{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3CGXK4FNBEB24CX37HQEXRSF34","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":"17844b8ee3aa05df5b26e5110434eb7b3c6eef8571b0b976408277325c75563c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-11T04:08:44Z","title_canon_sha256":"af224c50861d500836cbd2f6520bd5ce0078ef16406ad8b6ba864437941b4e98"},"schema_version":"1.0","source":{"id":"2501.06430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06430","created_at":"2026-07-05T10:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06430v1","created_at":"2026-07-05T10:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06430","created_at":"2026-07-05T10:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"3CGXK4FNBEB2","created_at":"2026-07-05T10:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"3CGXK4FNBEB24CX3","created_at":"2026-07-05T10:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"3CGXK4FN","created_at":"2026-07-05T10:00:03Z"}],"graph_snapshots":[{"event_id":"sha256:8bfa1b6036df204362b1d769030d52bddbd536ac9fd0c055c29b92fa84abd45b","target":"graph","created_at":"2026-07-05T10:00:03Z","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/2501.06430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely attributable to inadequate perception of geometric primitives during image-level contrastive pre-training (e.g., CLIP). While recent efforts to improve math MLLMs have focused on scaling up mathematical visual instruction datasets and employing stronger LLM backbones, they often overlook persistent errors in visual recognition. In this paper, we systematically evaluate the visual grounding capabilities of state-of-th","authors_text":"Anton van den Hengel, Aotian Chen, Jindong Gu, Kai Zou, Piotr Koniusz, Shan Zhang, Yanpeng Sun, Yi-Yu Zheng, Yuan Xue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-11T04:08:44Z","title":"Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06430","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:d80db0f3329a8be09f93726121b9e56363460053fb50a1a601b236bfc5d1ad30","target":"record","created_at":"2026-07-05T10:00:03Z","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":"17844b8ee3aa05df5b26e5110434eb7b3c6eef8571b0b976408277325c75563c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-11T04:08:44Z","title_canon_sha256":"af224c50861d500836cbd2f6520bd5ce0078ef16406ad8b6ba864437941b4e98"},"schema_version":"1.0","source":{"id":"2501.06430","kind":"arxiv","version":1}},"canonical_sha256":"d88d7570ad0903ae0afbf9e04bc645df0fd09cb7923f15914bebe78e408c7fe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d88d7570ad0903ae0afbf9e04bc645df0fd09cb7923f15914bebe78e408c7fe8","first_computed_at":"2026-07-05T10:00:03.188563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:03.188563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vuDILOaTYGC1UqRmDd7FrCPnK+9f87YA94Oqgn3wGuD5oXaiCZwWxfWf/gXwAstYJeRpPNVqLcUKa0GKOlg2Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:03.189004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d80db0f3329a8be09f93726121b9e56363460053fb50a1a601b236bfc5d1ad30","sha256:8bfa1b6036df204362b1d769030d52bddbd536ac9fd0c055c29b92fa84abd45b"],"state_sha256":"8133730cb4c845085e352ab4e082271fd860d392b2ad78a324eb6f306bf63fed"}