{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N7SFIPCTXDMV6XTBEW32ULTGHS","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":"2b94e8bf90177a4c36a7a7277cafe22b31e774cd5dbfd25c4360f1d5bf1ce316","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T07:33:55Z","title_canon_sha256":"b9b6b66334f5e0fb9ee5b7be41c9f44f0990bdba67672f58b12eab7dbb4b6aec"},"schema_version":"1.0","source":{"id":"2607.19848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19848","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19848v1","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19848","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"N7SFIPCTXDMV","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"N7SFIPCTXDMV6XTB","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"N7SFIPCT","created_at":"2026-07-23T01:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:3e362f6719bf0c835f943091ea041ecac65d53615b5bb07cf24b1f952266622a","target":"graph","created_at":"2026-07-23T01:24:03Z","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/2607.19848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is growing evidence that data diversity is crucial for developing fair and robust NLP models. However, current approaches to measure diversity remain inconsistent and fragmented: While there exist a number of tools for measuring the lexical diversity of texts, researchers lack standardized tools for quantifying diversity based on embeddings. Embedding-based diversity measures are highly flexible: They work with any embedding model and any data that can be embedded, and are thus applicable to many notions of diversity. With emb-diversity, we provide a comprehensive embedding-based diversi","authors_text":"Anna Wegmann, Cantao Su, Dong Nguyen, Esther Ploeger, Menan Velayuthan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T07:33:55Z","title":"emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19848","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:bee184a96b5c94e10cd1307c9bc64acc04b4f85ded44968386343abe456d2c6c","target":"record","created_at":"2026-07-23T01:24:03Z","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":"2b94e8bf90177a4c36a7a7277cafe22b31e774cd5dbfd25c4360f1d5bf1ce316","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T07:33:55Z","title_canon_sha256":"b9b6b66334f5e0fb9ee5b7be41c9f44f0990bdba67672f58b12eab7dbb4b6aec"},"schema_version":"1.0","source":{"id":"2607.19848","kind":"arxiv","version":1}},"canonical_sha256":"6fe4543c53b8d95f5e6125b7aa2e663cbf68e737bd8d73f1dc9cbb776ff897a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fe4543c53b8d95f5e6125b7aa2e663cbf68e737bd8d73f1dc9cbb776ff897a0","first_computed_at":"2026-07-23T01:24:03.511765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:03.511765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cz0uXr+QWtGW4YAjDfiUDKHhRJ+VPQ2ZPtg6JCLatyn6iIigySJatPd2KtROdyKRDXzuvKNGs0a6QqXha/MICQ==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:03.512865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bee184a96b5c94e10cd1307c9bc64acc04b4f85ded44968386343abe456d2c6c","sha256:3e362f6719bf0c835f943091ea041ecac65d53615b5bb07cf24b1f952266622a"],"state_sha256":"38feb1f53c332f42ea683f343a1ed3ed97448047b96e5c2da42ef260cb307ffc"}