{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CLI77TUJZQWWN4QEBOPUSO74CX","short_pith_number":"pith:CLI77TUJ","schema_version":"1.0","canonical_sha256":"12d1ffce89cc2d66f2040b9f493bfc15ed75b8231f1f00a8c860aa4a84e40f81","source":{"kind":"arxiv","id":"2008.02218","version":3},"attestation_state":"computed","paper":{"title":"BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Adam Hare, Christopher G. Brinton, Qiong Wu, Sirui Wang, Yanhua Li, Yuwei Tu, Zhenming Liu","submitted_at":"2020-08-05T16:34:33Z","abstract_excerpt":"Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems of \"topic identification\" and \"text segmentation\" for sparse document learning, when there is a single new text of interest. In developing a methodology to handle single documents, we face two major challenges. First is sparse information: with access to only one document, we cannot train traditional topic models or deep learning algorithms. Second is signif"},"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":"2008.02218","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-05T16:34:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9c386d9aa17e3e226385b638140a09c751a6d2e258e7201121f6f154b9f3400","abstract_canon_sha256":"249b77b66193a9fe8b4a49275ac75cf1979b1cd4a258783fb5b207ab4d2d4c67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:42.759086Z","signature_b64":"hfg50mJhP5p2hJlom6KWR9cBhhFw6zNksqOg6pnuQeeU1ohUNDL4QHQzMvCQrdf5Fowc114eZ6nHxRUM+CmsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d1ffce89cc2d66f2040b9f493bfc15ed75b8231f1f00a8c860aa4a84e40f81","last_reissued_at":"2026-07-05T02:42:42.758606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:42.758606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Adam Hare, Christopher G. Brinton, Qiong Wu, Sirui Wang, Yanhua Li, Yuwei Tu, Zhenming Liu","submitted_at":"2020-08-05T16:34:33Z","abstract_excerpt":"Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems of \"topic identification\" and \"text segmentation\" for sparse document learning, when there is a single new text of interest. In developing a methodology to handle single documents, we face two major challenges. First is sparse information: with access to only one document, we cannot train traditional topic models or deep learning algorithms. Second is signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02218","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/2008.02218/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":"2008.02218","created_at":"2026-07-05T02:42:42.758662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02218v3","created_at":"2026-07-05T02:42:42.758662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02218","created_at":"2026-07-05T02:42:42.758662+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLI77TUJZQWW","created_at":"2026-07-05T02:42:42.758662+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLI77TUJZQWWN4QE","created_at":"2026-07-05T02:42:42.758662+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLI77TUJ","created_at":"2026-07-05T02:42:42.758662+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/CLI77TUJZQWWN4QEBOPUSO74CX","json":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX.json","graph_json":"https://pith.science/api/pith-number/CLI77TUJZQWWN4QEBOPUSO74CX/graph.json","events_json":"https://pith.science/api/pith-number/CLI77TUJZQWWN4QEBOPUSO74CX/events.json","paper":"https://pith.science/paper/CLI77TUJ"},"agent_actions":{"view_html":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX","download_json":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX.json","view_paper":"https://pith.science/paper/CLI77TUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02218&json=true","fetch_graph":"https://pith.science/api/pith-number/CLI77TUJZQWWN4QEBOPUSO74CX/graph.json","fetch_events":"https://pith.science/api/pith-number/CLI77TUJZQWWN4QEBOPUSO74CX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX/action/storage_attestation","attest_author":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX/action/author_attestation","sign_citation":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX/action/citation_signature","submit_replication":"https://pith.science/pith/CLI77TUJZQWWN4QEBOPUSO74CX/action/replication_record"}},"created_at":"2026-07-05T02:42:42.758662+00:00","updated_at":"2026-07-05T02:42:42.758662+00:00"}