{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PT5TP6U66VPMSYJB4WYBSWYNLE","short_pith_number":"pith:PT5TP6U6","schema_version":"1.0","canonical_sha256":"7cfb37fa9ef55ec96121e5b0195b0d59116e12a6b6354c80db6c64684eb4539d","source":{"kind":"arxiv","id":"2310.14757","version":1},"attestation_state":"computed","paper":{"title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asahi Ushio, Dimosthenis Antypas, Francesco Barbieri, Jiaxin Pei, Jose Camacho-Collados, Kiamehr Rezaee, Leonardo Neves, Luis Espinosa-Anke","submitted_at":"2023-10-23T09:48:25Z","abstract_excerpt":"Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our result"},"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":"2310.14757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T09:48:25Z","cross_cats_sorted":[],"title_canon_sha256":"489023da5807ebd39c0eda014f2d7bb31851cb42f727444f8ab088f053793da1","abstract_canon_sha256":"da9fa31d7fb3ba16a4e02341e0c30d5ad0f25065815659aec23b41afc48f8120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:49.444660Z","signature_b64":"t8z3IL3EUGiROj5xvjWfdQrxyZFvpo7RflVGva+rEQlzyL+oNGp2j0eqXiQ6cGpGVlbEv+7BCcH2yU+7CP3ACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cfb37fa9ef55ec96121e5b0195b0d59116e12a6b6354c80db6c64684eb4539d","last_reissued_at":"2026-07-05T07:03:49.444205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:49.444205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asahi Ushio, Dimosthenis Antypas, Francesco Barbieri, Jiaxin Pei, Jose Camacho-Collados, Kiamehr Rezaee, Leonardo Neves, Luis Espinosa-Anke","submitted_at":"2023-10-23T09:48:25Z","abstract_excerpt":"Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14757","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/2310.14757/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":"2310.14757","created_at":"2026-07-05T07:03:49.444271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14757v1","created_at":"2026-07-05T07:03:49.444271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14757","created_at":"2026-07-05T07:03:49.444271+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT5TP6U66VPM","created_at":"2026-07-05T07:03:49.444271+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT5TP6U66VPMSYJB","created_at":"2026-07-05T07:03:49.444271+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT5TP6U6","created_at":"2026-07-05T07:03:49.444271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11285","citing_title":"AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models' Responses to Depression, Anxiety, and Stress Queries","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE","json":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE.json","graph_json":"https://pith.science/api/pith-number/PT5TP6U66VPMSYJB4WYBSWYNLE/graph.json","events_json":"https://pith.science/api/pith-number/PT5TP6U66VPMSYJB4WYBSWYNLE/events.json","paper":"https://pith.science/paper/PT5TP6U6"},"agent_actions":{"view_html":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE","download_json":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE.json","view_paper":"https://pith.science/paper/PT5TP6U6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14757&json=true","fetch_graph":"https://pith.science/api/pith-number/PT5TP6U66VPMSYJB4WYBSWYNLE/graph.json","fetch_events":"https://pith.science/api/pith-number/PT5TP6U66VPMSYJB4WYBSWYNLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE/action/storage_attestation","attest_author":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE/action/author_attestation","sign_citation":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE/action/citation_signature","submit_replication":"https://pith.science/pith/PT5TP6U66VPMSYJB4WYBSWYNLE/action/replication_record"}},"created_at":"2026-07-05T07:03:49.444271+00:00","updated_at":"2026-07-05T07:03:49.444271+00:00"}