{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NDSDVM3RAC7JYATTDKDH6PIER5","short_pith_number":"pith:NDSDVM3R","schema_version":"1.0","canonical_sha256":"68e43ab37100be9c02731a867f3d048f66cf15f648883d3f9e9eccbafd86ad01","source":{"kind":"arxiv","id":"2605.28313","version":1},"attestation_state":"computed","paper":{"title":"Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agnes Paullate Nyiranziza, Davide Ceolin, Nicol\\'as Benjam\\'in Ocampo","submitted_at":"2026-05-27T11:14:37Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arguments requires a rigorous evaluation. We investigate the extent to which LLMs can effectively perform this task. We tested 12 open-weight LLMs of different sizes and families under zero-shot, few-shot, and chain-of-thought to approximate expert pairwise comparisons of argument quality across three dimensions-logical, rhetorical, and dialectic-and used these comparisons in a Bradley-Terry model to infer latent strength scores and derive a ranki"},"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":"2605.28313","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T11:14:37Z","cross_cats_sorted":[],"title_canon_sha256":"2cd38312c1dafcc823d4cb8b938534e6cff5a3e390143c1bd8762d62e0a574c7","abstract_canon_sha256":"a9c01e0afd59e7b01b4aa435fc091a5871bd46c45897885dafab5b2f1246cb58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:06.130885Z","signature_b64":"Oobrswl9qJCFxMroicdDdRlO/vP+A6o46eUdtAuwQ8NBwCTf9wrReE1Cgxyu4hxrTE8LfTXVF2vgOLOHB+d4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e43ab37100be9c02731a867f3d048f66cf15f648883d3f9e9eccbafd86ad01","last_reissued_at":"2026-05-28T01:05:06.130359Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:06.130359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agnes Paullate Nyiranziza, Davide Ceolin, Nicol\\'as Benjam\\'in Ocampo","submitted_at":"2026-05-27T11:14:37Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arguments requires a rigorous evaluation. We investigate the extent to which LLMs can effectively perform this task. We tested 12 open-weight LLMs of different sizes and families under zero-shot, few-shot, and chain-of-thought to approximate expert pairwise comparisons of argument quality across three dimensions-logical, rhetorical, and dialectic-and used these comparisons in a Bradley-Terry model to infer latent strength scores and derive a ranki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28313","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/2605.28313/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":"2605.28313","created_at":"2026-05-28T01:05:06.130436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28313v1","created_at":"2026-05-28T01:05:06.130436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28313","created_at":"2026-05-28T01:05:06.130436+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDSDVM3RAC7J","created_at":"2026-05-28T01:05:06.130436+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDSDVM3RAC7JYATT","created_at":"2026-05-28T01:05:06.130436+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDSDVM3R","created_at":"2026-05-28T01:05:06.130436+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/NDSDVM3RAC7JYATTDKDH6PIER5","json":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5.json","graph_json":"https://pith.science/api/pith-number/NDSDVM3RAC7JYATTDKDH6PIER5/graph.json","events_json":"https://pith.science/api/pith-number/NDSDVM3RAC7JYATTDKDH6PIER5/events.json","paper":"https://pith.science/paper/NDSDVM3R"},"agent_actions":{"view_html":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5","download_json":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5.json","view_paper":"https://pith.science/paper/NDSDVM3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28313&json=true","fetch_graph":"https://pith.science/api/pith-number/NDSDVM3RAC7JYATTDKDH6PIER5/graph.json","fetch_events":"https://pith.science/api/pith-number/NDSDVM3RAC7JYATTDKDH6PIER5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5/action/storage_attestation","attest_author":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5/action/author_attestation","sign_citation":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5/action/citation_signature","submit_replication":"https://pith.science/pith/NDSDVM3RAC7JYATTDKDH6PIER5/action/replication_record"}},"created_at":"2026-05-28T01:05:06.130436+00:00","updated_at":"2026-05-28T01:05:06.130436+00:00"}