{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IEPC4P5LIN44OEVESSTJPA2SV4","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":"6e1e83963cf90a8471af8f7972b5543d779dd7a7f671c6ee65140ce83761e25e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T01:29:11Z","title_canon_sha256":"251eb757c8e5d95553bae3ccdd3036ff821baab53907e6033a019c4cc624d364"},"schema_version":"1.0","source":{"id":"2106.00877","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00877","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00877v1","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00877","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"IEPC4P5LIN44","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"IEPC4P5LIN44OEVE","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"IEPC4P5L","created_at":"2026-07-05T02:45:41Z"}],"graph_snapshots":[{"event_id":"sha256:3f6e608801ccdf2722cce6db1a53ad8d338c8f129bf40b8d7fd1edb1909d657c","target":"graph","created_at":"2026-07-05T02:45:41Z","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/2106.00877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce categorical modularity, a novel low-resource intrinsic metric to evaluate word embedding quality. Categorical modularity is a graph modularity metric based on the $k$-nearest neighbor graph constructed with embedding vectors of words from a fixed set of semantic categories, in which the goal is to measure the proportion of words that have nearest neighbors within the same categories. We use a core set of 500 words belonging to 59 neurobiologically motivated semantic categories in 29 languages and analyze three word embedding models per language (FastText, MUSE, and subs2vec). We f","authors_text":"Dami\\'an E. Blasi, Karina Halevy, S\\'ilvia Casacuberta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T01:29:11Z","title":"Evaluating Word Embeddings with Categorical Modularity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00877","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":"sha256:34f70a6d11a75e06ca38d5cd7c43f62b2ef02a1bd7077352e5d7f28b215b3621","target":"record","created_at":"2026-07-05T02:45:41Z","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":"6e1e83963cf90a8471af8f7972b5543d779dd7a7f671c6ee65140ce83761e25e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T01:29:11Z","title_canon_sha256":"251eb757c8e5d95553bae3ccdd3036ff821baab53907e6033a019c4cc624d364"},"schema_version":"1.0","source":{"id":"2106.00877","kind":"arxiv","version":1}},"canonical_sha256":"411e2e3fab4379c712a494a6978352af3ec28ada6c13067f34e697e6c078a56d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"411e2e3fab4379c712a494a6978352af3ec28ada6c13067f34e697e6c078a56d","first_computed_at":"2026-07-05T02:45:41.129615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:41.129615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"10wJRHBh3cm/Rh06sZR+OpMbz1wMbKneGqTUP/ZyfqfmnXIPACKUJYEXrm6tY9uq5QRE+vrWyisVNyc10EnACA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:41.130004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00877","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34f70a6d11a75e06ca38d5cd7c43f62b2ef02a1bd7077352e5d7f28b215b3621","sha256:3f6e608801ccdf2722cce6db1a53ad8d338c8f129bf40b8d7fd1edb1909d657c"],"state_sha256":"43aabc610023e4db21166f85c9a480a7c2fdaa3c6c3fa350825daa8c9c5cfd73"}