{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F75A6PKKLT73R2QWYL3UZTT375","short_pith_number":"pith:F75A6PKK","schema_version":"1.0","canonical_sha256":"2ffa0f3d4a5cffb8ea16c2f74cce7bff7946f2f937e3a68398f9702fd59cd2ef","source":{"kind":"arxiv","id":"2606.10479","version":1},"attestation_state":"computed","paper":{"title":"ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bangjie Xu, Dongrui Liu, Haodi Lei, Haoran Zhang, Ning Ding, Qianjia Cheng, Runzhe Zhan, Shunkai Zhang, Xiaoye Qu, Xinmiao Han, Yafu Li, Yizhuo Li, Yu Cheng, Yucheng Su, Yun Luo, Yu Qiao, Zhilin Wang, Zhouchen Lin","submitted_at":"2026-06-09T06:50:15Z","abstract_excerpt":"Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning. We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of large language models. ComBench contains 100 human-annotated competition-level problems organized around two complementary settings: a"},"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":"2606.10479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T06:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"556de02d528f4d9a7f907d44f1e6dfc311a6c80aed2c2488ba8371e20f7da25d","abstract_canon_sha256":"64cb1afacc14d44191f65115aed4e76e09b3daf5b10df53836a9a41694890344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:21.409762Z","signature_b64":"d9yV/NjHZqzOEax8Mg4NuNEMqMyL0/ayYzOWPBw7Jr53vrCdwmbM1HsDYcOW+I0T/UrsCecgC5EQQ2tkcZ6hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffa0f3d4a5cffb8ea16c2f74cce7bff7946f2f937e3a68398f9702fd59cd2ef","last_reissued_at":"2026-06-10T01:10:21.408893Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:21.408893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bangjie Xu, Dongrui Liu, Haodi Lei, Haoran Zhang, Ning Ding, Qianjia Cheng, Runzhe Zhan, Shunkai Zhang, Xiaoye Qu, Xinmiao Han, Yafu Li, Yizhuo Li, Yu Cheng, Yucheng Su, Yun Luo, Yu Qiao, Zhilin Wang, Zhouchen Lin","submitted_at":"2026-06-09T06:50:15Z","abstract_excerpt":"Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning. We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of large language models. ComBench contains 100 human-annotated competition-level problems organized around two complementary settings: a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10479","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/2606.10479/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":"2606.10479","created_at":"2026-06-10T01:10:21.409049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10479v1","created_at":"2026-06-10T01:10:21.409049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10479","created_at":"2026-06-10T01:10:21.409049+00:00"},{"alias_kind":"pith_short_12","alias_value":"F75A6PKKLT73","created_at":"2026-06-10T01:10:21.409049+00:00"},{"alias_kind":"pith_short_16","alias_value":"F75A6PKKLT73R2QW","created_at":"2026-06-10T01:10:21.409049+00:00"},{"alias_kind":"pith_short_8","alias_value":"F75A6PKK","created_at":"2026-06-10T01:10:21.409049+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/F75A6PKKLT73R2QWYL3UZTT375","json":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375.json","graph_json":"https://pith.science/api/pith-number/F75A6PKKLT73R2QWYL3UZTT375/graph.json","events_json":"https://pith.science/api/pith-number/F75A6PKKLT73R2QWYL3UZTT375/events.json","paper":"https://pith.science/paper/F75A6PKK"},"agent_actions":{"view_html":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375","download_json":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375.json","view_paper":"https://pith.science/paper/F75A6PKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10479&json=true","fetch_graph":"https://pith.science/api/pith-number/F75A6PKKLT73R2QWYL3UZTT375/graph.json","fetch_events":"https://pith.science/api/pith-number/F75A6PKKLT73R2QWYL3UZTT375/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375/action/storage_attestation","attest_author":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375/action/author_attestation","sign_citation":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375/action/citation_signature","submit_replication":"https://pith.science/pith/F75A6PKKLT73R2QWYL3UZTT375/action/replication_record"}},"created_at":"2026-06-10T01:10:21.409049+00:00","updated_at":"2026-06-10T01:10:21.409049+00:00"}