{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XDDEJFNSE6R6MGG4MGDOLRMVSX","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":"51f68d6528177cd950a82bc702caeb2d02a62b1a600b30165ca2ba58e30abb74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T22:27:02Z","title_canon_sha256":"6e4352eb1d2764d171b0295cc718cd78b50eee0a91b8b07d799455029ba1677f"},"schema_version":"1.0","source":{"id":"2502.07087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07087","created_at":"2026-07-05T10:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07087v1","created_at":"2026-07-05T10:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07087","created_at":"2026-07-05T10:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"XDDEJFNSE6R6","created_at":"2026-07-05T10:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"XDDEJFNSE6R6MGG4","created_at":"2026-07-05T10:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"XDDEJFNS","created_at":"2026-07-05T10:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:5780f44243aeeca4e3529002e7d7e4038d7b52c21bb50561f3048ae9dd973565","target":"graph","created_at":"2026-07-05T10:12:32Z","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/2502.07087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contemporary large language models are powerful problem-solving tools, but they exhibit weaknesses in their reasoning abilities which ongoing research seeks to mitigate. We investigate graph coloring as a means of evaluating an LLM's capacities for systematic step-by-step reasoning and possibility space exploration, as well as effects of semantic problem framing. We test Claude 3.5 Sonnet, Llama 3.1 405B, Gemini 1.5 Pro, GPT-4o, o1-mini, and DeepSeek-R1 on a dataset of $k$-coloring problems with $2 \\leq k \\leq 4$ and vertex count $4 \\leq n \\leq 8$, using partial algorithmic solvers to further ","authors_text":"Alex Heyman, Joel Zylberberg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T22:27:02Z","title":"Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07087","kind":"arxiv","version":1},"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":"sha256:8cc217883e7330426feb93d290fe25791560148b426d94ce810020e3e25c5d5d","target":"record","created_at":"2026-07-05T10:12:32Z","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":"51f68d6528177cd950a82bc702caeb2d02a62b1a600b30165ca2ba58e30abb74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T22:27:02Z","title_canon_sha256":"6e4352eb1d2764d171b0295cc718cd78b50eee0a91b8b07d799455029ba1677f"},"schema_version":"1.0","source":{"id":"2502.07087","kind":"arxiv","version":1}},"canonical_sha256":"b8c64495b227a3e618dc6186e5c59595d99191b01f3c0994cf0419dd4344e4a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8c64495b227a3e618dc6186e5c59595d99191b01f3c0994cf0419dd4344e4a9","first_computed_at":"2026-07-05T10:12:32.634819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:32.634819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pY/1dt4JlgI7jTn9Ps5QSzzBTVzATOY770/p0C5Ur/WcG8S5ujO2THUz4jSLgfaFE3yZ+TT5XJpR4qF4HdFxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:32.635322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cc217883e7330426feb93d290fe25791560148b426d94ce810020e3e25c5d5d","sha256:5780f44243aeeca4e3529002e7d7e4038d7b52c21bb50561f3048ae9dd973565"],"state_sha256":"d1340fceaf6cfc6926e665c22218e543c8261eb0d666355d94b849a67c50142c"}