{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WBQYXAMUHYCSM45QWSBJ7LP2HV","short_pith_number":"pith:WBQYXAMU","schema_version":"1.0","canonical_sha256":"b0618b81943e052673b0b4829fadfa3d5077e4d15067951606b7f103691b782f","source":{"kind":"arxiv","id":"2212.10496","version":1},"attestation_state":"computed","paper":{"title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Jamie Callan, Jimmy Lin, Luyu Gao, Xueguang Ma","submitted_at":"2022-12-20T18:09:52Z","abstract_excerpt":"While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false detail"},"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":"2212.10496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-20T18:09:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af2dbb1bf908b7309a3e2f8cca9a07e08ca3ca6d0d62f26af54b1f9e2750ec2e","abstract_canon_sha256":"385b4a303c9c276dbc8f56f36e29b140fdf74215b6ebcfaac21fafff78effb66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:08.138428Z","signature_b64":"XsLQFAYJKOBy06kaOrvagIZy1IDebyxp05FnKrw5ZBfXVOy/DAK//lC3j2HcsVnkLo2ToWWc6ZrErtt6FrwgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0618b81943e052673b0b4829fadfa3d5077e4d15067951606b7f103691b782f","last_reissued_at":"2026-07-05T05:27:08.138015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:08.138015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Jamie Callan, Jimmy Lin, Luyu Gao, Xueguang Ma","submitted_at":"2022-12-20T18:09:52Z","abstract_excerpt":"While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false detail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10496","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/2212.10496/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":"2212.10496","created_at":"2026-07-05T05:27:08.138069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10496v1","created_at":"2026-07-05T05:27:08.138069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10496","created_at":"2026-07-05T05:27:08.138069+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBQYXAMUHYCS","created_at":"2026-07-05T05:27:08.138069+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBQYXAMUHYCSM45Q","created_at":"2026-07-05T05:27:08.138069+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBQYXAMU","created_at":"2026-07-05T05:27:08.138069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27291","citing_title":"Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02387","citing_title":"Bringing Agentic Search to Earth Observation Data Discovery","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08151","citing_title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01240","citing_title":"Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16326","citing_title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16394","citing_title":"A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05779","citing_title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03989","citing_title":"An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05657","citing_title":"Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09492","citing_title":"Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07201","citing_title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07079","citing_title":"MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20174","citing_title":"Lever: Inference-Time Policy Reuse under Support Constraints","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03989","citing_title":"An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV","json":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV.json","graph_json":"https://pith.science/api/pith-number/WBQYXAMUHYCSM45QWSBJ7LP2HV/graph.json","events_json":"https://pith.science/api/pith-number/WBQYXAMUHYCSM45QWSBJ7LP2HV/events.json","paper":"https://pith.science/paper/WBQYXAMU"},"agent_actions":{"view_html":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV","download_json":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV.json","view_paper":"https://pith.science/paper/WBQYXAMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10496&json=true","fetch_graph":"https://pith.science/api/pith-number/WBQYXAMUHYCSM45QWSBJ7LP2HV/graph.json","fetch_events":"https://pith.science/api/pith-number/WBQYXAMUHYCSM45QWSBJ7LP2HV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV/action/storage_attestation","attest_author":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV/action/author_attestation","sign_citation":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV/action/citation_signature","submit_replication":"https://pith.science/pith/WBQYXAMUHYCSM45QWSBJ7LP2HV/action/replication_record"}},"created_at":"2026-07-05T05:27:08.138069+00:00","updated_at":"2026-07-05T05:27:08.138069+00:00"}