{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:47GARMVT4XXWY33UOMPTEG2HJH","short_pith_number":"pith:47GARMVT","schema_version":"1.0","canonical_sha256":"e7cc08b2b3e5ef6c6f74731f321b4749e4d2937de82c7c498b581e84c200d177","source":{"kind":"arxiv","id":"2606.19788","version":1},"attestation_state":"computed","paper":{"title":"CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ond\\v{r}ej Ku\\v{z}elka, Yi Chang, Yuanhong Wang, Yuxu Zhou, Yuyi Wang","submitted_at":"2026-06-18T04:47:49Z","abstract_excerpt":"We present CombEval, a dynamic benchmark for evaluating combinatorial counting in large language models. CombEval represents each problem as a typed Cofola specification over entities, combinatorial objects, object dependencies, and constraints, enabling controlled generation of natural-language counting problems with exact solver-verified answers. Unlike static collections, CombEval supports systematic variation of object type, entity scale, constraint count, and reasoning depth. We evaluate 11 LLMs under direct and code-augmented settings and find that models remain brittle on ordered object"},"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":"2606.19788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T04:47:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ed8d42087ea0e181e2f6888a6c8e6afa2341a7b8ef6267d523a8cbc61444eeb9","abstract_canon_sha256":"94278bff6a3c64c28808fcd359782578ef3c8187d4f85c11acf998a6cd6d3b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:35.190425Z","signature_b64":"KIOpz2SRVnZjMQq8orkS7pVeLiOHu7rhth/iizI2mkZ3v7KO7OE0ryzMyX7zkLDxAdt30hYBu0EdSj4idP0gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7cc08b2b3e5ef6c6f74731f321b4749e4d2937de82c7c498b581e84c200d177","last_reissued_at":"2026-06-19T16:12:35.190072Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:35.190072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ond\\v{r}ej Ku\\v{z}elka, Yi Chang, Yuanhong Wang, Yuxu Zhou, Yuyi Wang","submitted_at":"2026-06-18T04:47:49Z","abstract_excerpt":"We present CombEval, a dynamic benchmark for evaluating combinatorial counting in large language models. CombEval represents each problem as a typed Cofola specification over entities, combinatorial objects, object dependencies, and constraints, enabling controlled generation of natural-language counting problems with exact solver-verified answers. Unlike static collections, CombEval supports systematic variation of object type, entity scale, constraint count, and reasoning depth. We evaluate 11 LLMs under direct and code-augmented settings and find that models remain brittle on ordered object"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19788","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/2606.19788/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":"2606.19788","created_at":"2026-06-19T16:12:35.190132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19788v1","created_at":"2026-06-19T16:12:35.190132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19788","created_at":"2026-06-19T16:12:35.190132+00:00"},{"alias_kind":"pith_short_12","alias_value":"47GARMVT4XXW","created_at":"2026-06-19T16:12:35.190132+00:00"},{"alias_kind":"pith_short_16","alias_value":"47GARMVT4XXWY33U","created_at":"2026-06-19T16:12:35.190132+00:00"},{"alias_kind":"pith_short_8","alias_value":"47GARMVT","created_at":"2026-06-19T16:12:35.190132+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/47GARMVT4XXWY33UOMPTEG2HJH","json":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH.json","graph_json":"https://pith.science/api/pith-number/47GARMVT4XXWY33UOMPTEG2HJH/graph.json","events_json":"https://pith.science/api/pith-number/47GARMVT4XXWY33UOMPTEG2HJH/events.json","paper":"https://pith.science/paper/47GARMVT"},"agent_actions":{"view_html":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH","download_json":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH.json","view_paper":"https://pith.science/paper/47GARMVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19788&json=true","fetch_graph":"https://pith.science/api/pith-number/47GARMVT4XXWY33UOMPTEG2HJH/graph.json","fetch_events":"https://pith.science/api/pith-number/47GARMVT4XXWY33UOMPTEG2HJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH/action/storage_attestation","attest_author":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH/action/author_attestation","sign_citation":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH/action/citation_signature","submit_replication":"https://pith.science/pith/47GARMVT4XXWY33UOMPTEG2HJH/action/replication_record"}},"created_at":"2026-06-19T16:12:35.190132+00:00","updated_at":"2026-06-19T16:12:35.190132+00:00"}