{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4APF45BYRSJXGT7JRFRZU55MFO","short_pith_number":"pith:4APF45BY","schema_version":"1.0","canonical_sha256":"e01e5e74388c93734fe989639a77ac2b945fa1ec14a519acad147abb4c37d899","source":{"kind":"arxiv","id":"2206.00212","version":1},"attestation_state":"computed","paper":{"title":"Negative Sampling for Contrastive Representation Learning: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Jianxun Lian, Ji-Rong Wen, Lanling Xu, Linjun Shou, Ming Gong, Wayne Xin Zhao, Xing Xie","submitted_at":"2022-06-01T03:36:30Z","abstract_excerpt":"The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language processing, computer vision, information retrieval and graph learning. While many research works focus on data augmentations, nonlinear transformations or other certain parts of CRL, the importance of negative sample selection is usually overlooked in literature. In this paper, we provide a systematic review of negative sampling (NS) techniques and discuss how"},"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":"2206.00212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-01T03:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"32caf75d63598faedbadf6d05c2a4df5225d5e14d1ea413bef405b0c1c97b362","abstract_canon_sha256":"b1944f4bf0a0df29c5b0a3e86175f547b29455a28d84af84f8f4af7d755409b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:14.168220Z","signature_b64":"DqhWMX5Dv8MHQu2WHH/tFaveBhHL2+1hs4krPG74S/1pxw7rZDsAETrjZMld4Lw0FXrXi5f4MTFhGy5Gq+PgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01e5e74388c93734fe989639a77ac2b945fa1ec14a519acad147abb4c37d899","last_reissued_at":"2026-07-05T04:28:14.167719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:14.167719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Negative Sampling for Contrastive Representation Learning: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Jianxun Lian, Ji-Rong Wen, Lanling Xu, Linjun Shou, Ming Gong, Wayne Xin Zhao, Xing Xie","submitted_at":"2022-06-01T03:36:30Z","abstract_excerpt":"The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language processing, computer vision, information retrieval and graph learning. While many research works focus on data augmentations, nonlinear transformations or other certain parts of CRL, the importance of negative sample selection is usually overlooked in literature. In this paper, we provide a systematic review of negative sampling (NS) techniques and discuss how"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00212","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/2206.00212/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":"2206.00212","created_at":"2026-07-05T04:28:14.167780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00212v1","created_at":"2026-07-05T04:28:14.167780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00212","created_at":"2026-07-05T04:28:14.167780+00:00"},{"alias_kind":"pith_short_12","alias_value":"4APF45BYRSJX","created_at":"2026-07-05T04:28:14.167780+00:00"},{"alias_kind":"pith_short_16","alias_value":"4APF45BYRSJXGT7J","created_at":"2026-07-05T04:28:14.167780+00:00"},{"alias_kind":"pith_short_8","alias_value":"4APF45BY","created_at":"2026-07-05T04:28:14.167780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19638","citing_title":"MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detection","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19638","citing_title":"MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detection","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19651","citing_title":"Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16836","citing_title":"HYVINT: Intensity-Driven Hypergraph Generation with Variational Embeddings","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11541","citing_title":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18234","citing_title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO","json":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO.json","graph_json":"https://pith.science/api/pith-number/4APF45BYRSJXGT7JRFRZU55MFO/graph.json","events_json":"https://pith.science/api/pith-number/4APF45BYRSJXGT7JRFRZU55MFO/events.json","paper":"https://pith.science/paper/4APF45BY"},"agent_actions":{"view_html":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO","download_json":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO.json","view_paper":"https://pith.science/paper/4APF45BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00212&json=true","fetch_graph":"https://pith.science/api/pith-number/4APF45BYRSJXGT7JRFRZU55MFO/graph.json","fetch_events":"https://pith.science/api/pith-number/4APF45BYRSJXGT7JRFRZU55MFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO/action/storage_attestation","attest_author":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO/action/author_attestation","sign_citation":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO/action/citation_signature","submit_replication":"https://pith.science/pith/4APF45BYRSJXGT7JRFRZU55MFO/action/replication_record"}},"created_at":"2026-07-05T04:28:14.167780+00:00","updated_at":"2026-07-05T04:28:14.167780+00:00"}