{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VH6PTWUNTMJNVC7TIBNIATH4TM","short_pith_number":"pith:VH6PTWUN","schema_version":"1.0","canonical_sha256":"a9fcf9da8d9b12da8bf3405a804cfc9b228730205f37952d6941b970a0f1172c","source":{"kind":"arxiv","id":"2311.09761","version":2},"attestation_state":"computed","paper":{"title":"MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chadi Helwe, Chlo\\'e Clavel, Fabian Suchanek, Pierre-Henri Paris, Tom Calamai","submitted_at":"2023-11-16T10:35:11Z","abstract_excerpt":"We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets. It comes with a taxonomy that aligns, refines, and unifies existing classifications of fallacies. We further provide a manual annotation of a part of the dataset together with manual explanations for each annotation. We propose a new annotation scheme tailored for subjective NLP tasks, and a new evaluation method designed to handle subjectivity. We then evaluate several language models under a zero-shot learning setting and human performances on MAFALDA to assess their capability to d"},"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":"2311.09761","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:35:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e5f9b8f45771e243b2c9e78a0530f7e005c2f1d57796034d24207490cf7cb079","abstract_canon_sha256":"11a49e083b28fa33abb70b24cfcbf3fb35031b690967d91704b6d528d0a51d86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:11.980163Z","signature_b64":"XhrJk0+QXnAO6xjXdGvmc1WXJEk9SjH4LpG2DYY6bHWrajvEiCqGu8V14KhLaVLHoSmFLGnFTfOAwvCrFY9pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9fcf9da8d9b12da8bf3405a804cfc9b228730205f37952d6941b970a0f1172c","last_reissued_at":"2026-07-05T08:06:11.979733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:11.979733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chadi Helwe, Chlo\\'e Clavel, Fabian Suchanek, Pierre-Henri Paris, Tom Calamai","submitted_at":"2023-11-16T10:35:11Z","abstract_excerpt":"We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets. It comes with a taxonomy that aligns, refines, and unifies existing classifications of fallacies. We further provide a manual annotation of a part of the dataset together with manual explanations for each annotation. We propose a new annotation scheme tailored for subjective NLP tasks, and a new evaluation method designed to handle subjectivity. We then evaluate several language models under a zero-shot learning setting and human performances on MAFALDA to assess their capability to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09761","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/2311.09761/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":"2311.09761","created_at":"2026-07-05T08:06:11.979788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09761v2","created_at":"2026-07-05T08:06:11.979788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09761","created_at":"2026-07-05T08:06:11.979788+00:00"},{"alias_kind":"pith_short_12","alias_value":"VH6PTWUNTMJN","created_at":"2026-07-05T08:06:11.979788+00:00"},{"alias_kind":"pith_short_16","alias_value":"VH6PTWUNTMJNVC7T","created_at":"2026-07-05T08:06:11.979788+00:00"},{"alias_kind":"pith_short_8","alias_value":"VH6PTWUN","created_at":"2026-07-05T08:06:11.979788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17926","citing_title":"AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM","json":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM.json","graph_json":"https://pith.science/api/pith-number/VH6PTWUNTMJNVC7TIBNIATH4TM/graph.json","events_json":"https://pith.science/api/pith-number/VH6PTWUNTMJNVC7TIBNIATH4TM/events.json","paper":"https://pith.science/paper/VH6PTWUN"},"agent_actions":{"view_html":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM","download_json":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM.json","view_paper":"https://pith.science/paper/VH6PTWUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09761&json=true","fetch_graph":"https://pith.science/api/pith-number/VH6PTWUNTMJNVC7TIBNIATH4TM/graph.json","fetch_events":"https://pith.science/api/pith-number/VH6PTWUNTMJNVC7TIBNIATH4TM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM/action/storage_attestation","attest_author":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM/action/author_attestation","sign_citation":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM/action/citation_signature","submit_replication":"https://pith.science/pith/VH6PTWUNTMJNVC7TIBNIATH4TM/action/replication_record"}},"created_at":"2026-07-05T08:06:11.979788+00:00","updated_at":"2026-07-05T08:06:11.979788+00:00"}