{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Q2G7EZIN6IJQABB7NHBTNB5CFV","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":"5b829052b6232b71948ce1781070e253e4e6a689e3cb1442188683a89d1be280","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T21:35:54Z","title_canon_sha256":"873397f520859bc09adb62f7fdfb588baaf5e89ed755dc490b28327c1625bc23"},"schema_version":"1.0","source":{"id":"1902.08850","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08850","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08850v3","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08850","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"pith_short_12","alias_value":"Q2G7EZIN6IJQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"Q2G7EZIN6IJQABB7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"Q2G7EZIN","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:ff6f03f3e41d852b22d8f9217c2725f14dfde874aba9a91a037eba5f11862bcd","target":"graph","created_at":"2026-05-17T23:47:01Z","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"},"paper":{"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","authors_text":"Andrei M. Butnaru, Radu Tudor Ionescu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T21:35:54Z","title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08850","kind":"arxiv","version":3},"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":"sha256:303f1d1564ab05dfb521977fdbe77a773b32b700874840cad065065fae76943b","target":"record","created_at":"2026-05-17T23:47:01Z","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":"5b829052b6232b71948ce1781070e253e4e6a689e3cb1442188683a89d1be280","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T21:35:54Z","title_canon_sha256":"873397f520859bc09adb62f7fdfb588baaf5e89ed755dc490b28327c1625bc23"},"schema_version":"1.0","source":{"id":"1902.08850","kind":"arxiv","version":3}},"canonical_sha256":"868df2650df21300043f69c33687a22d63e5746d641c99873a673ef1d3af6c52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"868df2650df21300043f69c33687a22d63e5746d641c99873a673ef1d3af6c52","first_computed_at":"2026-05-17T23:47:01.755821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:01.755821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2K4Yzw5/+oLBdBw4NhFGomPcf6Emhb5osTaiX1CdAaskQRNukPxQVTnVib9YMnSR0YL7o/IG/4DTu3xHKWZYAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:01.756562Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.08850","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:303f1d1564ab05dfb521977fdbe77a773b32b700874840cad065065fae76943b","sha256:ff6f03f3e41d852b22d8f9217c2725f14dfde874aba9a91a037eba5f11862bcd"],"state_sha256":"6edd6ceb4269bd51b212c9f8329788635cb8cbcd3f20927676c6bd5f17976e72"}