{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UDHVWF52CJQEM2R2ROXQDMFOMQ","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":"bc22f464dcf94e83279447a88a95eac24aec1efba31127ff51e8b8c98b575a5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T12:09:59Z","title_canon_sha256":"c1091fdb0ab8156e9febd2addb09b4851e8df459ebe1cb77300be18e540a4dce"},"schema_version":"1.0","source":{"id":"2306.01481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01481","created_at":"2026-07-05T06:16:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01481v1","created_at":"2026-07-05T06:16:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01481","created_at":"2026-07-05T06:16:54Z"},{"alias_kind":"pith_short_12","alias_value":"UDHVWF52CJQE","created_at":"2026-07-05T06:16:54Z"},{"alias_kind":"pith_short_16","alias_value":"UDHVWF52CJQEM2R2","created_at":"2026-07-05T06:16:54Z"},{"alias_kind":"pith_short_8","alias_value":"UDHVWF52","created_at":"2026-07-05T06:16:54Z"}],"graph_snapshots":[{"event_id":"sha256:7c7fc91f718cf50824469960e0774891d962c292dcabff15a58012356f67acec","target":"graph","created_at":"2026-07-05T06:16:54Z","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/2306.01481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akintunde Oladipo, Aleksandra Piktus, Christopher Akiki, Hailey Schoelkopf, Jimmy Lin, Martin Potthast, Odunayo Ogundepo, Stella Biderman, Xinyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T12:09:59Z","title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01481","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:fec10db73c18a4dc49ceddf867c922dc8ea2cf9ce2b37044798721e2213ee99a","target":"record","created_at":"2026-07-05T06:16:54Z","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":"bc22f464dcf94e83279447a88a95eac24aec1efba31127ff51e8b8c98b575a5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T12:09:59Z","title_canon_sha256":"c1091fdb0ab8156e9febd2addb09b4851e8df459ebe1cb77300be18e540a4dce"},"schema_version":"1.0","source":{"id":"2306.01481","kind":"arxiv","version":1}},"canonical_sha256":"a0cf5b17ba1260466a3a8baf01b0ae643a024cf2116dea9f42024d0dba882fbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0cf5b17ba1260466a3a8baf01b0ae643a024cf2116dea9f42024d0dba882fbe","first_computed_at":"2026-07-05T06:16:54.751679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:54.751679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"139RFXI5YDvwKWx3VQbZPLaQoEU6KKkZoiPatqtuSg3/5m0rlSvljkH+kBsl2z9osvOPhXEK9Uhf7oXzr07jAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:54.752022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fec10db73c18a4dc49ceddf867c922dc8ea2cf9ce2b37044798721e2213ee99a","sha256:7c7fc91f718cf50824469960e0774891d962c292dcabff15a58012356f67acec"],"state_sha256":"30d6195de52db110cf9cf62271d1ff4e816e22a7955610219d93ce4741c31405"}