{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WG6IAFICGEJCZKH7N3ZW2HV47H","short_pith_number":"pith:WG6IAFIC","canonical_record":{"source":{"id":"2605.12524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2026-04-07T01:19:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a6ed2a57efe72d9274f01e470584a276bc3a7e762df172814a99a3ce8ff98ca","abstract_canon_sha256":"a9ebcdcf0dfeb1ed6e7425eadb8b206ec358c2bc2a8025fc1768b7a3799cb160"},"schema_version":"1.0"},"canonical_sha256":"b1bc80150231122ca8ff6ef36d1ebcf9f54b3e75056f59a6b56fc9cbcc40a85d","source":{"kind":"arxiv","id":"2605.12524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12524","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12524v1","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12524","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"WG6IAFICGEJC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WG6IAFICGEJCZKH7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WG6IAFIC","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WG6IAFICGEJCZKH7N3ZW2HV47H","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2026-04-07T01:19:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a6ed2a57efe72d9274f01e470584a276bc3a7e762df172814a99a3ce8ff98ca","abstract_canon_sha256":"a9ebcdcf0dfeb1ed6e7425eadb8b206ec358c2bc2a8025fc1768b7a3799cb160"},"schema_version":"1.0"},"canonical_sha256":"b1bc80150231122ca8ff6ef36d1ebcf9f54b3e75056f59a6b56fc9cbcc40a85d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:02.822186Z","signature_b64":"Oh4qcyKcWaf9tojuXk9hkDuB/roOk3LJNNSoDHedgCIuHmeR8fGUktnV8axfsjR94y1FMFSeCcE39tfZqg2oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1bc80150231122ca8ff6ef36d1ebcf9f54b3e75056f59a6b56fc9cbcc40a85d","last_reissued_at":"2026-05-18T03:10:02.821690Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:02.821690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12524","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":"2026-05-18T03:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YYZ0ST+Rgi5xQ3k7Ss36XdFoWOx7vDN0JK8N6TJ/UsUad5C6MfYz5DlmqVwyW0cFrDI4CNq21kIAmGdG9RxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:39:00.592276Z"},"content_sha256":"cde8e7b3cd89c1629c08bcbaa29b2e7b3403365e586806cbd7b22b5cbf69e28a","schema_version":"1.0","event_id":"sha256:cde8e7b3cd89c1629c08bcbaa29b2e7b3403365e586806cbd7b22b5cbf69e28a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WG6IAFICGEJCZKH7N3ZW2HV47H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Frontier LLMs perform well on foundational proof tasks but fail at those requiring global combinatorial reasoning or low-level proof synthesis.","cross_cats":["cs.AI"],"primary_cat":"cs.LO","authors_text":"Konstantine Arkoudas, Serafim Batzoglou","submitted_at":"2026-04-07T01:19:41Z","abstract_excerpt":"We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid contains 15 tasks spanning proof writing, proof checking, proof masking, and proof gap-filling. Tasks are expressed in minimal formal notation, especially NDL, a compact natural-deduction language that fits in short prompts and supports precise, auditable verification. This yields mechanical, reproducible, and fine-grained evaluation rather than judgments by humans or LLMs. ProofGrid covers a calibrated difficulty spectrum, from foundational reasoni"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Frontier models perform well on several foundational tasks, yet difficult tasks, especially those requiring global combinatorial reasoning or low-level proof synthesis, remain far from solved.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That success or failure on these minimal-formalism proof tasks provides a meaningful signal of general reasoning competence independent of domain knowledge, solver delegation, or long-context artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Frontier LLMs perform well on foundational proof tasks but fail at those requiring global combinatorial reasoning or low-level proof synthesis.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7da9e1e09eb38dc5827baded10d0b7655c84c536e5613372a3b31986e76e63d7"},"source":{"id":"2605.12524","kind":"arxiv","version":1},"verdict":{"id":"606dcf7d-7425-41b4-86c4-43fed6c3f513","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:59:21.683069Z","strongest_claim":"Frontier models perform well on several foundational tasks, yet difficult tasks, especially those requiring global combinatorial reasoning or low-level proof synthesis, remain far from solved.","one_line_summary":"ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That success or failure on these minimal-formalism proof tasks provides a meaningful signal of general reasoning competence independent of domain knowledge, solver delegation, or long-context artifacts.","pith_extraction_headline":"Frontier LLMs perform well on foundational proof tasks but fail at those requiring global combinatorial reasoning or low-level proof synthesis."},"references":{"count":143,"sample":[{"doi":"","year":2003,"title":"Karl Popper: Critical Assessments of Leading Philosophers , publisher =","work_id":"978160ee-d5ed-492c-8342-916ddfc76021","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal for General Philosophy of Science , year =","work_id":"f4e27fbb-a78d-4e44-96ad-521379df3b72","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Argumentation , year =","work_id":"dcef650e-211e-410e-bbe6-627866aa361b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1985,"title":"Item Response Theory: Principles and Applications , author=. 1985 , publisher=","work_id":"06c55e58-0592-453b-be05-385031c4899c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Handbook of Item Response Theory Modeling: Applications to Typical Performance Assessment , publisher =","work_id":"62f9f4a0-86f9-494c-b4e2-139368fecaab","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":143,"snapshot_sha256":"29e69991e019d7280ce36baaf4829cb7437869946a239f9f2074208f0339baef","internal_anchors":7},"formal_canon":{"evidence_count":1,"snapshot_sha256":"3f639379e1124ddb18d392e7d83844f790967d8b8a17a7f524cd246b51938013"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"606dcf7d-7425-41b4-86c4-43fed6c3f513"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzhjiNIcnNIaoy1LFTt0+WBPJ3cCctrw1tkYoQ6UXBINKcCZwGDzqEfKX6hEw63D7Y/SUrcaqNjr1Hp7XZrFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:39:00.593482Z"},"content_sha256":"fcc969c7e6dcfc687bb5bfbd72340996e0105bb828d1a873af1de9657e8fc20c","schema_version":"1.0","event_id":"sha256:fcc969c7e6dcfc687bb5bfbd72340996e0105bb828d1a873af1de9657e8fc20c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WG6IAFICGEJCZKH7N3ZW2HV47H/bundle.json","state_url":"https://pith.science/pith/WG6IAFICGEJCZKH7N3ZW2HV47H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WG6IAFICGEJCZKH7N3ZW2HV47H/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":"2026-05-25T23:39:00Z","links":{"resolver":"https://pith.science/pith/WG6IAFICGEJCZKH7N3ZW2HV47H","bundle":"https://pith.science/pith/WG6IAFICGEJCZKH7N3ZW2HV47H/bundle.json","state":"https://pith.science/pith/WG6IAFICGEJCZKH7N3ZW2HV47H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WG6IAFICGEJCZKH7N3ZW2HV47H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WG6IAFICGEJCZKH7N3ZW2HV47H","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":"a9ebcdcf0dfeb1ed6e7425eadb8b206ec358c2bc2a8025fc1768b7a3799cb160","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2026-04-07T01:19:41Z","title_canon_sha256":"2a6ed2a57efe72d9274f01e470584a276bc3a7e762df172814a99a3ce8ff98ca"},"schema_version":"1.0","source":{"id":"2605.12524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12524","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12524v1","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12524","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"WG6IAFICGEJC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WG6IAFICGEJCZKH7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WG6IAFIC","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fcc969c7e6dcfc687bb5bfbd72340996e0105bb828d1a873af1de9657e8fc20c","target":"graph","created_at":"2026-05-18T03:10:02Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Frontier models perform well on several foundational tasks, yet difficult tasks, especially those requiring global combinatorial reasoning or low-level proof synthesis, remain far from solved."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That success or failure on these minimal-formalism proof tasks provides a meaningful signal of general reasoning competence independent of domain knowledge, solver delegation, or long-context artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Frontier LLMs perform well on foundational proof tasks but fail at those requiring global combinatorial reasoning or low-level proof synthesis."}],"snapshot_sha256":"7da9e1e09eb38dc5827baded10d0b7655c84c536e5613372a3b31986e76e63d7"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"3f639379e1124ddb18d392e7d83844f790967d8b8a17a7f524cd246b51938013"},"paper":{"abstract_excerpt":"We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid contains 15 tasks spanning proof writing, proof checking, proof masking, and proof gap-filling. Tasks are expressed in minimal formal notation, especially NDL, a compact natural-deduction language that fits in short prompts and supports precise, auditable verification. This yields mechanical, reproducible, and fine-grained evaluation rather than judgments by humans or LLMs. ProofGrid covers a calibrated difficulty spectrum, from foundational reasoni","authors_text":"Konstantine Arkoudas, Serafim Batzoglou","cross_cats":["cs.AI"],"headline":"Frontier LLMs perform well on foundational proof tasks but fail at those requiring global combinatorial reasoning or low-level proof synthesis.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2026-04-07T01:19:41Z","title":"Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism"},"references":{"count":143,"internal_anchors":7,"resolved_work":143,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Karl Popper: Critical Assessments of Leading Philosophers , publisher =","work_id":"978160ee-d5ed-492c-8342-916ddfc76021","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Journal for General Philosophy of Science , year =","work_id":"f4e27fbb-a78d-4e44-96ad-521379df3b72","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Argumentation , year =","work_id":"dcef650e-211e-410e-bbe6-627866aa361b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Item Response Theory: Principles and Applications , author=. 1985 , publisher=","work_id":"06c55e58-0592-453b-be05-385031c4899c","year":1985},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Handbook of Item Response Theory Modeling: Applications to Typical Performance Assessment , publisher =","work_id":"62f9f4a0-86f9-494c-b4e2-139368fecaab","year":null}],"snapshot_sha256":"29e69991e019d7280ce36baaf4829cb7437869946a239f9f2074208f0339baef"},"source":{"id":"2605.12524","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:59:21.683069Z","id":"606dcf7d-7425-41b4-86c4-43fed6c3f513","model_set":{"reader":"grok-4.3"},"one_line_summary":"ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Frontier LLMs perform well on foundational proof tasks but fail at those requiring global combinatorial reasoning or low-level proof synthesis.","strongest_claim":"Frontier models perform well on several foundational tasks, yet difficult tasks, especially those requiring global combinatorial reasoning or low-level proof synthesis, remain far from solved.","weakest_assumption":"That success or failure on these minimal-formalism proof tasks provides a meaningful signal of general reasoning competence independent of domain knowledge, solver delegation, or long-context artifacts."}},"verdict_id":"606dcf7d-7425-41b4-86c4-43fed6c3f513"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cde8e7b3cd89c1629c08bcbaa29b2e7b3403365e586806cbd7b22b5cbf69e28a","target":"record","created_at":"2026-05-18T03:10:02Z","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":"a9ebcdcf0dfeb1ed6e7425eadb8b206ec358c2bc2a8025fc1768b7a3799cb160","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2026-04-07T01:19:41Z","title_canon_sha256":"2a6ed2a57efe72d9274f01e470584a276bc3a7e762df172814a99a3ce8ff98ca"},"schema_version":"1.0","source":{"id":"2605.12524","kind":"arxiv","version":1}},"canonical_sha256":"b1bc80150231122ca8ff6ef36d1ebcf9f54b3e75056f59a6b56fc9cbcc40a85d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1bc80150231122ca8ff6ef36d1ebcf9f54b3e75056f59a6b56fc9cbcc40a85d","first_computed_at":"2026-05-18T03:10:02.821690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:02.821690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oh4qcyKcWaf9tojuXk9hkDuB/roOk3LJNNSoDHedgCIuHmeR8fGUktnV8axfsjR94y1FMFSeCcE39tfZqg2oCw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:02.822186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cde8e7b3cd89c1629c08bcbaa29b2e7b3403365e586806cbd7b22b5cbf69e28a","sha256:fcc969c7e6dcfc687bb5bfbd72340996e0105bb828d1a873af1de9657e8fc20c"],"state_sha256":"0663aec7d7957e47f6c5820c0234fed2153d87309fac2f47cdb344d217102fb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05iJpaMsOhEdc8C0jcTO8/VU/ry3iCF21HrcEDkTSfSVH3RCNEv0jxH3fxeZQ57OWSmBmqwKX5Gw8BU+AQ7AAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:39:00.596984Z","bundle_sha256":"3ce825f0c5501fb4453f5113f8889079aa9e9e5f58dfc66cc616bb99224d2e8b"}}