{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VC4N3FRBGVHKY3OY4ODBEJOTDB","short_pith_number":"pith:VC4N3FRB","schema_version":"1.0","canonical_sha256":"a8b8dd9621354eac6dd8e3861225d3186f5975138b4b04b4483daed648420d2f","source":{"kind":"arxiv","id":"2404.18424","version":3},"attestation_state":"computed","paper":{"title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bevan Koopman, Guido Zuccon, Jimmy Lin, Shengyao Zhuang, Xueguang Ma","submitted_at":"2024-04-29T04:51:30Z","abstract_excerpt":"Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents due to computational costs; and (2) unsupervised contrastive trained dense retrieval methods, which can retrieve relevant documents from the entire corpus but require a large amount of paired text data for contrastive training. In this paper, we propose PromptReps, which combines the advantages of both categories: no need for training and the ability to retri"},"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":"2404.18424","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-04-29T04:51:30Z","cross_cats_sorted":[],"title_canon_sha256":"562288f1766d97b40725ef6452adbddc54c39a89857444364dce50af63eb70ac","abstract_canon_sha256":"d931f6d348d252fe4239c8873829547ec5869b7b0af1389f254e68d90e8b08dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:39.712603Z","signature_b64":"olJQA1oAxSE9HFsFnRosSgXMQxgylNn8Xx6PHjN/H+vD9zTypzzX36i1JdSrj3gWCWYH7xobzttAZYIsXmNDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8b8dd9621354eac6dd8e3861225d3186f5975138b4b04b4483daed648420d2f","last_reissued_at":"2026-07-05T09:22:39.712057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:39.712057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bevan Koopman, Guido Zuccon, Jimmy Lin, Shengyao Zhuang, Xueguang Ma","submitted_at":"2024-04-29T04:51:30Z","abstract_excerpt":"Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents due to computational costs; and (2) unsupervised contrastive trained dense retrieval methods, which can retrieve relevant documents from the entire corpus but require a large amount of paired text data for contrastive training. In this paper, we propose PromptReps, which combines the advantages of both categories: no need for training and the ability to retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18424","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/2404.18424/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":"2404.18424","created_at":"2026-07-05T09:22:39.712123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18424v3","created_at":"2026-07-05T09:22:39.712123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18424","created_at":"2026-07-05T09:22:39.712123+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC4N3FRBGVHK","created_at":"2026-07-05T09:22:39.712123+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC4N3FRBGVHKY3OY","created_at":"2026-07-05T09:22:39.712123+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC4N3FRB","created_at":"2026-07-05T09:22:39.712123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13464","citing_title":"Estimating Commonsense Plausibility through Semantic Shifts","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13415","citing_title":"Attention Grounded Enhancement for Visual Document Retrieval","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB","json":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB.json","graph_json":"https://pith.science/api/pith-number/VC4N3FRBGVHKY3OY4ODBEJOTDB/graph.json","events_json":"https://pith.science/api/pith-number/VC4N3FRBGVHKY3OY4ODBEJOTDB/events.json","paper":"https://pith.science/paper/VC4N3FRB"},"agent_actions":{"view_html":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB","download_json":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB.json","view_paper":"https://pith.science/paper/VC4N3FRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18424&json=true","fetch_graph":"https://pith.science/api/pith-number/VC4N3FRBGVHKY3OY4ODBEJOTDB/graph.json","fetch_events":"https://pith.science/api/pith-number/VC4N3FRBGVHKY3OY4ODBEJOTDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB/action/storage_attestation","attest_author":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB/action/author_attestation","sign_citation":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB/action/citation_signature","submit_replication":"https://pith.science/pith/VC4N3FRBGVHKY3OY4ODBEJOTDB/action/replication_record"}},"created_at":"2026-07-05T09:22:39.712123+00:00","updated_at":"2026-07-05T09:22:39.712123+00:00"}