{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7UY2KIUMNHBXB7BGAE7IGEYNQV","short_pith_number":"pith:7UY2KIUM","canonical_record":{"source":{"id":"2606.05818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.HO","submitted_at":"2026-06-04T07:59:08Z","cross_cats_sorted":["cs.AI","math.AG","math.CO","math.RT"],"title_canon_sha256":"bcb177aa6308292a16c4897baab2f3f4e8657e305f16f5fcd6687df484472e19","abstract_canon_sha256":"31173281692d3c6c23433a36607f9f31be9b90399d5243bb13572b0a82deaba0"},"schema_version":"1.0"},"canonical_sha256":"fd31a5228c69c370fc26013e83130d8571e55d0500eeca71bce7615c8be3476a","source":{"kind":"arxiv","id":"2606.05818","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05818","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05818v1","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05818","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"7UY2KIUMNHBX","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"7UY2KIUMNHBXB7BG","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"7UY2KIUM","created_at":"2026-06-05T01:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7UY2KIUMNHBXB7BGAE7IGEYNQV","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.HO","submitted_at":"2026-06-04T07:59:08Z","cross_cats_sorted":["cs.AI","math.AG","math.CO","math.RT"],"title_canon_sha256":"bcb177aa6308292a16c4897baab2f3f4e8657e305f16f5fcd6687df484472e19","abstract_canon_sha256":"31173281692d3c6c23433a36607f9f31be9b90399d5243bb13572b0a82deaba0"},"schema_version":"1.0"},"canonical_sha256":"fd31a5228c69c370fc26013e83130d8571e55d0500eeca71bce7615c8be3476a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:04.564879Z","signature_b64":"2S0IebGtRn7gxOeMI6fBjjClai/jjhLfkbCWupTsKaFi9apGJZXlXgyFUw73kOWqtdVrbSEMGye2JLdzwqjaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd31a5228c69c370fc26013e83130d8571e55d0500eeca71bce7615c8be3476a","last_reissued_at":"2026-06-05T01:15:04.564448Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:04.564448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05818","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":"2026-06-05T01:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WBRCIV5n99BRgDwDSIk0+mYb8aZ6GaNbo1n00subh+7hYUg/G2J4cULshM/6E2/h+mtPMbOO7cqBZXEov6AwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:15:14.000091Z"},"content_sha256":"800671bb92cf8e66f646f86e6aebe53a2387130cb55d74b1f1f12a988eaff879","schema_version":"1.0","event_id":"sha256:800671bb92cf8e66f646f86e6aebe53a2387130cb55d74b1f1f12a988eaff879"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7UY2KIUMNHBXB7BGAE7IGEYNQV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarks in Leipzig","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.AG","math.CO","math.RT"],"primary_cat":"math.HO","authors_text":"Alejandro Morales, Alexander Ivanov, Alexander Taveira Blomenhofer, Andrea Rosana, Andrei Balakin, Annette Werner, Aryaman Jal, Baran Hashemi, Bernd Sturmfels, Carl Felix Waller, Carlos Rodriguez, Chiara Giardino, Christian Stump, Clara Briand, Claudius Zibrowius, Danai Deligeorgaki, Elena Hoster, Emil Verkama, Felix Lotter, Flavio Salizzoni, Gianni Petrella, Greta Panova, Hannah Friedman, Jesus A. De Loera, Joris Koefler, Julian Weigert, Kevin K\\\"uhn, Lakshmi Ramesh, Leonie Kayser, Lina Maria Simbaqueba Marin, Luca Sodomaco, Marie-Charlotte Brandenburg, Mario Kummer, Mikl\\'os B\\'ona, Nathan Pflueger, Nathan Williams, Nikolas Rieke, Nupur Jain, Otto T.P. Schmidt, Philipp Tuchel, Ren\\'e Marczinzik, Shelby Cox, Simon Telen, Stephen Griffeth, Sven Ulf Schmitz, Tim Gehrunger, Veronica Calvo Cortes, Victor S. Miller","submitted_at":"2026-06-04T07:59:08Z","abstract_excerpt":"Between April 1 and May 15, 2026, a group of 49 mathematicians compiled a dataset of research-level mathematics questions with known answers. Most of the work was done during the 3-day workshop *Benchmarks in Leipzig* with 35 participants at the Max Planck Institute for Mathematics in the Sciences in Leipzig, Germany. We present the resulting collection of 100 questions. We evaluated these questions in three stages: a single attempt by five state-of-the-art LLMs, followed by a 20-runs-per-model evaluation with three of these models, and finally a 3-run attempt with two heavy-thinking models. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05818","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/2606.05818/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":"2026-06-05T01:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o5tVHvsBaFWbIjPjWuMV/4Dp0iS0jndlvvkmCU8Woipp4oCXWOMKiuqwDYOiEx/xSj/WxgzbBMieEpYqHgmfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:15:14.000937Z"},"content_sha256":"a7c68438983eaece786d3a76d8c9807e9dd7823d95fb7c5a1416070fbeb4ffa4","schema_version":"1.0","event_id":"sha256:a7c68438983eaece786d3a76d8c9807e9dd7823d95fb7c5a1416070fbeb4ffa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV/bundle.json","state_url":"https://pith.science/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV/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":"2026-06-10T12:15:14Z","links":{"resolver":"https://pith.science/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV","bundle":"https://pith.science/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV/bundle.json","state":"https://pith.science/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UY2KIUMNHBXB7BGAE7IGEYNQV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7UY2KIUMNHBXB7BGAE7IGEYNQV","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":"31173281692d3c6c23433a36607f9f31be9b90399d5243bb13572b0a82deaba0","cross_cats_sorted":["cs.AI","math.AG","math.CO","math.RT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.HO","submitted_at":"2026-06-04T07:59:08Z","title_canon_sha256":"bcb177aa6308292a16c4897baab2f3f4e8657e305f16f5fcd6687df484472e19"},"schema_version":"1.0","source":{"id":"2606.05818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05818","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05818v1","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05818","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"7UY2KIUMNHBX","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"7UY2KIUMNHBXB7BG","created_at":"2026-06-05T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"7UY2KIUM","created_at":"2026-06-05T01:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:a7c68438983eaece786d3a76d8c9807e9dd7823d95fb7c5a1416070fbeb4ffa4","target":"graph","created_at":"2026-06-05T01:15:04Z","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/2606.05818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Between April 1 and May 15, 2026, a group of 49 mathematicians compiled a dataset of research-level mathematics questions with known answers. Most of the work was done during the 3-day workshop *Benchmarks in Leipzig* with 35 participants at the Max Planck Institute for Mathematics in the Sciences in Leipzig, Germany. We present the resulting collection of 100 questions. We evaluated these questions in three stages: a single attempt by five state-of-the-art LLMs, followed by a 20-runs-per-model evaluation with three of these models, and finally a 3-run attempt with two heavy-thinking models. A","authors_text":"Alejandro Morales, Alexander Ivanov, Alexander Taveira Blomenhofer, Andrea Rosana, Andrei Balakin, Annette Werner, Aryaman Jal, Baran Hashemi, Bernd Sturmfels, Carl Felix Waller, Carlos Rodriguez, Chiara Giardino, Christian Stump, Clara Briand, Claudius Zibrowius, Danai Deligeorgaki, Elena Hoster, Emil Verkama, Felix Lotter, Flavio Salizzoni, Gianni Petrella, Greta Panova, Hannah Friedman, Jesus A. De Loera, Joris Koefler, Julian Weigert, Kevin K\\\"uhn, Lakshmi Ramesh, Leonie Kayser, Lina Maria Simbaqueba Marin, Luca Sodomaco, Marie-Charlotte Brandenburg, Mario Kummer, Mikl\\'os B\\'ona, Nathan Pflueger, Nathan Williams, Nikolas Rieke, Nupur Jain, Otto T.P. Schmidt, Philipp Tuchel, Ren\\'e Marczinzik, Shelby Cox, Simon Telen, Stephen Griffeth, Sven Ulf Schmitz, Tim Gehrunger, Veronica Calvo Cortes, Victor S. Miller","cross_cats":["cs.AI","math.AG","math.CO","math.RT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.HO","submitted_at":"2026-06-04T07:59:08Z","title":"Benchmarks in Leipzig"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05818","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":"sha256:800671bb92cf8e66f646f86e6aebe53a2387130cb55d74b1f1f12a988eaff879","target":"record","created_at":"2026-06-05T01:15:04Z","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":"31173281692d3c6c23433a36607f9f31be9b90399d5243bb13572b0a82deaba0","cross_cats_sorted":["cs.AI","math.AG","math.CO","math.RT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.HO","submitted_at":"2026-06-04T07:59:08Z","title_canon_sha256":"bcb177aa6308292a16c4897baab2f3f4e8657e305f16f5fcd6687df484472e19"},"schema_version":"1.0","source":{"id":"2606.05818","kind":"arxiv","version":1}},"canonical_sha256":"fd31a5228c69c370fc26013e83130d8571e55d0500eeca71bce7615c8be3476a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd31a5228c69c370fc26013e83130d8571e55d0500eeca71bce7615c8be3476a","first_computed_at":"2026-06-05T01:15:04.564448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:04.564448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2S0IebGtRn7gxOeMI6fBjjClai/jjhLfkbCWupTsKaFi9apGJZXlXgyFUw73kOWqtdVrbSEMGye2JLdzwqjaDg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:04.564879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:800671bb92cf8e66f646f86e6aebe53a2387130cb55d74b1f1f12a988eaff879","sha256:a7c68438983eaece786d3a76d8c9807e9dd7823d95fb7c5a1416070fbeb4ffa4"],"state_sha256":"a1c429901dfe24064bebba05e95b0b507768b3b9dd30887209d2c603e2927a80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"40eQ79ohkro2XxkQi/vjhu1gp3NpLzYWfZ/S8R/R8X+nxCoRxd2B2PjD9PjYGSx3vAd0CfQCfVBRev5rSNPGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:15:14.005387Z","bundle_sha256":"bde6d12ee7aa17c704a7e20e3f8a60c840291f6fbe7da7a7c10162632bec3336"}}