{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4G3OSCXIWEVSF425BSG5VVDVXG","short_pith_number":"pith:4G3OSCXI","schema_version":"1.0","canonical_sha256":"e1b6e90ae8b12b22f35d0c8ddad475b9871a71ed0afa5f2a014d84dbe2175747","source":{"kind":"arxiv","id":"2305.19840","version":2},"attestation_state":"computed","paper":{"title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Arkadiusz Janz, Kacper Wo{\\l}owiec, Konrad Wojtasik, Maciej Piasecki, Vadim Shishkin","submitted_at":"2023-05-31T13:29:07Z","abstract_excerpt":"The BEIR dataset is a large, heterogeneous benchmark for Information Retrieval (IR) in zero-shot settings, garnering considerable attention within the research community. However, BEIR and analogous datasets are predominantly restricted to the English language. Our objective is to establish extensive large-scale resources for IR in the Polish language, thereby advancing the research in this NLP area. In this work, inspired by mMARCO and Mr.~TyDi datasets, we translated all accessible open IR datasets into Polish, and we introduced the BEIR-PL benchmark -- a new benchmark which comprises 13 dat"},"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":"2305.19840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-31T13:29:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dc087afae0536e2bcddfff267edfcc63aecb28516ae1211738a721971f3b0245","abstract_canon_sha256":"f864842b81829d0b8b40135b01e17d7601cef186b21e23d488d31c6aecc6ec45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:34.883861Z","signature_b64":"8e7eUxkmLCKvb3mltizPiJp0h5ndzALTduj68JhOWU6b4xE5X5wcObkzBi1/3RLZHZAslSz5U+Oh9OJxK5bgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1b6e90ae8b12b22f35d0c8ddad475b9871a71ed0afa5f2a014d84dbe2175747","last_reissued_at":"2026-07-05T08:19:34.883307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:34.883307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Arkadiusz Janz, Kacper Wo{\\l}owiec, Konrad Wojtasik, Maciej Piasecki, Vadim Shishkin","submitted_at":"2023-05-31T13:29:07Z","abstract_excerpt":"The BEIR dataset is a large, heterogeneous benchmark for Information Retrieval (IR) in zero-shot settings, garnering considerable attention within the research community. However, BEIR and analogous datasets are predominantly restricted to the English language. Our objective is to establish extensive large-scale resources for IR in the Polish language, thereby advancing the research in this NLP area. In this work, inspired by mMARCO and Mr.~TyDi datasets, we translated all accessible open IR datasets into Polish, and we introduced the BEIR-PL benchmark -- a new benchmark which comprises 13 dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19840","kind":"arxiv","version":2},"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/2305.19840/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":"2305.19840","created_at":"2026-07-05T08:19:34.883376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19840v2","created_at":"2026-07-05T08:19:34.883376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19840","created_at":"2026-07-05T08:19:34.883376+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G3OSCXIWEVS","created_at":"2026-07-05T08:19:34.883376+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G3OSCXIWEVSF425","created_at":"2026-07-05T08:19:34.883376+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G3OSCXI","created_at":"2026-07-05T08:19:34.883376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG","json":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG.json","graph_json":"https://pith.science/api/pith-number/4G3OSCXIWEVSF425BSG5VVDVXG/graph.json","events_json":"https://pith.science/api/pith-number/4G3OSCXIWEVSF425BSG5VVDVXG/events.json","paper":"https://pith.science/paper/4G3OSCXI"},"agent_actions":{"view_html":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG","download_json":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG.json","view_paper":"https://pith.science/paper/4G3OSCXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19840&json=true","fetch_graph":"https://pith.science/api/pith-number/4G3OSCXIWEVSF425BSG5VVDVXG/graph.json","fetch_events":"https://pith.science/api/pith-number/4G3OSCXIWEVSF425BSG5VVDVXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG/action/storage_attestation","attest_author":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG/action/author_attestation","sign_citation":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG/action/citation_signature","submit_replication":"https://pith.science/pith/4G3OSCXIWEVSF425BSG5VVDVXG/action/replication_record"}},"created_at":"2026-07-05T08:19:34.883376+00:00","updated_at":"2026-07-05T08:19:34.883376+00:00"}