{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2Z37R66LRVULQZNW4YRU4HJGD6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3be82d6775ce53a8cc50de11a918bf3c6887f4465475500b81ef1b2ae81e5cbd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-01-04T20:58:43Z","title_canon_sha256":"109b5c8cae0fe477cff55285804177aac3d40d069a53c06b451ad2500a40db89"},"schema_version":"1.0","source":{"id":"2301.01820","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01820","created_at":"2026-07-05T06:14:23Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01820v4","created_at":"2026-07-05T06:14:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01820","created_at":"2026-07-05T06:14:23Z"},{"alias_kind":"pith_short_12","alias_value":"2Z37R66LRVUL","created_at":"2026-07-05T06:14:23Z"},{"alias_kind":"pith_short_16","alias_value":"2Z37R66LRVULQZNW","created_at":"2026-07-05T06:14:23Z"},{"alias_kind":"pith_short_8","alias_value":"2Z37R66L","created_at":"2026-07-05T06:14:23Z"}],"graph_snapshots":[{"event_id":"sha256:c71e02d840e233453f61c5200c1e85343678345660688be2d92c3a00e3d11d12","target":"graph","created_at":"2026-07-05T06:14:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.01820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, InPars introduced a method to efficiently use large language models (LLMs) in information retrieval tasks: via few-shot examples, an LLM is induced to generate relevant queries for documents. These synthetic query-document pairs can then be used to train a retriever. However, InPars and, more recently, Promptagator, rely on proprietary LLMs such as GPT-3 and FLAN to generate such datasets. In this work we introduce InPars-v2, a dataset generator that uses open-source LLMs and existing powerful rerankers to select synthetic query-document pairs for training. A simple BM25 retrieval pi","authors_text":"Hugo Abonizio, Jakub Zavrel, Luiz Bonifacio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-01-04T20:58:43Z","title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01820","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:243d76badac10a5b11112a5b54ecd6185c8b316b950641c3de6378c465bc21d9","target":"record","created_at":"2026-07-05T06:14:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3be82d6775ce53a8cc50de11a918bf3c6887f4465475500b81ef1b2ae81e5cbd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-01-04T20:58:43Z","title_canon_sha256":"109b5c8cae0fe477cff55285804177aac3d40d069a53c06b451ad2500a40db89"},"schema_version":"1.0","source":{"id":"2301.01820","kind":"arxiv","version":4}},"canonical_sha256":"d677f8fbcb8d68b865b6e6234e1d261fa8034bd3bcc24e82db8faee40e9b11ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d677f8fbcb8d68b865b6e6234e1d261fa8034bd3bcc24e82db8faee40e9b11ef","first_computed_at":"2026-07-05T06:14:23.562123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:23.562123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N8qdMRtAtbQPbX1CTMQS17tyl97YzXi9TsY05JwcE40F5V6ikmDKLZK3YS+lPawe04XrYagXJnNSMG16HhkiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:23.562627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.01820","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243d76badac10a5b11112a5b54ecd6185c8b316b950641c3de6378c465bc21d9","sha256:c71e02d840e233453f61c5200c1e85343678345660688be2d92c3a00e3d11d12"],"state_sha256":"45eaffad03ccd962ff462565d2b5904d25b2c20fa0c6f79541530c0500ee670c"}