{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BPMCYNJAZHIWDMMEUE25FJ5WMA","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":"e40171133f82f0733aac94e9b780aad12f40134b33ca4085f328eafb4ed30674","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T15:26:07Z","title_canon_sha256":"eaf7f69440e14f6914e354fdcfc285f02bd6bfe749795cb00f453e58cfacfb0f"},"schema_version":"1.0","source":{"id":"1609.08496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08496","created_at":"2026-05-18T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08496v1","created_at":"2026-05-18T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08496","created_at":"2026-05-18T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"BPMCYNJAZHIW","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BPMCYNJAZHIWDMME","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BPMCYNJA","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:6442928c1243ed59d9a662f7576be95d4f3eb840653f7505e38c33c4e897f0fb","target":"graph","created_at":"2026-05-18T01:03:45Z","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":"Inferring topics from the overwhelming amount of short texts becomes a critical but challenging task for many content analysis tasks, such as content charactering, user interest profiling, and emerging topic detecting. Existing methods such as probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA) cannot solve this prob- lem very well since only very limited word co-occurrence information is available in short texts. This paper studies how to incorporate the external word correlation knowledge into short texts to improve the coherence of topic modeling. Based on re","authors_text":"Jipeng Qiang, Ping Chen, Tong Wang, Xindong Wu","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T15:26:07Z","title":"Topic Modeling over Short Texts by Incorporating Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08496","kind":"arxiv","version":1},"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":"sha256:24f237f710006d864e6dd6414e4617beb8dc71956601cd61d018e8ae03dc0675","target":"record","created_at":"2026-05-18T01:03:45Z","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":"e40171133f82f0733aac94e9b780aad12f40134b33ca4085f328eafb4ed30674","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T15:26:07Z","title_canon_sha256":"eaf7f69440e14f6914e354fdcfc285f02bd6bfe749795cb00f453e58cfacfb0f"},"schema_version":"1.0","source":{"id":"1609.08496","kind":"arxiv","version":1}},"canonical_sha256":"0bd82c3520c9d161b184a135d2a7b6600d2075adad30794592ef0201e9549dae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bd82c3520c9d161b184a135d2a7b6600d2075adad30794592ef0201e9549dae","first_computed_at":"2026-05-18T01:03:45.780195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:45.780195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HdZjLRfJv0wJwjaqSJ7kh1o6+xeGLsmWs4UE/RwyNxS+Plb/cvpuBRc5WS8ov4tiXR48xhsVXOuMzNbS/TVYCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:45.780570Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.08496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24f237f710006d864e6dd6414e4617beb8dc71956601cd61d018e8ae03dc0675","sha256:6442928c1243ed59d9a662f7576be95d4f3eb840653f7505e38c33c4e897f0fb"],"state_sha256":"244ca1344c33b34ec750a58d977449b3e218170857882807c69a201a9b2597ab"}