{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DZ44BZ4W55DFWM63EWNM3LQGME","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0226eba0786271cf2801752da565eb37795da3bac878864f6008e8b5f8df284b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-04T20:56:09Z","title_canon_sha256":"858dbc47bc524dd1e3e386d61e7f69483777a3c04aad1378971838e9c9175434"},"schema_version":"1.0","source":{"id":"2402.02611","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02611","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02611v3","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02611","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"DZ44BZ4W55DF","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"DZ44BZ4W55DFWM63","created_at":"2026-07-05T10:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"DZ44BZ4W","created_at":"2026-07-05T10:21:57Z"}],"graph_snapshots":[{"event_id":"sha256:27de3cfbf7c766a666e11cbbfdf1c37005605b90d66ccfbc5de90f890ee61841","target":"graph","created_at":"2026-07-05T10:21:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.02611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chinmay Mittal, Krishna Kartik, Mausam, Parag Singla","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-04T20:56:09Z","title":"FCoReBench: Can Large Language Models Solve Challenging First-Order Combinatorial Reasoning Problems?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02611","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c12af5f9acc2c86174216aba5cfd896ccfa7e29e27e6ad7e91d19aacf84fc9c4","target":"record","created_at":"2026-07-05T10:21:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0226eba0786271cf2801752da565eb37795da3bac878864f6008e8b5f8df284b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-04T20:56:09Z","title_canon_sha256":"858dbc47bc524dd1e3e386d61e7f69483777a3c04aad1378971838e9c9175434"},"schema_version":"1.0","source":{"id":"2402.02611","kind":"arxiv","version":3}},"canonical_sha256":"1e79c0e796ef465b33db259acdae0661047f20f6addc167f5fa9bce22c6294c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e79c0e796ef465b33db259acdae0661047f20f6addc167f5fa9bce22c6294c7","first_computed_at":"2026-07-05T10:21:57.394920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:57.394920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"03ATz3kP12gOAY+v5D7tWhPQO8NDOJi2wwd/690scNbeauO9SEHwk4oAuc4FB5LBgdELWQMD4XYPpX5/BqG3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:57.395476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02611","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c12af5f9acc2c86174216aba5cfd896ccfa7e29e27e6ad7e91d19aacf84fc9c4","sha256:27de3cfbf7c766a666e11cbbfdf1c37005605b90d66ccfbc5de90f890ee61841"],"state_sha256":"a2dbc585e1b14363d41b4a5034973b0e9a104effb02b0884e40302363236f9b6"}