{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CL7EVHI4AAKEPUUR6LDEAQABOG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b5500343673466a6ef707e6f4ecec0eaeaed34f1e81c1f7618be2161591e7f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T23:02:56Z","title_canon_sha256":"a51fd9f4de8c3d269e5cbe97ef2df06453158e50269a94f054950f3d65a90b42"},"schema_version":"1.0","source":{"id":"2406.17169","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17169","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17169v3","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17169","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"CL7EVHI4AAKE","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"CL7EVHI4AAKEPUUR","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"CL7EVHI4","created_at":"2026-07-05T09:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:f606d9459dff9dd6300279dfb1f9faf3fd5826e7418bd9f549a786c4f0df68fe","target":"graph","created_at":"2026-07-05T09:16:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.17169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aashna Budhiraja, Chitta Baral, Mihir Parmar, Mohith Kulkarni, Mutsumi Nakamura, Neeraj Varshney, Nisarg Patel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T23:02:56Z","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17169","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fe680c45274a2a681e931a1ff7c9cd1b7cff4d3306ef136ee0d757e1f4aa64d1","target":"record","created_at":"2026-07-05T09:16:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b5500343673466a6ef707e6f4ecec0eaeaed34f1e81c1f7618be2161591e7f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T23:02:56Z","title_canon_sha256":"a51fd9f4de8c3d269e5cbe97ef2df06453158e50269a94f054950f3d65a90b42"},"schema_version":"1.0","source":{"id":"2406.17169","kind":"arxiv","version":3}},"canonical_sha256":"12fe4a9d1c001447d291f2c640400171a570d158308aa735d2c71598147547b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12fe4a9d1c001447d291f2c640400171a570d158308aa735d2c71598147547b3","first_computed_at":"2026-07-05T09:16:50.454138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:50.454138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"423XDmUGp3ptbYYE+U0ZiR+IfUdUHgvj0NDNNG8cyVdVzcwrBKEbweMYYQxcAKUu2ZVj1aoqRfeVs6SwSZGABw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:50.454625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17169","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe680c45274a2a681e931a1ff7c9cd1b7cff4d3306ef136ee0d757e1f4aa64d1","sha256:f606d9459dff9dd6300279dfb1f9faf3fd5826e7418bd9f549a786c4f0df68fe"],"state_sha256":"20129369915619204fab5a35ad4d211d7818abd860dbd708333e032f62754ae7"}