{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6AJLQCO5MPIP7MDUINANSLB2FG","short_pith_number":"pith:6AJLQCO5","schema_version":"1.0","canonical_sha256":"f012b809dd63d0ffb0744340d92c3a299cd5f879aac12605a982408312ac8c51","source":{"kind":"arxiv","id":"2505.03171","version":1},"attestation_state":"computed","paper":{"title":"CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Beibei Xiong, Haiming Wang, Jia Li, Jonas Bayer, Jujian Zhang, Junqi Liu, Lihong Zhi, Roman Soletskyi, Weijie Jiang, Xiaodan Liang, Xiaohan Lin, Yael Dillies, Yunzhou Xie, Zhengfeng Yang, Zhengying Liu","submitted_at":"2025-05-06T04:32:17Z","abstract_excerpt":"Neurosymbolic approaches integrating large language models with formal reasoning have recently achieved human-level performance on mathematics competition problems in algebra, geometry and number theory. In comparison, combinatorics remains a challenging domain, characterized by a lack of appropriate benchmarks and theorem libraries. To address this gap, we introduce CombiBench, a comprehensive benchmark comprising 100 combinatorial problems, each formalized in Lean~4 and paired with its corresponding informal statement. The problem set covers a wide spectrum of difficulty levels, ranging from"},"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":"2505.03171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T04:32:17Z","cross_cats_sorted":[],"title_canon_sha256":"21d3ede6346a4df1b8b2ad5a9e946e0f93df77b822192dbcac9d4b9a3386d67d","abstract_canon_sha256":"915cd785fcaf57b475af6cd274bf6bcdf14cd4d4d2ebdb40786d9aeb87c7e54a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:11.360829Z","signature_b64":"k6p46o5gZNB5e+0PEmJxiXq6DrqslcxiQ91ymYv8SqfTpQTaQW6rwAbQbN4ZUBE4Yp9LrCYq5tY21oEf1ipPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f012b809dd63d0ffb0744340d92c3a299cd5f879aac12605a982408312ac8c51","last_reissued_at":"2026-07-05T10:59:11.360268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:11.360268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Beibei Xiong, Haiming Wang, Jia Li, Jonas Bayer, Jujian Zhang, Junqi Liu, Lihong Zhi, Roman Soletskyi, Weijie Jiang, Xiaodan Liang, Xiaohan Lin, Yael Dillies, Yunzhou Xie, Zhengfeng Yang, Zhengying Liu","submitted_at":"2025-05-06T04:32:17Z","abstract_excerpt":"Neurosymbolic approaches integrating large language models with formal reasoning have recently achieved human-level performance on mathematics competition problems in algebra, geometry and number theory. In comparison, combinatorics remains a challenging domain, characterized by a lack of appropriate benchmarks and theorem libraries. To address this gap, we introduce CombiBench, a comprehensive benchmark comprising 100 combinatorial problems, each formalized in Lean~4 and paired with its corresponding informal statement. The problem set covers a wide spectrum of difficulty levels, ranging from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03171","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/2505.03171/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":"2505.03171","created_at":"2026-07-05T10:59:11.360332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03171v1","created_at":"2026-07-05T10:59:11.360332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03171","created_at":"2026-07-05T10:59:11.360332+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AJLQCO5MPIP","created_at":"2026-07-05T10:59:11.360332+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AJLQCO5MPIP7MDU","created_at":"2026-07-05T10:59:11.360332+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AJLQCO5","created_at":"2026-07-05T10:59:11.360332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":150,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09450","citing_title":"TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03144","citing_title":"GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29493","citing_title":"Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17255","citing_title":"CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG","json":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG.json","graph_json":"https://pith.science/api/pith-number/6AJLQCO5MPIP7MDUINANSLB2FG/graph.json","events_json":"https://pith.science/api/pith-number/6AJLQCO5MPIP7MDUINANSLB2FG/events.json","paper":"https://pith.science/paper/6AJLQCO5"},"agent_actions":{"view_html":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG","download_json":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG.json","view_paper":"https://pith.science/paper/6AJLQCO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03171&json=true","fetch_graph":"https://pith.science/api/pith-number/6AJLQCO5MPIP7MDUINANSLB2FG/graph.json","fetch_events":"https://pith.science/api/pith-number/6AJLQCO5MPIP7MDUINANSLB2FG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG/action/storage_attestation","attest_author":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG/action/author_attestation","sign_citation":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG/action/citation_signature","submit_replication":"https://pith.science/pith/6AJLQCO5MPIP7MDUINANSLB2FG/action/replication_record"}},"created_at":"2026-07-05T10:59:11.360332+00:00","updated_at":"2026-07-05T10:59:11.360332+00:00"}