{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:65S5CVSV3WONUSSAPEMKYIFZKO","short_pith_number":"pith:65S5CVSV","canonical_record":{"source":{"id":"2507.22958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T23:46:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"29bce09e4ae777cec1fa70567ad64777859ba0a62203afa333f530fe9e04c7f1","abstract_canon_sha256":"208d320184549cfd162de2f76efdfffb045aab36025592851e2822257dc058d4"},"schema_version":"1.0"},"canonical_sha256":"f765d15655dd9cda4a407918ac20b9538f8f92ff5db6b41a8558eafabb58dd3b","source":{"kind":"arxiv","id":"2507.22958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22958","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22958v1","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22958","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"65S5CVSV3WON","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"65S5CVSV3WONUSSA","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"65S5CVSV","created_at":"2026-07-05T11:46:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:65S5CVSV3WONUSSAPEMKYIFZKO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T23:46:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"29bce09e4ae777cec1fa70567ad64777859ba0a62203afa333f530fe9e04c7f1","abstract_canon_sha256":"208d320184549cfd162de2f76efdfffb045aab36025592851e2822257dc058d4"},"schema_version":"1.0"},"canonical_sha256":"f765d15655dd9cda4a407918ac20b9538f8f92ff5db6b41a8558eafabb58dd3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:02.858491Z","signature_b64":"Jjc09fIx9E40b2iDxgMtVNI9eS+M2lrPRUa9fONiI+7c81g5y4prgO21KNroezORDLuzOQwv4WFjbgQo6B2ZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f765d15655dd9cda4a407918ac20b9538f8f92ff5db6b41a8558eafabb58dd3b","last_reissued_at":"2026-07-05T11:46:02.857844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:02.857844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22958","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":"2026-07-05T11:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6zs0tm9HZcSSs6X88QUVpYikIhAzka3U0787v6hHL/3jrIlO1ODGE77k4yAQyb9k/d3arEedXPgFujWteLeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:20:25.818640Z"},"content_sha256":"e7c6f1e96ebedda1c4bd7b56c056945ada7b7e6261383e867b60da976df05ee8","schema_version":"1.0","event_id":"sha256:e7c6f1e96ebedda1c4bd7b56c056945ada7b7e6261383e867b60da976df05ee8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:65S5CVSV3WONUSSAPEMKYIFZKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHECK-MAT: Checking Hand-Written Mathematical Answers for the Russian Unified State Exam","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ruslan Khrulev","submitted_at":"2025-07-29T23:46:45Z","abstract_excerpt":"This paper introduces a novel benchmark, EGE-Math Solutions Assessment Benchmark, for evaluating Vision-Language Models (VLMs) on their ability to assess hand-written mathematical solutions. Unlike existing benchmarks that focus on problem solving, our approach centres on understanding student solutions, identifying mistakes, and assigning grades according to fixed criteria. We compile 122 scanned solutions from the Russian Unified State Exam (EGE) together with official expert grades, and evaluate seven modern VLMs from Google, OpenAI, Arcee AI, and Alibaba Cloud in three inference modes. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22958","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/2507.22958/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":"2026-07-05T11:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ns+HysfcgTxi2RePc5WKCXraZba6ft4PCdZqg+vgR0dvGIwMrAW6WsApNLS4i+hXbCnATd4hmpBr0x2t+w7kCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:20:25.819171Z"},"content_sha256":"f29bd5d74b421daf8afab0ba346171f5467e4603ec6d5813502b40db4879a3f5","schema_version":"1.0","event_id":"sha256:f29bd5d74b421daf8afab0ba346171f5467e4603ec6d5813502b40db4879a3f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65S5CVSV3WONUSSAPEMKYIFZKO/bundle.json","state_url":"https://pith.science/pith/65S5CVSV3WONUSSAPEMKYIFZKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65S5CVSV3WONUSSAPEMKYIFZKO/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":"2026-08-01T12:20:25Z","links":{"resolver":"https://pith.science/pith/65S5CVSV3WONUSSAPEMKYIFZKO","bundle":"https://pith.science/pith/65S5CVSV3WONUSSAPEMKYIFZKO/bundle.json","state":"https://pith.science/pith/65S5CVSV3WONUSSAPEMKYIFZKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65S5CVSV3WONUSSAPEMKYIFZKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:65S5CVSV3WONUSSAPEMKYIFZKO","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":"208d320184549cfd162de2f76efdfffb045aab36025592851e2822257dc058d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T23:46:45Z","title_canon_sha256":"29bce09e4ae777cec1fa70567ad64777859ba0a62203afa333f530fe9e04c7f1"},"schema_version":"1.0","source":{"id":"2507.22958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22958","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22958v1","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22958","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"65S5CVSV3WON","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"65S5CVSV3WONUSSA","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"65S5CVSV","created_at":"2026-07-05T11:46:02Z"}],"graph_snapshots":[{"event_id":"sha256:f29bd5d74b421daf8afab0ba346171f5467e4603ec6d5813502b40db4879a3f5","target":"graph","created_at":"2026-07-05T11:46:02Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.22958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a novel benchmark, EGE-Math Solutions Assessment Benchmark, for evaluating Vision-Language Models (VLMs) on their ability to assess hand-written mathematical solutions. Unlike existing benchmarks that focus on problem solving, our approach centres on understanding student solutions, identifying mistakes, and assigning grades according to fixed criteria. We compile 122 scanned solutions from the Russian Unified State Exam (EGE) together with official expert grades, and evaluate seven modern VLMs from Google, OpenAI, Arcee AI, and Alibaba Cloud in three inference modes. The","authors_text":"Ruslan Khrulev","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T23:46:45Z","title":"CHECK-MAT: Checking Hand-Written Mathematical Answers for the Russian Unified State Exam"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22958","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:e7c6f1e96ebedda1c4bd7b56c056945ada7b7e6261383e867b60da976df05ee8","target":"record","created_at":"2026-07-05T11:46:02Z","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":"208d320184549cfd162de2f76efdfffb045aab36025592851e2822257dc058d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T23:46:45Z","title_canon_sha256":"29bce09e4ae777cec1fa70567ad64777859ba0a62203afa333f530fe9e04c7f1"},"schema_version":"1.0","source":{"id":"2507.22958","kind":"arxiv","version":1}},"canonical_sha256":"f765d15655dd9cda4a407918ac20b9538f8f92ff5db6b41a8558eafabb58dd3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f765d15655dd9cda4a407918ac20b9538f8f92ff5db6b41a8558eafabb58dd3b","first_computed_at":"2026-07-05T11:46:02.857844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:02.857844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jjc09fIx9E40b2iDxgMtVNI9eS+M2lrPRUa9fONiI+7c81g5y4prgO21KNroezORDLuzOQwv4WFjbgQo6B2ZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:02.858491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c6f1e96ebedda1c4bd7b56c056945ada7b7e6261383e867b60da976df05ee8","sha256:f29bd5d74b421daf8afab0ba346171f5467e4603ec6d5813502b40db4879a3f5"],"state_sha256":"0ec93f4b23ea6bc81fe6c61468b37e736c11ae60f0a89e0f9b4b862b39a087f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jlZRZhPciMMdbu1mzvgdczgNs93fP18zRu1RqjYssg2kDTOm6xhUPWHCIrWPHQFh6QPdlw2GucnPXgKwkkI6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T12:20:25.824999Z","bundle_sha256":"e1c1082ec7f0de838d7f2234f2ca92fa0ef4243643409cff4d7910385794e058"}}