{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BI74F3G75OEXV337F5XQE4P4I4","short_pith_number":"pith:BI74F3G7","schema_version":"1.0","canonical_sha256":"0a3fc2ecdfeb897aef7f2f6f0271fc473722eade97415eb09c6a7279eeac1883","source":{"kind":"arxiv","id":"2305.15074","version":3},"attestation_state":"computed","paper":{"title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daman Arora, Himanshu Gaurav Singh, Mausam","submitted_at":"2023-05-24T11:55:59Z","abstract_excerpt":"The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs. We curate 515 challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT JEE-Advanced exam. Long-horizon reasoning on top of deep in-domain knowledge is essential for solving problems in this benchmark. Our evaluation on various open-source and proprietary models reveals that the highest"},"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":"2305.15074","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:55:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"274db546dc3a7c42fd9375fdad325eb135dd1b09bde3865a1b09f9fe49438c1b","abstract_canon_sha256":"8a47804b696efec15d4e7f6324c28ff290c0f394112d0201070835aaa7be6f02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:59.337385Z","signature_b64":"Q67EuJcilI9cNHa+/xZ9fBK85qliJkjBkbmo36Pz8Xy+nSK1KOoIvmWn8X7yQFH1Lja5UtoYeRABGLzWji/KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a3fc2ecdfeb897aef7f2f6f0271fc473722eade97415eb09c6a7279eeac1883","last_reissued_at":"2026-07-05T07:03:59.336891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:59.336891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daman Arora, Himanshu Gaurav Singh, Mausam","submitted_at":"2023-05-24T11:55:59Z","abstract_excerpt":"The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs. We curate 515 challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT JEE-Advanced exam. Long-horizon reasoning on top of deep in-domain knowledge is essential for solving problems in this benchmark. Our evaluation on various open-source and proprietary models reveals that the highest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15074","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/2305.15074/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":"2305.15074","created_at":"2026-07-05T07:03:59.336945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15074v3","created_at":"2026-07-05T07:03:59.336945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15074","created_at":"2026-07-05T07:03:59.336945+00:00"},{"alias_kind":"pith_short_12","alias_value":"BI74F3G75OEX","created_at":"2026-07-05T07:03:59.336945+00:00"},{"alias_kind":"pith_short_16","alias_value":"BI74F3G75OEXV337","created_at":"2026-07-05T07:03:59.336945+00:00"},{"alias_kind":"pith_short_8","alias_value":"BI74F3G7","created_at":"2026-07-05T07:03:59.336945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05199","citing_title":"Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10930","citing_title":"Evaluating the False Trust Engendered by LLM Explanations","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07985","citing_title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10930","citing_title":"Evaluating the False Trust Engendered by LLM Explanations","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4","json":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4.json","graph_json":"https://pith.science/api/pith-number/BI74F3G75OEXV337F5XQE4P4I4/graph.json","events_json":"https://pith.science/api/pith-number/BI74F3G75OEXV337F5XQE4P4I4/events.json","paper":"https://pith.science/paper/BI74F3G7"},"agent_actions":{"view_html":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4","download_json":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4.json","view_paper":"https://pith.science/paper/BI74F3G7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15074&json=true","fetch_graph":"https://pith.science/api/pith-number/BI74F3G75OEXV337F5XQE4P4I4/graph.json","fetch_events":"https://pith.science/api/pith-number/BI74F3G75OEXV337F5XQE4P4I4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4/action/storage_attestation","attest_author":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4/action/author_attestation","sign_citation":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4/action/citation_signature","submit_replication":"https://pith.science/pith/BI74F3G75OEXV337F5XQE4P4I4/action/replication_record"}},"created_at":"2026-07-05T07:03:59.336945+00:00","updated_at":"2026-07-05T07:03:59.336945+00:00"}