{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:2FWOMBD5DA43C4SN6FMGI3WTRI","short_pith_number":"pith:2FWOMBD5","schema_version":"1.0","canonical_sha256":"d16ce6047d1839b1724df158646ed38a1ca8262668eb6c60621c8d6ef239b1f5","source":{"kind":"arxiv","id":"1604.00126","version":1},"attestation_state":"computed","paper":{"title":"Nonparametric Spherical Topic Modeling with Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ardavan Saeedi, Karthik Narasimhan, Kayhan Batmanghelich, Sam Gershman","submitted_at":"2016-04-01T04:36:58Z","abstract_excerpt":"Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and p"},"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":"1604.00126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-01T04:36:58Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"a985de48a7a256776f71980be13f8ea0b89eef5774cb780fe4454b2a399b04b2","abstract_canon_sha256":"2e356262c7caff6bcf68162402a73ce5833fb04eaa039730cc417c32f1757312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:54.494141Z","signature_b64":"C2wrsng9AJ1Lmh/jIG8s9SmltMoqCTF5Not9jlUAL/XU8EMZ8aq5nHmcqnCgJPpLep2pDNYZopEteAdR/JDWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d16ce6047d1839b1724df158646ed38a1ca8262668eb6c60621c8d6ef239b1f5","last_reissued_at":"2026-05-18T01:17:54.493370Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:54.493370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric Spherical Topic Modeling with Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ardavan Saeedi, Karthik Narasimhan, Kayhan Batmanghelich, Sam Gershman","submitted_at":"2016-04-01T04:36:58Z","abstract_excerpt":"Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00126","kind":"arxiv","version":1},"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":"1604.00126","created_at":"2026-05-18T01:17:54.493518+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.00126v1","created_at":"2026-05-18T01:17:54.493518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00126","created_at":"2026-05-18T01:17:54.493518+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FWOMBD5DA43","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FWOMBD5DA43C4SN","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FWOMBD5","created_at":"2026-05-18T12:29:55.572404+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/2FWOMBD5DA43C4SN6FMGI3WTRI","json":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI.json","graph_json":"https://pith.science/api/pith-number/2FWOMBD5DA43C4SN6FMGI3WTRI/graph.json","events_json":"https://pith.science/api/pith-number/2FWOMBD5DA43C4SN6FMGI3WTRI/events.json","paper":"https://pith.science/paper/2FWOMBD5"},"agent_actions":{"view_html":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI","download_json":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI.json","view_paper":"https://pith.science/paper/2FWOMBD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.00126&json=true","fetch_graph":"https://pith.science/api/pith-number/2FWOMBD5DA43C4SN6FMGI3WTRI/graph.json","fetch_events":"https://pith.science/api/pith-number/2FWOMBD5DA43C4SN6FMGI3WTRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI/action/storage_attestation","attest_author":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI/action/author_attestation","sign_citation":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI/action/citation_signature","submit_replication":"https://pith.science/pith/2FWOMBD5DA43C4SN6FMGI3WTRI/action/replication_record"}},"created_at":"2026-05-18T01:17:54.493518+00:00","updated_at":"2026-05-18T01:17:54.493518+00:00"}