{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BZRFQISKTJ5C5EXG754VEHISC7","short_pith_number":"pith:BZRFQISK","schema_version":"1.0","canonical_sha256":"0e6258224a9a7a2e92e6ff79521d1217d17caaf0798613c02031bdf069337cb2","source":{"kind":"arxiv","id":"1911.05758","version":2},"attestation_state":"computed","paper":{"title":"What do you mean, BERT? Assessing BERT as a Distributional Semantics Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Denis Paperno, Kees van Deemter, Mathieu Constant, Timothee Mickus","submitted_at":"2019-11-13T19:04:42Z","abstract_excerpt":"Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that produces contextualized embeddings and has set the state-of-the-art in several semantic tasks, and study the semantic coherence of its embedding space. While showing a tendency towards coherence, BERT does not fully live up to the natural expectations for a semantic vector space. In particular, we find that the position of the sentence in which a word occurs, whil"},"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":"1911.05758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-13T19:04:42Z","cross_cats_sorted":[],"title_canon_sha256":"2a247b54acc090502c6d86032f79f4edfdaf605c6098b408be896f8a8496c96d","abstract_canon_sha256":"ccb8cf8137f6d5d5c0a55e1dcbb5aa94e08431fc94586f619f6b8ab4c60b3184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:21.727999Z","signature_b64":"4w/2ng+5WqHJ8/myLhHxTIZybUhqrlo1EDtse/Hw0oqeW/8Vg7HcTIy9+SdJpTdn/5ubNGZBcYKPjcGyxRAkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e6258224a9a7a2e92e6ff79521d1217d17caaf0798613c02031bdf069337cb2","last_reissued_at":"2026-07-05T01:01:21.727375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:21.727375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What do you mean, BERT? Assessing BERT as a Distributional Semantics Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Denis Paperno, Kees van Deemter, Mathieu Constant, Timothee Mickus","submitted_at":"2019-11-13T19:04:42Z","abstract_excerpt":"Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that produces contextualized embeddings and has set the state-of-the-art in several semantic tasks, and study the semantic coherence of its embedding space. While showing a tendency towards coherence, BERT does not fully live up to the natural expectations for a semantic vector space. In particular, we find that the position of the sentence in which a word occurs, whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05758","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.05758/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":"1911.05758","created_at":"2026-07-05T01:01:21.727451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05758v2","created_at":"2026-07-05T01:01:21.727451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05758","created_at":"2026-07-05T01:01:21.727451+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZRFQISKTJ5C","created_at":"2026-07-05T01:01:21.727451+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZRFQISKTJ5C5EXG","created_at":"2026-07-05T01:01:21.727451+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZRFQISK","created_at":"2026-07-05T01:01:21.727451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14877","citing_title":"Astro-HEP-BERT: A bidirectional language model for studying the meanings of concepts in astrophysics and high energy physics","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7","json":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7.json","graph_json":"https://pith.science/api/pith-number/BZRFQISKTJ5C5EXG754VEHISC7/graph.json","events_json":"https://pith.science/api/pith-number/BZRFQISKTJ5C5EXG754VEHISC7/events.json","paper":"https://pith.science/paper/BZRFQISK"},"agent_actions":{"view_html":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7","download_json":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7.json","view_paper":"https://pith.science/paper/BZRFQISK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05758&json=true","fetch_graph":"https://pith.science/api/pith-number/BZRFQISKTJ5C5EXG754VEHISC7/graph.json","fetch_events":"https://pith.science/api/pith-number/BZRFQISKTJ5C5EXG754VEHISC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7/action/storage_attestation","attest_author":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7/action/author_attestation","sign_citation":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7/action/citation_signature","submit_replication":"https://pith.science/pith/BZRFQISKTJ5C5EXG754VEHISC7/action/replication_record"}},"created_at":"2026-07-05T01:01:21.727451+00:00","updated_at":"2026-07-05T01:01:21.727451+00:00"}