{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7PHGMMLFQ4YFQMNJXNVKSBP7JM","short_pith_number":"pith:7PHGMMLF","schema_version":"1.0","canonical_sha256":"fbce66316587305831a9bb6aa905ff4b0d734a35a3b356879ca6974c8017cd56","source":{"kind":"arxiv","id":"2508.19988","version":3},"attestation_state":"computed","paper":{"title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Brassard, Hossein A. Rahmani, Joe Stacey, Lihu Chen, Lisa Alazraki, Marek Rei","submitted_at":"2025-08-27T15:47:19Z","abstract_excerpt":"Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple reasoning steps. However, current compositional benchmarks testing these skills tend to focus on either commonsense or math reasoning, whereas LLM agents solving real-world tasks would require a combination of both. In this work, we introduce an Agentic Commonsense and Math benchmark (AgentCoMa), where each compositional task requires a commonsense reasoning step and a math reasoning step. We test it on 61 LLMs of different sizes, model families, an"},"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":"2508.19988","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T15:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"995c59d6d533f10ccc0ecc302ff34dc1b30c2902235df7b13c9186871742ab72","abstract_canon_sha256":"fa57dac6e09ced8e3d0c72eecec595f418350a354cbdff3895f896f20dceb86d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:54.019451Z","signature_b64":"iABvFP4sVbB6ERp6tJNH9KF4iBjoftXQSS9MU24Wnwp8fjA9O4QPvWxRtOa0aO1fgq7B/30fiCigAHcCaB1/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbce66316587305831a9bb6aa905ff4b0d734a35a3b356879ca6974c8017cd56","last_reissued_at":"2026-05-26T02:03:54.018582Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:54.018582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Brassard, Hossein A. Rahmani, Joe Stacey, Lihu Chen, Lisa Alazraki, Marek Rei","submitted_at":"2025-08-27T15:47:19Z","abstract_excerpt":"Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple reasoning steps. However, current compositional benchmarks testing these skills tend to focus on either commonsense or math reasoning, whereas LLM agents solving real-world tasks would require a combination of both. In this work, we introduce an Agentic Commonsense and Math benchmark (AgentCoMa), where each compositional task requires a commonsense reasoning step and a math reasoning step. We test it on 61 LLMs of different sizes, model families, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19988","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/2508.19988/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":"2508.19988","created_at":"2026-05-26T02:03:54.018712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19988v3","created_at":"2026-05-26T02:03:54.018712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19988","created_at":"2026-05-26T02:03:54.018712+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PHGMMLFQ4YF","created_at":"2026-05-26T02:03:54.018712+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PHGMMLFQ4YFQMNJ","created_at":"2026-05-26T02:03:54.018712+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PHGMMLF","created_at":"2026-05-26T02:03:54.018712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.16593","citing_title":"Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16593","citing_title":"Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM","json":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM.json","graph_json":"https://pith.science/api/pith-number/7PHGMMLFQ4YFQMNJXNVKSBP7JM/graph.json","events_json":"https://pith.science/api/pith-number/7PHGMMLFQ4YFQMNJXNVKSBP7JM/events.json","paper":"https://pith.science/paper/7PHGMMLF"},"agent_actions":{"view_html":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM","download_json":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM.json","view_paper":"https://pith.science/paper/7PHGMMLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19988&json=true","fetch_graph":"https://pith.science/api/pith-number/7PHGMMLFQ4YFQMNJXNVKSBP7JM/graph.json","fetch_events":"https://pith.science/api/pith-number/7PHGMMLFQ4YFQMNJXNVKSBP7JM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM/action/storage_attestation","attest_author":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM/action/author_attestation","sign_citation":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM/action/citation_signature","submit_replication":"https://pith.science/pith/7PHGMMLFQ4YFQMNJXNVKSBP7JM/action/replication_record"}},"created_at":"2026-05-26T02:03:54.018712+00:00","updated_at":"2026-05-26T02:03:54.018712+00:00"}