{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LOFFQWE4EOKK5U5MAG5753EWJB","short_pith_number":"pith:LOFFQWE4","schema_version":"1.0","canonical_sha256":"5b8a58589c2394aed3ac01bbfeec964864f419b5391f5faf66c568ffd1d0d856","source":{"kind":"arxiv","id":"2202.05144","version":1},"attestation_state":"computed","paper":{"title":"InPars: Data Augmentation for Information Retrieval using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Abonizio, Luiz Bonifacio, Marzieh Fadaee, Rodrigo Nogueira","submitted_at":"2022-02-10T16:52:45Z","abstract_excerpt":"The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO dataset, whose scale and diversity has enabled zero-shot transfer learning to various tasks. However, not all IR tasks and domains can benefit from one single dataset equally. Extensive research in various NLP tasks has shown that using domain-specific training data, as opposed to a general-purpose one, improves the performance of neural models. In this work, we harness the few-shot capabilities of large pretrained langu"},"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":"2202.05144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-10T16:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"b01c4474c27d95be84065b7741175a1d15dced74605b44eb26962863a6661c87","abstract_canon_sha256":"ef568ac89d250316b2a48dd8702c5e2195c379459f6ea0b0ef49678181c8334a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:57.725169Z","signature_b64":"W/9zlj2plCvXn/vILoGFo/b7aNr69FYQA/nQvBN4xgl1FvVnfc0hi/1irSq1/G3QUxcvOUkDOqVqgjpCaiIlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8a58589c2394aed3ac01bbfeec964864f419b5391f5faf66c568ffd1d0d856","last_reissued_at":"2026-07-05T03:55:57.724685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:57.724685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InPars: Data Augmentation for Information Retrieval using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Abonizio, Luiz Bonifacio, Marzieh Fadaee, Rodrigo Nogueira","submitted_at":"2022-02-10T16:52:45Z","abstract_excerpt":"The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO dataset, whose scale and diversity has enabled zero-shot transfer learning to various tasks. However, not all IR tasks and domains can benefit from one single dataset equally. Extensive research in various NLP tasks has shown that using domain-specific training data, as opposed to a general-purpose one, improves the performance of neural models. In this work, we harness the few-shot capabilities of large pretrained langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05144","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/2202.05144/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":"2202.05144","created_at":"2026-07-05T03:55:57.724746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05144v1","created_at":"2026-07-05T03:55:57.724746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05144","created_at":"2026-07-05T03:55:57.724746+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOFFQWE4EOKK","created_at":"2026-07-05T03:55:57.724746+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOFFQWE4EOKK5U5M","created_at":"2026-07-05T03:55:57.724746+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOFFQWE4","created_at":"2026-07-05T03:55:57.724746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20369","citing_title":"CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32002","citing_title":"Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25486","citing_title":"RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance","ref_index":10,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00709","citing_title":"RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21812","citing_title":"Bridging the Cold-Start Gap: LLM-Powered Synthetic Data Generation for Natural Language Search at Airbnb","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22435","citing_title":"Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":139,"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":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":4,"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":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB","json":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB.json","graph_json":"https://pith.science/api/pith-number/LOFFQWE4EOKK5U5MAG5753EWJB/graph.json","events_json":"https://pith.science/api/pith-number/LOFFQWE4EOKK5U5MAG5753EWJB/events.json","paper":"https://pith.science/paper/LOFFQWE4"},"agent_actions":{"view_html":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB","download_json":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB.json","view_paper":"https://pith.science/paper/LOFFQWE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05144&json=true","fetch_graph":"https://pith.science/api/pith-number/LOFFQWE4EOKK5U5MAG5753EWJB/graph.json","fetch_events":"https://pith.science/api/pith-number/LOFFQWE4EOKK5U5MAG5753EWJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB/action/storage_attestation","attest_author":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB/action/author_attestation","sign_citation":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB/action/citation_signature","submit_replication":"https://pith.science/pith/LOFFQWE4EOKK5U5MAG5753EWJB/action/replication_record"}},"created_at":"2026-07-05T03:55:57.724746+00:00","updated_at":"2026-07-05T03:55:57.724746+00:00"}