{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q2G7EZIN6IJQABB7NHBTNB5CFV","short_pith_number":"pith:Q2G7EZIN","schema_version":"1.0","canonical_sha256":"868df2650df21300043f69c33687a22d63e5746d641c99873a673ef1d3af6c52","source":{"kind":"arxiv","id":"1902.08850","version":3},"attestation_state":"computed","paper":{"title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei M. Butnaru, Radu Tudor Ionescu","submitted_at":"2019-02-23T21:35:54Z","abstract_excerpt":"In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for image representation, and it works as follows. First, the word embeddings gathered from a collection of documents are clustered by k-means in order to learn a codebook of semnatically-related word embeddings. Each word embedding is then associated to its nearest cluster centroid (codeword). The Vector of Locally-Aggregated Word Embeddings (VLAWE) representation of a document is"},"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":"1902.08850","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T21:35:54Z","cross_cats_sorted":[],"title_canon_sha256":"873397f520859bc09adb62f7fdfb588baaf5e89ed755dc490b28327c1625bc23","abstract_canon_sha256":"5b829052b6232b71948ce1781070e253e4e6a689e3cb1442188683a89d1be280"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:01.756562Z","signature_b64":"2K4Yzw5/+oLBdBw4NhFGomPcf6Emhb5osTaiX1CdAaskQRNukPxQVTnVib9YMnSR0YL7o/IG/4DTu3xHKWZYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"868df2650df21300043f69c33687a22d63e5746d641c99873a673ef1d3af6c52","last_reissued_at":"2026-05-17T23:47:01.755821Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:01.755821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei M. Butnaru, Radu Tudor Ionescu","submitted_at":"2019-02-23T21:35:54Z","abstract_excerpt":"In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for image representation, and it works as follows. First, the word embeddings gathered from a collection of documents are clustered by k-means in order to learn a codebook of semnatically-related word embeddings. Each word embedding is then associated to its nearest cluster centroid (codeword). The Vector of Locally-Aggregated Word Embeddings (VLAWE) representation of a document is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08850","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":""},"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":"1902.08850","created_at":"2026-05-17T23:47:01.755942+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08850v3","created_at":"2026-05-17T23:47:01.755942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08850","created_at":"2026-05-17T23:47:01.755942+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2G7EZIN6IJQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2G7EZIN6IJQABB7","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2G7EZIN","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07414","citing_title":"GNN-CNN: An Efficient Hybrid Model of Convolutional and Graph Neural Networks for Text Representation","ref_index":2013,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV","json":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV.json","graph_json":"https://pith.science/api/pith-number/Q2G7EZIN6IJQABB7NHBTNB5CFV/graph.json","events_json":"https://pith.science/api/pith-number/Q2G7EZIN6IJQABB7NHBTNB5CFV/events.json","paper":"https://pith.science/paper/Q2G7EZIN"},"agent_actions":{"view_html":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV","download_json":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV.json","view_paper":"https://pith.science/paper/Q2G7EZIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08850&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2G7EZIN6IJQABB7NHBTNB5CFV/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2G7EZIN6IJQABB7NHBTNB5CFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/action/storage_attestation","attest_author":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/action/author_attestation","sign_citation":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/action/citation_signature","submit_replication":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/action/replication_record"}},"created_at":"2026-05-17T23:47:01.755942+00:00","updated_at":"2026-05-17T23:47:01.755942+00:00"}