{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Q2G7EZIN6IJQABB7NHBTNB5CFV","short_pith_number":"pith:Q2G7EZIN","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"},"canonical_sha256":"868df2650df21300043f69c33687a22d63e5746d641c99873a673ef1d3af6c52","source":{"kind":"arxiv","id":"1902.08850","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Q2G7EZIN6IJQABB7NHBTNB5CFV","target":"record","payload":{"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"},"canonical_sha256":"868df2650df21300043f69c33687a22d63e5746d641c99873a673ef1d3af6c52","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"},"source_kind":"arxiv","source_id":"1902.08850","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dunNUPgWUsXRvDAjDrIHOR1jGrq77aO+yNgoOyyn6ZJDzxtesHIEn1M+cnVH1TLYW/KoVwNllzPs0JoF2zUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:28:05.301875Z"},"content_sha256":"303f1d1564ab05dfb521977fdbe77a773b32b700874840cad065065fae76943b","schema_version":"1.0","event_id":"sha256:303f1d1564ab05dfb521977fdbe77a773b32b700874840cad065065fae76943b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Q2G7EZIN6IJQABB7NHBTNB5CFV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/J95Boa6TsaFITsnQT0Lo09rbHJHBB7T/JamglTEb16HQtrMncivZQrLocyH3Oe7fqD50fy4XUliVB9TgL/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:28:05.302545Z"},"content_sha256":"ff6f03f3e41d852b22d8f9217c2725f14dfde874aba9a91a037eba5f11862bcd","schema_version":"1.0","event_id":"sha256:ff6f03f3e41d852b22d8f9217c2725f14dfde874aba9a91a037eba5f11862bcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/bundle.json","state_url":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:28:05Z","links":{"resolver":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV","bundle":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/bundle.json","state":"https://pith.science/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q2G7EZIN6IJQABB7NHBTNB5CFV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aXYa8VCn2aVOFyiJLHWMA0Ky3+aUvltN658ghNPpjC+wsw2zAmNPJodUi4M/Y5vlhdthl0l+tVZyE7LOky7rCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:28:05.305741Z","bundle_sha256":"6b28b4150cdbceb305999c505f7124048018dc131ef25bf9ec226bc4683a88e1"}}