{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VB3HR7774ZLFDOEPXL6GMPJSML","short_pith_number":"pith:VB3HR777","schema_version":"1.0","canonical_sha256":"a87678ffffe65651b88fbafc663d3262cbdd4faf64c20c0341149883dab83fc8","source":{"kind":"arxiv","id":"2204.04937","version":1},"attestation_state":"computed","paper":{"title":"Assessment of Massively Multilingual Sentiment Classifiers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Krzysztof Rajda, {\\L}ukasz Augustyniak, Marcin Gruza, Piotr Gramacki, Szymon Wo\\'zniak, Tomasz Kajdanowicz","submitted_at":"2022-04-11T08:22:05Z","abstract_excerpt":"Models are increasing in size and complexity in the hunt for SOTA. But what if those 2\\% increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included "},"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":"2204.04937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T08:22:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"34a3b048fcbf35278b277add31dbebf09b87d538b8be84f318b398060071c55f","abstract_canon_sha256":"cdac321d988f456b439278efdd89ce6d0c7b43c549e055a4b265efd82dc4a1a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:15.761114Z","signature_b64":"c9SQwS9iqNX/0Uux9/5Kz6sW9zP8zNXvgXoQOr2A5IMppzEiTzqxmhc4+s6Ixw70+IibblAyY/QyiT5tALNdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a87678ffffe65651b88fbafc663d3262cbdd4faf64c20c0341149883dab83fc8","last_reissued_at":"2026-07-05T04:13:15.760728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:15.760728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessment of Massively Multilingual Sentiment Classifiers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Krzysztof Rajda, {\\L}ukasz Augustyniak, Marcin Gruza, Piotr Gramacki, Szymon Wo\\'zniak, Tomasz Kajdanowicz","submitted_at":"2022-04-11T08:22:05Z","abstract_excerpt":"Models are increasing in size and complexity in the hunt for SOTA. But what if those 2\\% increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04937","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/2204.04937/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":"2204.04937","created_at":"2026-07-05T04:13:15.760789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04937v1","created_at":"2026-07-05T04:13:15.760789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04937","created_at":"2026-07-05T04:13:15.760789+00:00"},{"alias_kind":"pith_short_12","alias_value":"VB3HR7774ZLF","created_at":"2026-07-05T04:13:15.760789+00:00"},{"alias_kind":"pith_short_16","alias_value":"VB3HR7774ZLFDOEP","created_at":"2026-07-05T04:13:15.760789+00:00"},{"alias_kind":"pith_short_8","alias_value":"VB3HR777","created_at":"2026-07-05T04:13:15.760789+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/VB3HR7774ZLFDOEPXL6GMPJSML","json":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML.json","graph_json":"https://pith.science/api/pith-number/VB3HR7774ZLFDOEPXL6GMPJSML/graph.json","events_json":"https://pith.science/api/pith-number/VB3HR7774ZLFDOEPXL6GMPJSML/events.json","paper":"https://pith.science/paper/VB3HR777"},"agent_actions":{"view_html":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML","download_json":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML.json","view_paper":"https://pith.science/paper/VB3HR777","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04937&json=true","fetch_graph":"https://pith.science/api/pith-number/VB3HR7774ZLFDOEPXL6GMPJSML/graph.json","fetch_events":"https://pith.science/api/pith-number/VB3HR7774ZLFDOEPXL6GMPJSML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML/action/storage_attestation","attest_author":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML/action/author_attestation","sign_citation":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML/action/citation_signature","submit_replication":"https://pith.science/pith/VB3HR7774ZLFDOEPXL6GMPJSML/action/replication_record"}},"created_at":"2026-07-05T04:13:15.760789+00:00","updated_at":"2026-07-05T04:13:15.760789+00:00"}