{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CL7EVHI4AAKEPUUR6LDEAQABOG","short_pith_number":"pith:CL7EVHI4","schema_version":"1.0","canonical_sha256":"12fe4a9d1c001447d291f2c640400171a570d158308aa735d2c71598147547b3","source":{"kind":"arxiv","id":"2406.17169","version":3},"attestation_state":"computed","paper":{"title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aashna Budhiraja, Chitta Baral, Mihir Parmar, Mohith Kulkarni, Mutsumi Nakamura, Neeraj Varshney, Nisarg Patel","submitted_at":"2024-06-24T23:02:56Z","abstract_excerpt":"As Large Language Models (LLMs) continue to exhibit remarkable performance in natural language understanding tasks, there is a crucial need to measure their ability for human-like multi-step logical reasoning. Existing logical reasoning evaluation benchmarks often focus primarily on simplistic single-step or multi-step reasoning with a limited set of inference rules. Furthermore, the lack of datasets for evaluating non-monotonic reasoning represents a crucial gap since it aligns more closely with human-like reasoning. To address these limitations, we propose Multi-LogiEval, a comprehensive eva"},"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":"2406.17169","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T23:02:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a51fd9f4de8c3d269e5cbe97ef2df06453158e50269a94f054950f3d65a90b42","abstract_canon_sha256":"0b5500343673466a6ef707e6f4ecec0eaeaed34f1e81c1f7618be2161591e7f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:50.454625Z","signature_b64":"423XDmUGp3ptbYYE+U0ZiR+IfUdUHgvj0NDNNG8cyVdVzcwrBKEbweMYYQxcAKUu2ZVj1aoqRfeVs6SwSZGABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12fe4a9d1c001447d291f2c640400171a570d158308aa735d2c71598147547b3","last_reissued_at":"2026-07-05T09:16:50.454138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:50.454138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aashna Budhiraja, Chitta Baral, Mihir Parmar, Mohith Kulkarni, Mutsumi Nakamura, Neeraj Varshney, Nisarg Patel","submitted_at":"2024-06-24T23:02:56Z","abstract_excerpt":"As Large Language Models (LLMs) continue to exhibit remarkable performance in natural language understanding tasks, there is a crucial need to measure their ability for human-like multi-step logical reasoning. Existing logical reasoning evaluation benchmarks often focus primarily on simplistic single-step or multi-step reasoning with a limited set of inference rules. Furthermore, the lack of datasets for evaluating non-monotonic reasoning represents a crucial gap since it aligns more closely with human-like reasoning. To address these limitations, we propose Multi-LogiEval, a comprehensive eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17169","kind":"arxiv","version":3},"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/2406.17169/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":"2406.17169","created_at":"2026-07-05T09:16:50.454197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17169v3","created_at":"2026-07-05T09:16:50.454197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17169","created_at":"2026-07-05T09:16:50.454197+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL7EVHI4AAKE","created_at":"2026-07-05T09:16:50.454197+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL7EVHI4AAKEPUUR","created_at":"2026-07-05T09:16:50.454197+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL7EVHI4","created_at":"2026-07-05T09:16:50.454197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15079","citing_title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19807","citing_title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24765","citing_title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG","json":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG.json","graph_json":"https://pith.science/api/pith-number/CL7EVHI4AAKEPUUR6LDEAQABOG/graph.json","events_json":"https://pith.science/api/pith-number/CL7EVHI4AAKEPUUR6LDEAQABOG/events.json","paper":"https://pith.science/paper/CL7EVHI4"},"agent_actions":{"view_html":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG","download_json":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG.json","view_paper":"https://pith.science/paper/CL7EVHI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17169&json=true","fetch_graph":"https://pith.science/api/pith-number/CL7EVHI4AAKEPUUR6LDEAQABOG/graph.json","fetch_events":"https://pith.science/api/pith-number/CL7EVHI4AAKEPUUR6LDEAQABOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG/action/storage_attestation","attest_author":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG/action/author_attestation","sign_citation":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG/action/citation_signature","submit_replication":"https://pith.science/pith/CL7EVHI4AAKEPUUR6LDEAQABOG/action/replication_record"}},"created_at":"2026-07-05T09:16:50.454197+00:00","updated_at":"2026-07-05T09:16:50.454197+00:00"}