{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2Z37R66LRVULQZNW4YRU4HJGD6","short_pith_number":"pith:2Z37R66L","canonical_record":{"source":{"id":"2301.01820","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-01-04T20:58:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"109b5c8cae0fe477cff55285804177aac3d40d069a53c06b451ad2500a40db89","abstract_canon_sha256":"3be82d6775ce53a8cc50de11a918bf3c6887f4465475500b81ef1b2ae81e5cbd"},"schema_version":"1.0"},"canonical_sha256":"d677f8fbcb8d68b865b6e6234e1d261fa8034bd3bcc24e82db8faee40e9b11ef","source":{"kind":"arxiv","id":"2301.01820","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2Z37R66LRVULQZNW4YRU4HJGD6","target":"record","payload":{"canonical_record":{"source":{"id":"2301.01820","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-01-04T20:58:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"109b5c8cae0fe477cff55285804177aac3d40d069a53c06b451ad2500a40db89","abstract_canon_sha256":"3be82d6775ce53a8cc50de11a918bf3c6887f4465475500b81ef1b2ae81e5cbd"},"schema_version":"1.0"},"canonical_sha256":"d677f8fbcb8d68b865b6e6234e1d261fa8034bd3bcc24e82db8faee40e9b11ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:23.562627Z","signature_b64":"N8qdMRtAtbQPbX1CTMQS17tyl97YzXi9TsY05JwcE40F5V6ikmDKLZK3YS+lPawe04XrYagXJnNSMG16HhkiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d677f8fbcb8d68b865b6e6234e1d261fa8034bd3bcc24e82db8faee40e9b11ef","last_reissued_at":"2026-07-05T06:14:23.562123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:23.562123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.01820","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q1cR1cZVSE8llYjKGes9vxpuQtXeZVYtc/sR5sMc9td97sCO0l9zNeCTKniOwo4MZgDjzo2lsMIHcKLd5j53CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:15:07.695047Z"},"content_sha256":"243d76badac10a5b11112a5b54ecd6185c8b316b950641c3de6378c465bc21d9","schema_version":"1.0","event_id":"sha256:243d76badac10a5b11112a5b54ecd6185c8b316b950641c3de6378c465bc21d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2Z37R66LRVULQZNW4YRU4HJGD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Hugo Abonizio, Jakub Zavrel, Luiz Bonifacio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2023-01-04T20:58:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01820","kind":"arxiv","version":4},"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/2301.01820/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"trxBBZTn5mRi0o2w7rExqf8ihifhuZfjflxmPUE4NR21hheApvBTC8pSPdheI2gysIrn5YdSY688G7XcYYQHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:15:07.695447Z"},"content_sha256":"c71e02d840e233453f61c5200c1e85343678345660688be2d92c3a00e3d11d12","schema_version":"1.0","event_id":"sha256:c71e02d840e233453f61c5200c1e85343678345660688be2d92c3a00e3d11d12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Z37R66LRVULQZNW4YRU4HJGD6/bundle.json","state_url":"https://pith.science/pith/2Z37R66LRVULQZNW4YRU4HJGD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Z37R66LRVULQZNW4YRU4HJGD6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T07:15:07Z","links":{"resolver":"https://pith.science/pith/2Z37R66LRVULQZNW4YRU4HJGD6","bundle":"https://pith.science/pith/2Z37R66LRVULQZNW4YRU4HJGD6/bundle.json","state":"https://pith.science/pith/2Z37R66LRVULQZNW4YRU4HJGD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Z37R66LRVULQZNW4YRU4HJGD6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTWBLbgSM0Uot+kF6gE/+OF8SAcjxSx12Yc2XwyPvD/sRO4WK+FOJzZTXjw0V+LNq2cXJIoMEocIB3rZvqPaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:15:07.698353Z","bundle_sha256":"aef46c8f4f26d44f1c16a80403e762311e83b6d1b28d4cd9353ee6e6fcba3bf1"}}