{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EAYPWJ76F3C5Q7OINZ7EXWZFTE","short_pith_number":"pith:EAYPWJ76","schema_version":"1.0","canonical_sha256":"2030fb27fe2ec5d87dc86e7e4bdb25991699197e13b13840fe9050b587711a98","source":{"kind":"arxiv","id":"1611.09921","version":2},"attestation_state":"computed","paper":{"title":"Less is More: Learning Prominent and Diverse Topics for Data Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Cheng Li, Jian Tang, Ming Zhang, Qiaozhu Mei","submitted_at":"2016-11-29T22:24:30Z","abstract_excerpt":"Statistical topic models efficiently facilitate the exploration of large-scale data sets. Many models have been developed and broadly used to summarize the semantic structure in news, science, social media, and digital humanities. However, a common and practical objective in data exploration tasks is not to enumerate all existing topics, but to quickly extract representative ones that broadly cover the content of the corpus, i.e., a few topics that serve as a good summary of the data. Most existing topic models fit exactly the same number of topics as a user specifies, which have imposed an un"},"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":"1611.09921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2016-11-29T22:24:30Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"92c41403737c2aa21a6dce16c6ccea5ddb030f008437d6894ad9b9334393b73e","abstract_canon_sha256":"bc78c7748472422d2bb5a53f3d26794e0f254afba33838feaad1eaeee0aa150a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:07.062504Z","signature_b64":"dHwqwVBofMqD1cCgo7lqtZddLxLgL6MM1B7msAPP40MO1/YS2+OFjOCt95EwVGkkZkRfzL+9ufwBRIhkcccbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2030fb27fe2ec5d87dc86e7e4bdb25991699197e13b13840fe9050b587711a98","last_reissued_at":"2026-05-18T00:56:07.061771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:07.061771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: Learning Prominent and Diverse Topics for Data Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Cheng Li, Jian Tang, Ming Zhang, Qiaozhu Mei","submitted_at":"2016-11-29T22:24:30Z","abstract_excerpt":"Statistical topic models efficiently facilitate the exploration of large-scale data sets. Many models have been developed and broadly used to summarize the semantic structure in news, science, social media, and digital humanities. However, a common and practical objective in data exploration tasks is not to enumerate all existing topics, but to quickly extract representative ones that broadly cover the content of the corpus, i.e., a few topics that serve as a good summary of the data. Most existing topic models fit exactly the same number of topics as a user specifies, which have imposed an un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09921","kind":"arxiv","version":2},"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":"1611.09921","created_at":"2026-05-18T00:56:07.061858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09921v2","created_at":"2026-05-18T00:56:07.061858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09921","created_at":"2026-05-18T00:56:07.061858+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAYPWJ76F3C5","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAYPWJ76F3C5Q7OI","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAYPWJ76","created_at":"2026-05-18T12:30:12.583610+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/EAYPWJ76F3C5Q7OINZ7EXWZFTE","json":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE.json","graph_json":"https://pith.science/api/pith-number/EAYPWJ76F3C5Q7OINZ7EXWZFTE/graph.json","events_json":"https://pith.science/api/pith-number/EAYPWJ76F3C5Q7OINZ7EXWZFTE/events.json","paper":"https://pith.science/paper/EAYPWJ76"},"agent_actions":{"view_html":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE","download_json":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE.json","view_paper":"https://pith.science/paper/EAYPWJ76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09921&json=true","fetch_graph":"https://pith.science/api/pith-number/EAYPWJ76F3C5Q7OINZ7EXWZFTE/graph.json","fetch_events":"https://pith.science/api/pith-number/EAYPWJ76F3C5Q7OINZ7EXWZFTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE/action/storage_attestation","attest_author":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE/action/author_attestation","sign_citation":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE/action/citation_signature","submit_replication":"https://pith.science/pith/EAYPWJ76F3C5Q7OINZ7EXWZFTE/action/replication_record"}},"created_at":"2026-05-18T00:56:07.061858+00:00","updated_at":"2026-05-18T00:56:07.061858+00:00"}