{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7TLLTEKWVHYVX2FMUTHQDATPYW","short_pith_number":"pith:7TLLTEKW","schema_version":"1.0","canonical_sha256":"fcd6b99156a9f15be8aca4cf01826fc5a6dcd8b31ec59845609d72cc98f08df2","source":{"kind":"arxiv","id":"2209.11755","version":1},"attestation_state":"computed","paper":{"title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anton Bakalov, Jianmo Ni, Ji Ma, Jing Lu, Keith B. Hall, Kelvin Guu, Ming-Wei Chang, Vincent Y. Zhao, Yi Luan, Zhuyun Dai","submitted_at":"2022-09-23T17:59:06Z","abstract_excerpt":"Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, this overlooks the fact that there are many diverse and unique retrieval tasks, each targeting different search intents, queries, and search domains. In this paper, we suggest to work on Few-shot Dense Retrieval, a setting where each task comes with a short description and a few examples. To amplify the power "},"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":"2209.11755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-23T17:59:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"35ce441b8f85d7691c63acc24ef04fe4e21d9b0dc3965b010627fb2be11e5587","abstract_canon_sha256":"86c592ebc013c48add0abdf1bab8bac6843c74d0c52f1792b1d3931bc0dbc950"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:25.617967Z","signature_b64":"IbRtcALVcP3PKu4OXxtq1bm40TcuuW9yh85q4kQYD10JrT6sY+7v8aQ1bk0xy3TIIy73ILydxcBskJouYYcEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd6b99156a9f15be8aca4cf01826fc5a6dcd8b31ec59845609d72cc98f08df2","last_reissued_at":"2026-07-05T05:00:25.617471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:25.617471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anton Bakalov, Jianmo Ni, Ji Ma, Jing Lu, Keith B. Hall, Kelvin Guu, Ming-Wei Chang, Vincent Y. Zhao, Yi Luan, Zhuyun Dai","submitted_at":"2022-09-23T17:59:06Z","abstract_excerpt":"Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, this overlooks the fact that there are many diverse and unique retrieval tasks, each targeting different search intents, queries, and search domains. In this paper, we suggest to work on Few-shot Dense Retrieval, a setting where each task comes with a short description and a few examples. To amplify the power "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11755","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/2209.11755/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":"2209.11755","created_at":"2026-07-05T05:00:25.617539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11755v1","created_at":"2026-07-05T05:00:25.617539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11755","created_at":"2026-07-05T05:00:25.617539+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TLLTEKWVHYV","created_at":"2026-07-05T05:00:25.617539+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TLLTEKWVHYVX2FM","created_at":"2026-07-05T05:00:25.617539+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TLLTEKW","created_at":"2026-07-05T05:00:25.617539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32002","citing_title":"Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31575","citing_title":"SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2312.02724","citing_title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03676","citing_title":"Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11272","citing_title":"Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25142","citing_title":"UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11092","citing_title":"ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense Retrieval","ref_index":8,"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":5,"is_internal_anchor":false},{"citing_arxiv_id":"2212.03533","citing_title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW","json":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW.json","graph_json":"https://pith.science/api/pith-number/7TLLTEKWVHYVX2FMUTHQDATPYW/graph.json","events_json":"https://pith.science/api/pith-number/7TLLTEKWVHYVX2FMUTHQDATPYW/events.json","paper":"https://pith.science/paper/7TLLTEKW"},"agent_actions":{"view_html":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW","download_json":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW.json","view_paper":"https://pith.science/paper/7TLLTEKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11755&json=true","fetch_graph":"https://pith.science/api/pith-number/7TLLTEKWVHYVX2FMUTHQDATPYW/graph.json","fetch_events":"https://pith.science/api/pith-number/7TLLTEKWVHYVX2FMUTHQDATPYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW/action/storage_attestation","attest_author":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW/action/author_attestation","sign_citation":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW/action/citation_signature","submit_replication":"https://pith.science/pith/7TLLTEKWVHYVX2FMUTHQDATPYW/action/replication_record"}},"created_at":"2026-07-05T05:00:25.617539+00:00","updated_at":"2026-07-05T05:00:25.617539+00:00"}