{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QNA3Z5KAG34JVCVARABYZBQKYR","short_pith_number":"pith:QNA3Z5KA","schema_version":"1.0","canonical_sha256":"8341bcf54036f89a8aa088038c860ac45bc564bfb592e11a6ad6215e433e6c04","source":{"kind":"arxiv","id":"2412.00539","version":2},"attestation_state":"computed","paper":{"title":"TextClass Benchmark: A Continuous Elo Rating of LLMs in Social Sciences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Basti\\'an Gonz\\'alez-Bustamante","submitted_at":"2024-11-30T17:09:49Z","abstract_excerpt":"The TextClass Benchmark project is an ongoing, continuous benchmarking process that aims to provide a comprehensive, fair, and dynamic evaluation of LLMs and transformers for text classification tasks. This evaluation spans various domains and languages in social sciences disciplines engaged in NLP and text-as-data approach. The leaderboards present performance metrics and relative ranking using a tailored Elo rating system. With each leaderboard cycle, novel models are added, fixed test sets can be replaced for unseen, equivalent data to test generalisation power, ratings are updated, and a M"},"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":"2412.00539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T17:09:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3985a7d5e2b57a9a0a3eb9c5881b4041efc083a90be9835914bbd98a2555d43c","abstract_canon_sha256":"993439d385e9448ef5117890ac8662e8ce788913fae19239a9d4920231a67832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:59.103743Z","signature_b64":"Z/qGP7rKBOCbAsXYHBHq+C8/fRuzR8IH7DGe1K5oQyLAEyLlMDryKFUT/1PbzaE7gDEa5wiTgOg68D2PsRZ4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8341bcf54036f89a8aa088038c860ac45bc564bfb592e11a6ad6215e433e6c04","last_reissued_at":"2026-07-05T09:45:59.103351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:59.103351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextClass Benchmark: A Continuous Elo Rating of LLMs in Social Sciences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Basti\\'an Gonz\\'alez-Bustamante","submitted_at":"2024-11-30T17:09:49Z","abstract_excerpt":"The TextClass Benchmark project is an ongoing, continuous benchmarking process that aims to provide a comprehensive, fair, and dynamic evaluation of LLMs and transformers for text classification tasks. This evaluation spans various domains and languages in social sciences disciplines engaged in NLP and text-as-data approach. The leaderboards present performance metrics and relative ranking using a tailored Elo rating system. With each leaderboard cycle, novel models are added, fixed test sets can be replaced for unseen, equivalent data to test generalisation power, ratings are updated, and a M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00539","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/2412.00539/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":"2412.00539","created_at":"2026-07-05T09:45:59.103407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00539v2","created_at":"2026-07-05T09:45:59.103407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00539","created_at":"2026-07-05T09:45:59.103407+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNA3Z5KAG34J","created_at":"2026-07-05T09:45:59.103407+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNA3Z5KAG34JVCVA","created_at":"2026-07-05T09:45:59.103407+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNA3Z5KA","created_at":"2026-07-05T09:45:59.103407+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/QNA3Z5KAG34JVCVARABYZBQKYR","json":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR.json","graph_json":"https://pith.science/api/pith-number/QNA3Z5KAG34JVCVARABYZBQKYR/graph.json","events_json":"https://pith.science/api/pith-number/QNA3Z5KAG34JVCVARABYZBQKYR/events.json","paper":"https://pith.science/paper/QNA3Z5KA"},"agent_actions":{"view_html":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR","download_json":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR.json","view_paper":"https://pith.science/paper/QNA3Z5KA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00539&json=true","fetch_graph":"https://pith.science/api/pith-number/QNA3Z5KAG34JVCVARABYZBQKYR/graph.json","fetch_events":"https://pith.science/api/pith-number/QNA3Z5KAG34JVCVARABYZBQKYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR/action/storage_attestation","attest_author":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR/action/author_attestation","sign_citation":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR/action/citation_signature","submit_replication":"https://pith.science/pith/QNA3Z5KAG34JVCVARABYZBQKYR/action/replication_record"}},"created_at":"2026-07-05T09:45:59.103407+00:00","updated_at":"2026-07-05T09:45:59.103407+00:00"}