{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CPBAEWDT76HSCOZJQKAWKH5NXU","short_pith_number":"pith:CPBAEWDT","canonical_record":{"source":{"id":"2411.00836","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:29:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a89097622af148690084c143d73558ff1751ba7d9dc80115d7e6088806e5c9a2","abstract_canon_sha256":"9fcba2ba0fbeae30723eecfb6a69e5252446dcedcabea9a6c696e2b1544d4f3f"},"schema_version":"1.0"},"canonical_sha256":"13c2025873ff8f213b298281651fadbd3bb0bcbcae48026afcb2ee49866bc7aa","source":{"kind":"arxiv","id":"2411.00836","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00836","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00836v2","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00836","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"CPBAEWDT76HS","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"CPBAEWDT76HSCOZJ","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"CPBAEWDT","created_at":"2026-07-05T10:18:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CPBAEWDT76HSCOZJQKAWKH5NXU","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00836","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:29:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a89097622af148690084c143d73558ff1751ba7d9dc80115d7e6088806e5c9a2","abstract_canon_sha256":"9fcba2ba0fbeae30723eecfb6a69e5252446dcedcabea9a6c696e2b1544d4f3f"},"schema_version":"1.0"},"canonical_sha256":"13c2025873ff8f213b298281651fadbd3bb0bcbcae48026afcb2ee49866bc7aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:44.517223Z","signature_b64":"Lq2/pB9zIXf1tgtEWoAIcToTjxBFYRusJ3gCwhbOMG+uW7MF51zZQ+k8NXk2dwHJoQKM4OETEUVspX6NRJnvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13c2025873ff8f213b298281651fadbd3bb0bcbcae48026afcb2ee49866bc7aa","last_reissued_at":"2026-07-05T10:18:44.516671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:44.516671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00836","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBPovUtuud2+M9w33BZe8bwMyoIlHucwbGZvnDrxapONN3cBZzrxedcps98zOiMPag0tXMk7KG1dSpMPCEwoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T08:27:38.460826Z"},"content_sha256":"1435fe39c177a0dd8b076e313ff1c7e5968fdd49b9e71d24add76653841a05e4","schema_version":"1.0","event_id":"sha256:1435fe39c177a0dd8b076e313ff1c7e5968fdd49b9e71d24add76653841a05e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CPBAEWDT76HSCOZJQKAWKH5NXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Hu, Chengke Zou, Huan Zhang, Junyu Zhang, Rui Yang, Xingang Guo","submitted_at":"2024-10-29T17:29:19Z","abstract_excerpt":"The rapid advancements in Vision-Language Models (VLMs) have shown great potential in tackling mathematical reasoning tasks that involve visual context. Unlike humans who can reliably apply solution steps to similar problems with minor modifications, we found that SOTA VLMs like GPT-4o can consistently fail in these scenarios, revealing limitations in their mathematical reasoning capabilities. In this paper, we investigate the mathematical reasoning robustness in VLMs and evaluate how well these models perform under different variants of the same question, such as changes in visual numerical v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00836","kind":"arxiv","version":2},"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/2411.00836/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":"2026-07-05T10:18:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/OddCQhTtGGopCd5gf/ZNS0iLBBzaZLSGe28vcfCOjBv4u/AuZYlYbarvsGnfUV01vuQT4iWsZxujQZRnZZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T08:27:38.461340Z"},"content_sha256":"402a084e167c4149ff9b46e1b2b6b580a88b67bdbef5e484a2829e3837004eff","schema_version":"1.0","event_id":"sha256:402a084e167c4149ff9b46e1b2b6b580a88b67bdbef5e484a2829e3837004eff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPBAEWDT76HSCOZJQKAWKH5NXU/bundle.json","state_url":"https://pith.science/pith/CPBAEWDT76HSCOZJQKAWKH5NXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPBAEWDT76HSCOZJQKAWKH5NXU/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":"2026-08-03T08:27:38Z","links":{"resolver":"https://pith.science/pith/CPBAEWDT76HSCOZJQKAWKH5NXU","bundle":"https://pith.science/pith/CPBAEWDT76HSCOZJQKAWKH5NXU/bundle.json","state":"https://pith.science/pith/CPBAEWDT76HSCOZJQKAWKH5NXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPBAEWDT76HSCOZJQKAWKH5NXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CPBAEWDT76HSCOZJQKAWKH5NXU","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":"9fcba2ba0fbeae30723eecfb6a69e5252446dcedcabea9a6c696e2b1544d4f3f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:29:19Z","title_canon_sha256":"a89097622af148690084c143d73558ff1751ba7d9dc80115d7e6088806e5c9a2"},"schema_version":"1.0","source":{"id":"2411.00836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00836","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00836v2","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00836","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"CPBAEWDT76HS","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"CPBAEWDT76HSCOZJ","created_at":"2026-07-05T10:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"CPBAEWDT","created_at":"2026-07-05T10:18:44Z"}],"graph_snapshots":[{"event_id":"sha256:402a084e167c4149ff9b46e1b2b6b580a88b67bdbef5e484a2829e3837004eff","target":"graph","created_at":"2026-07-05T10:18:44Z","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/2411.00836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancements in Vision-Language Models (VLMs) have shown great potential in tackling mathematical reasoning tasks that involve visual context. Unlike humans who can reliably apply solution steps to similar problems with minor modifications, we found that SOTA VLMs like GPT-4o can consistently fail in these scenarios, revealing limitations in their mathematical reasoning capabilities. In this paper, we investigate the mathematical reasoning robustness in VLMs and evaluate how well these models perform under different variants of the same question, such as changes in visual numerical v","authors_text":"Bin Hu, Chengke Zou, Huan Zhang, Junyu Zhang, Rui Yang, Xingang Guo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:29:19Z","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00836","kind":"arxiv","version":2},"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":"sha256:1435fe39c177a0dd8b076e313ff1c7e5968fdd49b9e71d24add76653841a05e4","target":"record","created_at":"2026-07-05T10:18:44Z","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":"9fcba2ba0fbeae30723eecfb6a69e5252446dcedcabea9a6c696e2b1544d4f3f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:29:19Z","title_canon_sha256":"a89097622af148690084c143d73558ff1751ba7d9dc80115d7e6088806e5c9a2"},"schema_version":"1.0","source":{"id":"2411.00836","kind":"arxiv","version":2}},"canonical_sha256":"13c2025873ff8f213b298281651fadbd3bb0bcbcae48026afcb2ee49866bc7aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13c2025873ff8f213b298281651fadbd3bb0bcbcae48026afcb2ee49866bc7aa","first_computed_at":"2026-07-05T10:18:44.516671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:44.516671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lq2/pB9zIXf1tgtEWoAIcToTjxBFYRusJ3gCwhbOMG+uW7MF51zZQ+k8NXk2dwHJoQKM4OETEUVspX6NRJnvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:44.517223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1435fe39c177a0dd8b076e313ff1c7e5968fdd49b9e71d24add76653841a05e4","sha256:402a084e167c4149ff9b46e1b2b6b580a88b67bdbef5e484a2829e3837004eff"],"state_sha256":"d0d69d5bea94f91fcb2acd23679ad5cbe44700e35ea741aae3ae8416df5301d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6nwbnCPB1wr8+6Le8v8FAxLd/g7KlS9zakgwpBtIfQ2gjrz4UlFliUJTz99FKRiMiba6dpE92xeH66fGCsvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T08:27:38.465245Z","bundle_sha256":"adef60c83cbda75ad57146b329869e1139d905df5799679ebdd8b3e6c25757b1"}}