7KGYJKYP5AV36PXNWWCPWNSW/bundle.json","state_url":"https://pith.science/pith/RB7KGYJKYP5AV36PXNWWCPWNSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RB7KGYJKYP5AV36PXNWWCPWNSW/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":"2026-08-04T11:59:04Z","links":{"resolver":"https://pith.science/pith/RB7KGYJKYP5AV36PXNWWCPWNSW","bundle":"https://pith.science/pith/RB7KGYJKYP5AV36PXNWWCPWNSW/bundle.json","state":"https://pith.science/pith/RB7KGYJKYP5AV36PXNWWCPWNSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RB7KGYJKYP5AV36PXNWWCPWNSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RB7KGYJKYP5AV36PXNWWCPWNSW","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":"5d184811c33a6318660fb46137089343bc7637bd50594dc3edfeb110d74be558","cross_cats_sorted":["cs.IR","physics.soc-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:40:59Z","title_canon_sha256":"699bf52c73df5ade281aafb1885a9b4efafd64954cb17d1513a5412fddf4aaa7"},"schema_version":"1.0","source":{"id":"2411.10227","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10227","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10227v3","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10227","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"pith_short_12","alias_value":"RB7KGYJKYP5A","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"pith_short_16","alias_value":"RB7KGYJKYP5AV36P","created_at":"2026-07-05T11:37:12Z"},{"alias_kind":"pith_short_8","alias_value":"RB7KGYJK","created_at":"2026-07-05T11:37:12Z"}],"graph_snapshots":[{"event_id":"sha256:35c1fbeb76d2cf1c74c3fa15d89ee18420563565b0bdff94a3e9a90c9c7d5a03","target":"graph","created_at":"2026-07-05T11:37:12Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.10227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are different ways of measuring diversity in complex systems. In particular, in language, lexical diversity is characterized in terms of the type-token ratio and the word entropy. We here investigate both diversity metrics in six massive linguistic datasets in English, Spanish, and Turkish, consisting of books, news articles, and tweets. These gigaword corpora correspond to languages with distinct morphological features and differ in registers and genres, thus constituting a varied testbed for a quantitative approach to lexical diversity. We unveil an empirical functional relation betwee","authors_text":"David Sanchez, Maxi San Miguel, Pablo Rosillo-Rodes","cross_cats":["cs.IR","physics.soc-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:40:59Z","title":"Entropy and type-token ratio in gigaword corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10227","kind":"arxiv","version":3},"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":"sha256:5e784ad47a1fe82abca5615f290bb0c4dfcf6d3304fedf155759a2b8fb2f61b8","target":"record","created_at":"2026-07-05T11:37:12Z","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":"5d184811c33a6318660fb46137089343bc7637bd50594dc3edfeb110d74be558","cross_cats_sorted":["cs.IR","physics.soc-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:40:59Z","title_canon_sha256":"699bf52c73df5ade281aafb1885a9b4efafd64954cb17d1513a5412fddf4aaa7"},"schema_version":"1.0","source":{"id":"2411.10227","kind":"arxiv","version":3}},"canonical_sha256":"887ea3612ac3fa0aefcfbb6d613ecd9584017ddb6c39e90a60ce016dc9abc343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"887ea3612ac3fa0aefcfbb6d613ecd9584017ddb6c39e90a60ce016dc9abc343","first_computed_at":"2026-07-05T11:37:12.169678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:12.169678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tcB8Yf6cxbkBAK0AV7vL8p9H6e33KNFD21+XbwJGsGopKyM40+Ez8rAlGahBSGTmAx4WepejcN6Rr84XOm43DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:12.170099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10227","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e784ad47a1fe82abca5615f290bb0c4dfcf6d3304fedf155759a2b8fb2f61b8","sha256:35c1fbeb76d2cf1c74c3fa15d89ee18420563565b0bdff94a3e9a90c9c7d5a03"],"state_sha256":"261c6f2258af4dd18f183574b70fa732d03b31daba9733e408314419fd683355"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuwsF7hzFl0ooSM8ZrOuRpwgPN6BwwEfbf16WdaaadgSHShksZ+huXWYXt5VZ2w+f9iiQDVmxa4mRAnodsX6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:59:04.948178Z","bundle_sha256":"035dd22b9eb1b584753da66cf467ad9df9009fd941895f0c59434a80062c8862"}}