{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WPAGGOYU2RUOHMB3VH3BOAIKPE","short_pith_number":"pith:WPAGGOYU","canonical_record":{"source":{"id":"2307.04601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-07-10T14:39:43Z","cross_cats_sorted":[],"title_canon_sha256":"75f1644edd81f1396efbac30895181d9007a06cff452101883a879a81bff8c1c","abstract_canon_sha256":"5ab7af716a48b8a7e51ea46b433458db3e5fb664ae16352c56cb6d2c4c87cbab"},"schema_version":"1.0"},"canonical_sha256":"b3c0633b14d468e3b03ba9f617010a790b72511c493d13882066fecb286d5ac1","source":{"kind":"arxiv","id":"2307.04601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04601","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04601v1","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04601","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"WPAGGOYU2RUO","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"WPAGGOYU2RUOHMB3","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"WPAGGOYU","created_at":"2026-07-05T06:29:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WPAGGOYU2RUOHMB3VH3BOAIKPE","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-07-10T14:39:43Z","cross_cats_sorted":[],"title_canon_sha256":"75f1644edd81f1396efbac30895181d9007a06cff452101883a879a81bff8c1c","abstract_canon_sha256":"5ab7af716a48b8a7e51ea46b433458db3e5fb664ae16352c56cb6d2c4c87cbab"},"schema_version":"1.0"},"canonical_sha256":"b3c0633b14d468e3b03ba9f617010a790b72511c493d13882066fecb286d5ac1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:15.443702Z","signature_b64":"AfIPvAmRpnYc85a9JCYy2BQ8K5YdXKwYWhmen/C2AQqQcZ5yzqsLja9A1iwtzWxiKboo/jdEi2ZrJvtiuDwzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3c0633b14d468e3b03ba9f617010a790b72511c493d13882066fecb286d5ac1","last_reissued_at":"2026-07-05T06:29:15.443289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:15.443289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04601","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:29:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STtdzB9z5xVTCuyfuVkiTzyZoJ5qVcbohmyM2XNIiiOETLFRVL0uzqdsj+1UQPadUNZ86WHD4tngQym6gHYyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:33:04.982935Z"},"content_sha256":"9c92011c690f5036670de6dec9871cc05bc59176d36e77d5096f2db5e523bb23","schema_version":"1.0","event_id":"sha256:9c92011c690f5036670de6dec9871cc05bc59176d36e77d5096f2db5e523bb23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WPAGGOYU2RUOHMB3VH3BOAIKPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hugo Abonizio, Jakub Zavrel, Luiz Bonifacio, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2023-07-10T14:39:43Z","abstract_excerpt":"Recent work has explored Large Language Models (LLMs) to overcome the lack of training data for Information Retrieval (IR) tasks. The generalization abilities of these models have enabled the creation of synthetic in-domain data by providing instructions and a few examples on a prompt. InPars and Promptagator have pioneered this approach and both methods have demonstrated the potential of using LLMs as synthetic data generators for IR tasks. This makes them an attractive solution for IR tasks that suffer from a lack of annotated data. However, the reproducibility of these methods was limited, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04601","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/2307.04601/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":"2026-07-05T06:29:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMk2VCHIecFz7CqDrSJeyawooxWtYsnk5PFmqV6AmjGw/m77B2cGjOzVLFqV6TSNyp4sfez3m1T6znE1rAbtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:33:04.983564Z"},"content_sha256":"36078b3caceb7e7a8eae1b25ecb0c9034c45e851f169f90ee4ca45119892b685","schema_version":"1.0","event_id":"sha256:36078b3caceb7e7a8eae1b25ecb0c9034c45e851f169f90ee4ca45119892b685"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE/bundle.json","state_url":"https://pith.science/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE/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":"2026-08-01T11:33:04Z","links":{"resolver":"https://pith.science/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE","bundle":"https://pith.science/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE/bundle.json","state":"https://pith.science/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WPAGGOYU2RUOHMB3VH3BOAIKPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WPAGGOYU2RUOHMB3VH3BOAIKPE","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":"5ab7af716a48b8a7e51ea46b433458db3e5fb664ae16352c56cb6d2c4c87cbab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-07-10T14:39:43Z","title_canon_sha256":"75f1644edd81f1396efbac30895181d9007a06cff452101883a879a81bff8c1c"},"schema_version":"1.0","source":{"id":"2307.04601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04601","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04601v1","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04601","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"WPAGGOYU2RUO","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"WPAGGOYU2RUOHMB3","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"WPAGGOYU","created_at":"2026-07-05T06:29:15Z"}],"graph_snapshots":[{"event_id":"sha256:36078b3caceb7e7a8eae1b25ecb0c9034c45e851f169f90ee4ca45119892b685","target":"graph","created_at":"2026-07-05T06:29:15Z","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/2307.04601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has explored Large Language Models (LLMs) to overcome the lack of training data for Information Retrieval (IR) tasks. The generalization abilities of these models have enabled the creation of synthetic in-domain data by providing instructions and a few examples on a prompt. InPars and Promptagator have pioneered this approach and both methods have demonstrated the potential of using LLMs as synthetic data generators for IR tasks. This makes them an attractive solution for IR tasks that suffer from a lack of annotated data. However, the reproducibility of these methods was limited, ","authors_text":"Hugo Abonizio, Jakub Zavrel, Luiz Bonifacio, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-07-10T14:39:43Z","title":"InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04601","kind":"arxiv","version":1},"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":"sha256:9c92011c690f5036670de6dec9871cc05bc59176d36e77d5096f2db5e523bb23","target":"record","created_at":"2026-07-05T06:29:15Z","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":"5ab7af716a48b8a7e51ea46b433458db3e5fb664ae16352c56cb6d2c4c87cbab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-07-10T14:39:43Z","title_canon_sha256":"75f1644edd81f1396efbac30895181d9007a06cff452101883a879a81bff8c1c"},"schema_version":"1.0","source":{"id":"2307.04601","kind":"arxiv","version":1}},"canonical_sha256":"b3c0633b14d468e3b03ba9f617010a790b72511c493d13882066fecb286d5ac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3c0633b14d468e3b03ba9f617010a790b72511c493d13882066fecb286d5ac1","first_computed_at":"2026-07-05T06:29:15.443289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:15.443289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfIPvAmRpnYc85a9JCYy2BQ8K5YdXKwYWhmen/C2AQqQcZ5yzqsLja9A1iwtzWxiKboo/jdEi2ZrJvtiuDwzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:15.443702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c92011c690f5036670de6dec9871cc05bc59176d36e77d5096f2db5e523bb23","sha256:36078b3caceb7e7a8eae1b25ecb0c9034c45e851f169f90ee4ca45119892b685"],"state_sha256":"f324b11a9af93e5ae134d3a56151805091e87b47111522aa1c13cd325a89d667"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UWrOh5jaSr2up3uYz0FmIAX6f+QWu1YHkZrTlc8YPwMQLiOYu2FXfoqYDBse3trhaQ2pwRfzGrkqNGfKY7JAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T11:33:04.986762Z","bundle_sha256":"bf3b6507b7c16d9814b5994a1db9605e8d2f6877d0ca5102d826ed19ee9077db"}}