{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UDHVWF52CJQEM2R2ROXQDMFOMQ","short_pith_number":"pith:UDHVWF52","schema_version":"1.0","canonical_sha256":"a0cf5b17ba1260466a3a8baf01b0ae643a024cf2116dea9f42024d0dba882fbe","source":{"kind":"arxiv","id":"2306.01481","version":1},"attestation_state":"computed","paper":{"title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akintunde Oladipo, Aleksandra Piktus, Christopher Akiki, Hailey Schoelkopf, Jimmy Lin, Martin Potthast, Odunayo Ogundepo, Stella Biderman, Xinyu Zhang","submitted_at":"2023-06-02T12:09:59Z","abstract_excerpt":"Noticing the urgent need to provide tools for fast and user-friendly qualitative analysis of large-scale textual corpora of the modern NLP, we propose to turn to the mature and well-tested methods from the domain of Information Retrieval (IR) - a research field with a long history of tackling TB-scale document collections. We discuss how Pyserini - a widely used toolkit for reproducible IR research can be integrated with the Hugging Face ecosystem of open-source AI libraries and artifacts. We leverage the existing functionalities of both platforms while proposing novel features further facilit"},"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":"2306.01481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T12:09:59Z","cross_cats_sorted":[],"title_canon_sha256":"c1091fdb0ab8156e9febd2addb09b4851e8df459ebe1cb77300be18e540a4dce","abstract_canon_sha256":"bc22f464dcf94e83279447a88a95eac24aec1efba31127ff51e8b8c98b575a5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:54.752022Z","signature_b64":"139RFXI5YDvwKWx3VQbZPLaQoEU6KKkZoiPatqtuSg3/5m0rlSvljkH+kBsl2z9osvOPhXEK9Uhf7oXzr07jAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0cf5b17ba1260466a3a8baf01b0ae643a024cf2116dea9f42024d0dba882fbe","last_reissued_at":"2026-07-05T06:16:54.751679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:54.751679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akintunde Oladipo, Aleksandra Piktus, Christopher Akiki, Hailey Schoelkopf, Jimmy Lin, Martin Potthast, Odunayo Ogundepo, Stella Biderman, Xinyu Zhang","submitted_at":"2023-06-02T12:09:59Z","abstract_excerpt":"Noticing the urgent need to provide tools for fast and user-friendly qualitative analysis of large-scale textual corpora of the modern NLP, we propose to turn to the mature and well-tested methods from the domain of Information Retrieval (IR) - a research field with a long history of tackling TB-scale document collections. We discuss how Pyserini - a widely used toolkit for reproducible IR research can be integrated with the Hugging Face ecosystem of open-source AI libraries and artifacts. We leverage the existing functionalities of both platforms while proposing novel features further facilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01481","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/2306.01481/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":"2306.01481","created_at":"2026-07-05T06:16:54.751735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01481v1","created_at":"2026-07-05T06:16:54.751735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01481","created_at":"2026-07-05T06:16:54.751735+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDHVWF52CJQE","created_at":"2026-07-05T06:16:54.751735+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDHVWF52CJQEM2R2","created_at":"2026-07-05T06:16:54.751735+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDHVWF52","created_at":"2026-07-05T06:16:54.751735+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/UDHVWF52CJQEM2R2ROXQDMFOMQ","json":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ.json","graph_json":"https://pith.science/api/pith-number/UDHVWF52CJQEM2R2ROXQDMFOMQ/graph.json","events_json":"https://pith.science/api/pith-number/UDHVWF52CJQEM2R2ROXQDMFOMQ/events.json","paper":"https://pith.science/paper/UDHVWF52"},"agent_actions":{"view_html":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ","download_json":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ.json","view_paper":"https://pith.science/paper/UDHVWF52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01481&json=true","fetch_graph":"https://pith.science/api/pith-number/UDHVWF52CJQEM2R2ROXQDMFOMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UDHVWF52CJQEM2R2ROXQDMFOMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ/action/storage_attestation","attest_author":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ/action/author_attestation","sign_citation":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ/action/citation_signature","submit_replication":"https://pith.science/pith/UDHVWF52CJQEM2R2ROXQDMFOMQ/action/replication_record"}},"created_at":"2026-07-05T06:16:54.751735+00:00","updated_at":"2026-07-05T06:16:54.751735+00:00"}