{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VELCT7UGDVEEK54ZDT4OTUGQVW","short_pith_number":"pith:VELCT7UG","schema_version":"1.0","canonical_sha256":"a91629fe861d484577991cf8e9d0d0adb732d0bcfb50a958a8a6771eaf112a2d","source":{"kind":"arxiv","id":"2402.11094","version":3},"attestation_state":"computed","paper":{"title":"Revisiting Word Embeddings in the LLM Era","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Matthew Freestone, Naman Bansal, Sathyanarayanan Aakur, Shubhra Kanti Karmaker Santu, Yash Mahajan","submitted_at":"2024-02-16T21:47:30Z","abstract_excerpt":"Large Language Models (LLMs) have recently shown remarkable advancement in various NLP tasks. As such, a popular trend has emerged lately where NLP researchers extract word/sentence/document embeddings from these large decoder-only models and use them for various inference tasks with promising results. However, it is still unclear whether the performance improvement of LLM-induced embeddings is merely because of scale or whether underlying embeddings they produce significantly differ from classical encoding models like Word2Vec, GloVe, Sentence-BERT (SBERT) or Universal Sentence Encoder (USE)."},"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":"2402.11094","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T21:47:30Z","cross_cats_sorted":[],"title_canon_sha256":"feb8a31e98a39dd5253fdcd7652299b9959bced2dd519fb2913bb81a0f1256d2","abstract_canon_sha256":"93269f47a9fc48ac4afca98505b178af4149845b22393e7fd09fad49cada8b9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:44.417660Z","signature_b64":"fhjF/V4Z8+rrteWLyMHIrhZepnNcLFZLjVJnxmgotpSStQ5jSNlBUs58W2FBvC/tHwnhUai8q8zfgovD7r8QBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a91629fe861d484577991cf8e9d0d0adb732d0bcfb50a958a8a6771eaf112a2d","last_reissued_at":"2026-07-05T10:22:44.416985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:44.416985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Word Embeddings in the LLM Era","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Matthew Freestone, Naman Bansal, Sathyanarayanan Aakur, Shubhra Kanti Karmaker Santu, Yash Mahajan","submitted_at":"2024-02-16T21:47:30Z","abstract_excerpt":"Large Language Models (LLMs) have recently shown remarkable advancement in various NLP tasks. As such, a popular trend has emerged lately where NLP researchers extract word/sentence/document embeddings from these large decoder-only models and use them for various inference tasks with promising results. However, it is still unclear whether the performance improvement of LLM-induced embeddings is merely because of scale or whether underlying embeddings they produce significantly differ from classical encoding models like Word2Vec, GloVe, Sentence-BERT (SBERT) or Universal Sentence Encoder (USE)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11094","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/2402.11094/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":"2402.11094","created_at":"2026-07-05T10:22:44.417096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11094v3","created_at":"2026-07-05T10:22:44.417096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11094","created_at":"2026-07-05T10:22:44.417096+00:00"},{"alias_kind":"pith_short_12","alias_value":"VELCT7UGDVEE","created_at":"2026-07-05T10:22:44.417096+00:00"},{"alias_kind":"pith_short_16","alias_value":"VELCT7UGDVEEK54Z","created_at":"2026-07-05T10:22:44.417096+00:00"},{"alias_kind":"pith_short_8","alias_value":"VELCT7UG","created_at":"2026-07-05T10:22:44.417096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21354","citing_title":"Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW","json":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW.json","graph_json":"https://pith.science/api/pith-number/VELCT7UGDVEEK54ZDT4OTUGQVW/graph.json","events_json":"https://pith.science/api/pith-number/VELCT7UGDVEEK54ZDT4OTUGQVW/events.json","paper":"https://pith.science/paper/VELCT7UG"},"agent_actions":{"view_html":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW","download_json":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW.json","view_paper":"https://pith.science/paper/VELCT7UG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11094&json=true","fetch_graph":"https://pith.science/api/pith-number/VELCT7UGDVEEK54ZDT4OTUGQVW/graph.json","fetch_events":"https://pith.science/api/pith-number/VELCT7UGDVEEK54ZDT4OTUGQVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW/action/storage_attestation","attest_author":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW/action/author_attestation","sign_citation":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW/action/citation_signature","submit_replication":"https://pith.science/pith/VELCT7UGDVEEK54ZDT4OTUGQVW/action/replication_record"}},"created_at":"2026-07-05T10:22:44.417096+00:00","updated_at":"2026-07-05T10:22:44.417096+00:00"}