{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FEP3S3CCWI24X7PBB7IRVWN5B5","short_pith_number":"pith:FEP3S3CC","schema_version":"1.0","canonical_sha256":"291fb96c42b235cbfde10fd11ad9bd0f6a932a9ed4d67ce02a18e6b7b42baaa5","source":{"kind":"arxiv","id":"2110.12764","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Learning for Neural Topic Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Thong Nguyen","submitted_at":"2021-10-25T09:46:26Z","abstract_excerpt":"Recent empirical studies show that adversarial topic models (ATM) can successfully capture semantic patterns of the document by differentiating a document with another dissimilar sample. However, utilizing that discriminative-generative architecture has two important drawbacks: (1) the architecture does not relate similar documents, which has the same document-word distribution of salient words; (2) it restricts the ability to integrate external information, such as sentiments of the document, which has been shown to benefit the training of neural topic model. To address those issues, we revis"},"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":"2110.12764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-25T09:46:26Z","cross_cats_sorted":[],"title_canon_sha256":"9ec4b25e9d2516ad13cba6661ce1c4f96c08cd84561a49d708d654f71944470f","abstract_canon_sha256":"58f2a46301e7eb775491f7d51650aad68ef279a48d2f2fa5372f6379ed33bea5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:23.676071Z","signature_b64":"h56wbvLIwdAGKyDyw5gS23iI0VO2aEyeb8W3Oqxqh/8juxoFlV3P4lowP03XZpxcv/N6aykhAlOE5/uW7GDWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"291fb96c42b235cbfde10fd11ad9bd0f6a932a9ed4d67ce02a18e6b7b42baaa5","last_reissued_at":"2026-07-05T03:25:23.675687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:23.675687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning for Neural Topic Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Thong Nguyen","submitted_at":"2021-10-25T09:46:26Z","abstract_excerpt":"Recent empirical studies show that adversarial topic models (ATM) can successfully capture semantic patterns of the document by differentiating a document with another dissimilar sample. However, utilizing that discriminative-generative architecture has two important drawbacks: (1) the architecture does not relate similar documents, which has the same document-word distribution of salient words; (2) it restricts the ability to integrate external information, such as sentiments of the document, which has been shown to benefit the training of neural topic model. To address those issues, we revis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12764","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/2110.12764/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":"2110.12764","created_at":"2026-07-05T03:25:23.675759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12764v1","created_at":"2026-07-05T03:25:23.675759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12764","created_at":"2026-07-05T03:25:23.675759+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEP3S3CCWI24","created_at":"2026-07-05T03:25:23.675759+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEP3S3CCWI24X7PB","created_at":"2026-07-05T03:25:23.675759+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEP3S3CC","created_at":"2026-07-05T03:25:23.675759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14166","citing_title":"Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5","json":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5.json","graph_json":"https://pith.science/api/pith-number/FEP3S3CCWI24X7PBB7IRVWN5B5/graph.json","events_json":"https://pith.science/api/pith-number/FEP3S3CCWI24X7PBB7IRVWN5B5/events.json","paper":"https://pith.science/paper/FEP3S3CC"},"agent_actions":{"view_html":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5","download_json":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5.json","view_paper":"https://pith.science/paper/FEP3S3CC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12764&json=true","fetch_graph":"https://pith.science/api/pith-number/FEP3S3CCWI24X7PBB7IRVWN5B5/graph.json","fetch_events":"https://pith.science/api/pith-number/FEP3S3CCWI24X7PBB7IRVWN5B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5/action/storage_attestation","attest_author":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5/action/author_attestation","sign_citation":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5/action/citation_signature","submit_replication":"https://pith.science/pith/FEP3S3CCWI24X7PBB7IRVWN5B5/action/replication_record"}},"created_at":"2026-07-05T03:25:23.675759+00:00","updated_at":"2026-07-05T03:25:23.675759+00:00"}