{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XDDEJFNSE6R6MGG4MGDOLRMVSX","short_pith_number":"pith:XDDEJFNS","canonical_record":{"source":{"id":"2502.07087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T22:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"6e4352eb1d2764d171b0295cc718cd78b50eee0a91b8b07d799455029ba1677f","abstract_canon_sha256":"51f68d6528177cd950a82bc702caeb2d02a62b1a600b30165ca2ba58e30abb74"},"schema_version":"1.0"},"canonical_sha256":"b8c64495b227a3e618dc6186e5c59595d99191b01f3c0994cf0419dd4344e4a9","source":{"kind":"arxiv","id":"2502.07087","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XDDEJFNSE6R6MGG4MGDOLRMVSX","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T22:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"6e4352eb1d2764d171b0295cc718cd78b50eee0a91b8b07d799455029ba1677f","abstract_canon_sha256":"51f68d6528177cd950a82bc702caeb2d02a62b1a600b30165ca2ba58e30abb74"},"schema_version":"1.0"},"canonical_sha256":"b8c64495b227a3e618dc6186e5c59595d99191b01f3c0994cf0419dd4344e4a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:32.635322Z","signature_b64":"pY/1dt4JlgI7jTn9Ps5QSzzBTVzATOY770/p0C5Ur/WcG8S5ujO2THUz4jSLgfaFE3yZ+TT5XJpR4qF4HdFxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8c64495b227a3e618dc6186e5c59595d99191b01f3c0994cf0419dd4344e4a9","last_reissued_at":"2026-07-05T10:12:32.634819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:32.634819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07087","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSLQs0dTZvVMO+1K/QgsKewrE08iWg+7DTBarOmXasthwThqbaTO9hAhLp2aY4PYp+pPimbv8aLjdqJjYAIiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:16.463763Z"},"content_sha256":"8cc217883e7330426feb93d290fe25791560148b426d94ce810020e3e25c5d5d","schema_version":"1.0","event_id":"sha256:8cc217883e7330426feb93d290fe25791560148b426d94ce810020e3e25c5d5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XDDEJFNSE6R6MGG4MGDOLRMVSX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Heyman, Joel Zylberberg","submitted_at":"2025-02-10T22:27:02Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07087","kind":"arxiv","version":1},"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/2502.07087/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SsJijhkJt9005YCne1hhZ3Ad3Q5DOTM4hE6343NGDQnS4Gbx4c0Oxa+KeCLxx0xBKeqTkbehrj4ZIVsQM2C/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:16.464309Z"},"content_sha256":"5780f44243aeeca4e3529002e7d7e4038d7b52c21bb50561f3048ae9dd973565","schema_version":"1.0","event_id":"sha256:5780f44243aeeca4e3529002e7d7e4038d7b52c21bb50561f3048ae9dd973565"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX/bundle.json","state_url":"https://pith.science/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T16:42:16Z","links":{"resolver":"https://pith.science/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX","bundle":"https://pith.science/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX/bundle.json","state":"https://pith.science/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XDDEJFNSE6R6MGG4MGDOLRMVSX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1LvRAUIibXbpcwAVe2Lc1joSGGtZcJYH7QqzHNxhNNQnNU/coMPPZ017rgOJlg/9m7X7HaX7XbCwCnuqtvwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:42:16.468555Z","bundle_sha256":"3ef525cc08d5b5b5ef4f48d227bb20eb7b1e407826ef95c76ee6da7fb5e2bed7"}}