{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W4ZNRIYLX3ZKRGE5OJZIR474GI","short_pith_number":"pith:W4ZNRIYL","schema_version":"1.0","canonical_sha256":"b732d8a30bbef2a8989d727288f3fc3235907ac3daeca2c675706cf3fa3d296d","source":{"kind":"arxiv","id":"2310.05163","version":3},"attestation_state":"computed","paper":{"title":"An Investigation of LLMs' Inefficacy in Understanding Converse Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bailin Wang, Binyuan Hui, Bowen Li, Chengwen Qi, Jinwang Wu, Jinyang Li, Yuanjun Laili","submitted_at":"2023-10-08T13:45:05Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success in many formal language oriented tasks, such as structural data-to-text and semantic parsing. However current benchmarks mostly follow the data distribution of the pre-training data of LLMs. Therefore, a natural question rises that do LLMs really understand the structured semantics of formal languages. In this paper, we investigate this problem on a special case, converse binary relation. We introduce a new benchmark ConvRe focusing on converse relations, which contains 17 relations and 1240 triples extracted from popular knowledge "},"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":"2310.05163","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T13:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"89e7ec2269c62a7a036c51b26aba3b9a926abcb9c081a63575c85c6fa295cd7c","abstract_canon_sha256":"6e3107493f1b6a699b7a61c60e5e89a0fcd60b9e56fbce5fd9957e70cf58fa9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:00.183488Z","signature_b64":"c7pcyYPRAh1PAEfePhybM1vWxp0fkJkGY3p9vAdUh5ALTJDQ5PNDJRB/B+gm6llXhztP0Z3f6NTI9QxlHqwIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b732d8a30bbef2a8989d727288f3fc3235907ac3daeca2c675706cf3fa3d296d","last_reissued_at":"2026-07-05T07:12:00.183008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:00.183008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Investigation of LLMs' Inefficacy in Understanding Converse Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bailin Wang, Binyuan Hui, Bowen Li, Chengwen Qi, Jinwang Wu, Jinyang Li, Yuanjun Laili","submitted_at":"2023-10-08T13:45:05Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success in many formal language oriented tasks, such as structural data-to-text and semantic parsing. However current benchmarks mostly follow the data distribution of the pre-training data of LLMs. Therefore, a natural question rises that do LLMs really understand the structured semantics of formal languages. In this paper, we investigate this problem on a special case, converse binary relation. We introduce a new benchmark ConvRe focusing on converse relations, which contains 17 relations and 1240 triples extracted from popular knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05163","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/2310.05163/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":"2310.05163","created_at":"2026-07-05T07:12:00.183061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05163v3","created_at":"2026-07-05T07:12:00.183061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05163","created_at":"2026-07-05T07:12:00.183061+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4ZNRIYLX3ZK","created_at":"2026-07-05T07:12:00.183061+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4ZNRIYLX3ZKRGE5","created_at":"2026-07-05T07:12:00.183061+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4ZNRIYL","created_at":"2026-07-05T07:12:00.183061+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/W4ZNRIYLX3ZKRGE5OJZIR474GI","json":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI.json","graph_json":"https://pith.science/api/pith-number/W4ZNRIYLX3ZKRGE5OJZIR474GI/graph.json","events_json":"https://pith.science/api/pith-number/W4ZNRIYLX3ZKRGE5OJZIR474GI/events.json","paper":"https://pith.science/paper/W4ZNRIYL"},"agent_actions":{"view_html":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI","download_json":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI.json","view_paper":"https://pith.science/paper/W4ZNRIYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05163&json=true","fetch_graph":"https://pith.science/api/pith-number/W4ZNRIYLX3ZKRGE5OJZIR474GI/graph.json","fetch_events":"https://pith.science/api/pith-number/W4ZNRIYLX3ZKRGE5OJZIR474GI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI/action/storage_attestation","attest_author":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI/action/author_attestation","sign_citation":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI/action/citation_signature","submit_replication":"https://pith.science/pith/W4ZNRIYLX3ZKRGE5OJZIR474GI/action/replication_record"}},"created_at":"2026-07-05T07:12:00.183061+00:00","updated_at":"2026-07-05T07:12:00.183061+00:00"}