{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MNHI5O2TGNHAGROOIHMFVEHV5R","short_pith_number":"pith:MNHI5O2T","schema_version":"1.0","canonical_sha256":"634e8ebb53334e0345ce41d85a90f5ec5349a0c0440cc0ef333be6f0ee016e43","source":{"kind":"arxiv","id":"2506.07453","version":1},"attestation_state":"computed","paper":{"title":"Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Chen-Chuan Chang, Pritom Saha Akash","submitted_at":"2025-06-09T05:59:18Z","abstract_excerpt":"Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We address this challenge by formally introducing domain adaptation for low-resource topic modeling, where a high-resource source domain informs a low-resource target domain without overwhelming it with irrelevant content. We establish a finite-sample generalization bound showing that effective knowledge transfer depends on robust performance in both domains, minim"},"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":"2506.07453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T05:59:18Z","cross_cats_sorted":[],"title_canon_sha256":"ba6c5e5f8f42acc1722b4e2cc9f6d93bc1721e272a03774a48f1b1fc79ded062","abstract_canon_sha256":"a04b2845b24bd7565d07dc6acde5e92cdeb027702e2294c63b46231f8b93b6a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:27.560112Z","signature_b64":"Te8Aq60iJd4IB1i3fTLKOFvS7rP8Jn4A6IZevIgqabgEn68UX9IQyCnrxMquSZb/iH6Zl8fyLbLlmwyQUeekAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634e8ebb53334e0345ce41d85a90f5ec5349a0c0440cc0ef333be6f0ee016e43","last_reissued_at":"2026-07-05T11:18:27.559445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:27.559445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Chen-Chuan Chang, Pritom Saha Akash","submitted_at":"2025-06-09T05:59:18Z","abstract_excerpt":"Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We address this challenge by formally introducing domain adaptation for low-resource topic modeling, where a high-resource source domain informs a low-resource target domain without overwhelming it with irrelevant content. We establish a finite-sample generalization bound showing that effective knowledge transfer depends on robust performance in both domains, minim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07453","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.07453/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":"2506.07453","created_at":"2026-07-05T11:18:27.559531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07453v1","created_at":"2026-07-05T11:18:27.559531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07453","created_at":"2026-07-05T11:18:27.559531+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNHI5O2TGNHA","created_at":"2026-07-05T11:18:27.559531+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNHI5O2TGNHAGROO","created_at":"2026-07-05T11:18:27.559531+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNHI5O2T","created_at":"2026-07-05T11:18:27.559531+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/MNHI5O2TGNHAGROOIHMFVEHV5R","json":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R.json","graph_json":"https://pith.science/api/pith-number/MNHI5O2TGNHAGROOIHMFVEHV5R/graph.json","events_json":"https://pith.science/api/pith-number/MNHI5O2TGNHAGROOIHMFVEHV5R/events.json","paper":"https://pith.science/paper/MNHI5O2T"},"agent_actions":{"view_html":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R","download_json":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R.json","view_paper":"https://pith.science/paper/MNHI5O2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07453&json=true","fetch_graph":"https://pith.science/api/pith-number/MNHI5O2TGNHAGROOIHMFVEHV5R/graph.json","fetch_events":"https://pith.science/api/pith-number/MNHI5O2TGNHAGROOIHMFVEHV5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R/action/storage_attestation","attest_author":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R/action/author_attestation","sign_citation":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R/action/citation_signature","submit_replication":"https://pith.science/pith/MNHI5O2TGNHAGROOIHMFVEHV5R/action/replication_record"}},"created_at":"2026-07-05T11:18:27.559531+00:00","updated_at":"2026-07-05T11:18:27.559531+00:00"}