{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HUBOGQ3G7RJBBM33OSIXSZFCDO","short_pith_number":"pith:HUBOGQ3G","schema_version":"1.0","canonical_sha256":"3d02e34366fc5210b37b74917964a21b897ffdc90e1c59c53dc37e1cae64cdf6","source":{"kind":"arxiv","id":"2605.23821","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andres Nava, Matthieu Wyart","submitted_at":"2026-05-22T16:24:30Z","abstract_excerpt":"We propose a distributional theory of how hypernymy -- the ``is-a'' relation between general and specific concepts -- is encoded geometrically in language representations. Starting from the empirically verified assumption that words closer on the WordNet hypernym graph co-occur more often, we characterize theoretically the spectrum of the resulting embedding Gram matrix of word2vec embeddings. Under mild positivity and decay conditions on the co-occurrence kernel, we prove that the leading eigenvectors first separate broad taxonomic branches and then progressively finer sub-branches, producing"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.23821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T16:24:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0e64886d294b0fe65ab78588c1665d715193d33c024d31994191c250cc1f4bf","abstract_canon_sha256":"3dd421076734bd8ca3953f80c3955c2940f1760a5f966af739958b3c621267e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:34.147105Z","signature_b64":"e2/ormBLVG6GGvF0QXuaLH29p0Mqpl5LLEY2C9v02HCbIy6Zcz2uhlMUl6+ArkUfR2DzTEid2dcaPMrEVe3ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d02e34366fc5210b37b74917964a21b897ffdc90e1c59c53dc37e1cae64cdf6","last_reissued_at":"2026-05-25T02:02:34.146289Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:34.146289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andres Nava, Matthieu Wyart","submitted_at":"2026-05-22T16:24:30Z","abstract_excerpt":"We propose a distributional theory of how hypernymy -- the ``is-a'' relation between general and specific concepts -- is encoded geometrically in language representations. Starting from the empirically verified assumption that words closer on the WordNet hypernym graph co-occur more often, we characterize theoretically the spectrum of the resulting embedding Gram matrix of word2vec embeddings. Under mild positivity and decay conditions on the co-occurrence kernel, we prove that the leading eigenvectors first separate broad taxonomic branches and then progressively finer sub-branches, producing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23821","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.23821/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.23821","created_at":"2026-05-25T02:02:34.146428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23821v1","created_at":"2026-05-25T02:02:34.146428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23821","created_at":"2026-05-25T02:02:34.146428+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUBOGQ3G7RJB","created_at":"2026-05-25T02:02:34.146428+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUBOGQ3G7RJBBM33","created_at":"2026-05-25T02:02:34.146428+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUBOGQ3G","created_at":"2026-05-25T02:02:34.146428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO","json":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO.json","graph_json":"https://pith.science/api/pith-number/HUBOGQ3G7RJBBM33OSIXSZFCDO/graph.json","events_json":"https://pith.science/api/pith-number/HUBOGQ3G7RJBBM33OSIXSZFCDO/events.json","paper":"https://pith.science/paper/HUBOGQ3G"},"agent_actions":{"view_html":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO","download_json":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO.json","view_paper":"https://pith.science/paper/HUBOGQ3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23821&json=true","fetch_graph":"https://pith.science/api/pith-number/HUBOGQ3G7RJBBM33OSIXSZFCDO/graph.json","fetch_events":"https://pith.science/api/pith-number/HUBOGQ3G7RJBBM33OSIXSZFCDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO/action/storage_attestation","attest_author":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO/action/author_attestation","sign_citation":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO/action/citation_signature","submit_replication":"https://pith.science/pith/HUBOGQ3G7RJBBM33OSIXSZFCDO/action/replication_record"}},"created_at":"2026-05-25T02:02:34.146428+00:00","updated_at":"2026-05-25T02:02:34.146428+00:00"}