{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RAX6IXIFVIC3LNAJXEGD3GVIA6","short_pith_number":"pith:RAX6IXIF","schema_version":"1.0","canonical_sha256":"882fe45d05aa05b5b409b90c3d9aa807ad505449c8092843d6900c11de1c3a6e","source":{"kind":"arxiv","id":"2212.06002","version":2},"attestation_state":"computed","paper":{"title":"Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Martin Michalski, Yucheng Jiang, Yu Meng, Yunyi Zhang, Yu Zhang","submitted_at":"2022-12-12T16:03:38Z","abstract_excerpt":"Instead of mining coherent topics from a given text corpus in a completely unsupervised manner, seed-guided topic discovery methods leverage user-provided seed words to extract distinctive and coherent topics so that the mined topics can better cater to the user's interest. To model the semantic correlation between words and seeds for discovering topic-indicative terms, existing seed-guided approaches utilize different types of context signals, such as document-level word co-occurrences, sliding window-based local contexts, and generic linguistic knowledge brought by pre-trained language model"},"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":"2212.06002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-12T16:03:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e6160fcf268c067d29dfbfe71d58ed560a21c1ea536fe493e2e7b02467f2b761","abstract_canon_sha256":"459b59d9886045ad6fdaa35d2d2cb8450f2811f389d70aeaff8d43e582c0784a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:12.704787Z","signature_b64":"hxJNFOma0gmuaQm9YKqAmst9zniurWWnuwF4R1DWYlXwHu9cEzpf/M+5qOWi0uZWmZDdBBUUUe9VAY1nr+yMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"882fe45d05aa05b5b409b90c3d9aa807ad505449c8092843d6900c11de1c3a6e","last_reissued_at":"2026-07-05T05:32:12.704240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:12.704240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Martin Michalski, Yucheng Jiang, Yu Meng, Yunyi Zhang, Yu Zhang","submitted_at":"2022-12-12T16:03:38Z","abstract_excerpt":"Instead of mining coherent topics from a given text corpus in a completely unsupervised manner, seed-guided topic discovery methods leverage user-provided seed words to extract distinctive and coherent topics so that the mined topics can better cater to the user's interest. To model the semantic correlation between words and seeds for discovering topic-indicative terms, existing seed-guided approaches utilize different types of context signals, such as document-level word co-occurrences, sliding window-based local contexts, and generic linguistic knowledge brought by pre-trained language model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06002","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.06002/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":"2212.06002","created_at":"2026-07-05T05:32:12.704303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06002v2","created_at":"2026-07-05T05:32:12.704303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06002","created_at":"2026-07-05T05:32:12.704303+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAX6IXIFVIC3","created_at":"2026-07-05T05:32:12.704303+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAX6IXIFVIC3LNAJ","created_at":"2026-07-05T05:32:12.704303+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAX6IXIF","created_at":"2026-07-05T05:32:12.704303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02090","citing_title":"Applying Text Mining to Analyze Human Question Asking in Creativity Research","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6","json":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6.json","graph_json":"https://pith.science/api/pith-number/RAX6IXIFVIC3LNAJXEGD3GVIA6/graph.json","events_json":"https://pith.science/api/pith-number/RAX6IXIFVIC3LNAJXEGD3GVIA6/events.json","paper":"https://pith.science/paper/RAX6IXIF"},"agent_actions":{"view_html":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6","download_json":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6.json","view_paper":"https://pith.science/paper/RAX6IXIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06002&json=true","fetch_graph":"https://pith.science/api/pith-number/RAX6IXIFVIC3LNAJXEGD3GVIA6/graph.json","fetch_events":"https://pith.science/api/pith-number/RAX6IXIFVIC3LNAJXEGD3GVIA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6/action/storage_attestation","attest_author":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6/action/author_attestation","sign_citation":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6/action/citation_signature","submit_replication":"https://pith.science/pith/RAX6IXIFVIC3LNAJXEGD3GVIA6/action/replication_record"}},"created_at":"2026-07-05T05:32:12.704303+00:00","updated_at":"2026-07-05T05:32:12.704303+00:00"}