{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VGBHSI6ZGPHVKEC24APY55BMLT","short_pith_number":"pith:VGBHSI6Z","schema_version":"1.0","canonical_sha256":"a9827923d933cf55105ae01f8ef42c5cff4db68243bb0a9e87174a03b3ba2a3a","source":{"kind":"arxiv","id":"1908.07599","version":3},"attestation_state":"computed","paper":{"title":"Learning document embeddings along with their uncertainties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Luk\\'a\\v{s} Burget, Old\\v{r}ich Plchot, Santosh Kesiraju, Suryakanth V Gangashetty","submitted_at":"2019-08-20T20:31:51Z","abstract_excerpt":"Majority of the text modelling techniques yield only point-estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its co-variance. Additionally, in the proposed Bayesian SMM, we address a commonly encountered problem of intractability that appears during variational inference in "},"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":"1908.07599","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-20T20:31:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"68e838514f4663fa826d1bd624a790f213a1f0eaea08451b3156786a01f5839b","abstract_canon_sha256":"44a849bc3caf0839c91551d22d42890d1102df44579246f6bd35031854a68af4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:45.549922Z","signature_b64":"LKgwlXrj0/AUj/x193L7eOucDgDXArDOMFlLsgH+BaYGKHv1TJ2MYKd2TvUChW7czs4KFNEjrEMfuBBYdxnMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9827923d933cf55105ae01f8ef42c5cff4db68243bb0a9e87174a03b3ba2a3a","last_reissued_at":"2026-07-05T01:23:45.549437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:45.549437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning document embeddings along with their uncertainties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Luk\\'a\\v{s} Burget, Old\\v{r}ich Plchot, Santosh Kesiraju, Suryakanth V Gangashetty","submitted_at":"2019-08-20T20:31:51Z","abstract_excerpt":"Majority of the text modelling techniques yield only point-estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its co-variance. Additionally, in the proposed Bayesian SMM, we address a commonly encountered problem of intractability that appears during variational inference in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07599","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/1908.07599/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":"1908.07599","created_at":"2026-07-05T01:23:45.549499+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07599v3","created_at":"2026-07-05T01:23:45.549499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07599","created_at":"2026-07-05T01:23:45.549499+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGBHSI6ZGPHV","created_at":"2026-07-05T01:23:45.549499+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGBHSI6ZGPHVKEC2","created_at":"2026-07-05T01:23:45.549499+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGBHSI6Z","created_at":"2026-07-05T01:23:45.549499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT","json":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT.json","graph_json":"https://pith.science/api/pith-number/VGBHSI6ZGPHVKEC24APY55BMLT/graph.json","events_json":"https://pith.science/api/pith-number/VGBHSI6ZGPHVKEC24APY55BMLT/events.json","paper":"https://pith.science/paper/VGBHSI6Z"},"agent_actions":{"view_html":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT","download_json":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT.json","view_paper":"https://pith.science/paper/VGBHSI6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07599&json=true","fetch_graph":"https://pith.science/api/pith-number/VGBHSI6ZGPHVKEC24APY55BMLT/graph.json","fetch_events":"https://pith.science/api/pith-number/VGBHSI6ZGPHVKEC24APY55BMLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT/action/storage_attestation","attest_author":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT/action/author_attestation","sign_citation":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT/action/citation_signature","submit_replication":"https://pith.science/pith/VGBHSI6ZGPHVKEC24APY55BMLT/action/replication_record"}},"created_at":"2026-07-05T01:23:45.549499+00:00","updated_at":"2026-07-05T01:23:45.549499+00:00"}