{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZ44BZ4W55DFWM63EWNM3LQGME","short_pith_number":"pith:DZ44BZ4W","schema_version":"1.0","canonical_sha256":"1e79c0e796ef465b33db259acdae0661047f20f6addc167f5fa9bce22c6294c7","source":{"kind":"arxiv","id":"2402.02611","version":3},"attestation_state":"computed","paper":{"title":"FCoReBench: Can Large Language Models Solve Challenging First-Order Combinatorial Reasoning Problems?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chinmay Mittal, Krishna Kartik, Mausam, Parag Singla","submitted_at":"2024-02-04T20:56:09Z","abstract_excerpt":"Can the large language models (LLMs) solve challenging first-order combinatorial reasoning problems such as graph coloring, knapsack, and cryptarithmetic? By first-order, we mean these problems can be instantiated with potentially an infinite number of problem instances of varying sizes. They are also challenging being NP-hard and requiring several reasoning steps to reach a solution. While existing work has focused on coming up with datasets with hard benchmarks, there is limited work which exploits the first-order nature of the problem structure. To address this challenge, we present FCoReBe"},"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":"2402.02611","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-04T20:56:09Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"858dbc47bc524dd1e3e386d61e7f69483777a3c04aad1378971838e9c9175434","abstract_canon_sha256":"0226eba0786271cf2801752da565eb37795da3bac878864f6008e8b5f8df284b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:57.395476Z","signature_b64":"03ATz3kP12gOAY+v5D7tWhPQO8NDOJi2wwd/690scNbeauO9SEHwk4oAuc4FB5LBgdELWQMD4XYPpX5/BqG3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e79c0e796ef465b33db259acdae0661047f20f6addc167f5fa9bce22c6294c7","last_reissued_at":"2026-07-05T10:21:57.394920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:57.394920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FCoReBench: Can Large Language Models Solve Challenging First-Order Combinatorial Reasoning Problems?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chinmay Mittal, Krishna Kartik, Mausam, Parag Singla","submitted_at":"2024-02-04T20:56:09Z","abstract_excerpt":"Can the large language models (LLMs) solve challenging first-order combinatorial reasoning problems such as graph coloring, knapsack, and cryptarithmetic? By first-order, we mean these problems can be instantiated with potentially an infinite number of problem instances of varying sizes. They are also challenging being NP-hard and requiring several reasoning steps to reach a solution. While existing work has focused on coming up with datasets with hard benchmarks, there is limited work which exploits the first-order nature of the problem structure. To address this challenge, we present FCoReBe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02611","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/2402.02611/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":"2402.02611","created_at":"2026-07-05T10:21:57.395004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02611v3","created_at":"2026-07-05T10:21:57.395004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02611","created_at":"2026-07-05T10:21:57.395004+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZ44BZ4W55DF","created_at":"2026-07-05T10:21:57.395004+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZ44BZ4W55DFWM63","created_at":"2026-07-05T10:21:57.395004+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZ44BZ4W","created_at":"2026-07-05T10:21:57.395004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.08636","citing_title":"InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME","json":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME.json","graph_json":"https://pith.science/api/pith-number/DZ44BZ4W55DFWM63EWNM3LQGME/graph.json","events_json":"https://pith.science/api/pith-number/DZ44BZ4W55DFWM63EWNM3LQGME/events.json","paper":"https://pith.science/paper/DZ44BZ4W"},"agent_actions":{"view_html":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME","download_json":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME.json","view_paper":"https://pith.science/paper/DZ44BZ4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02611&json=true","fetch_graph":"https://pith.science/api/pith-number/DZ44BZ4W55DFWM63EWNM3LQGME/graph.json","fetch_events":"https://pith.science/api/pith-number/DZ44BZ4W55DFWM63EWNM3LQGME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME/action/storage_attestation","attest_author":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME/action/author_attestation","sign_citation":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME/action/citation_signature","submit_replication":"https://pith.science/pith/DZ44BZ4W55DFWM63EWNM3LQGME/action/replication_record"}},"created_at":"2026-07-05T10:21:57.395004+00:00","updated_at":"2026-07-05T10:21:57.395004+00:00"}