{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PM3H4E2U66QJXUFHNPWEO7P2KT","short_pith_number":"pith:PM3H4E2U","canonical_record":{"source":{"id":"2506.06034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T12:33:12Z","cross_cats_sorted":[],"title_canon_sha256":"932c12b6aa27ac14fc3b5ce9666ec0779479c807f7bdc95e70236218d6d8b29c","abstract_canon_sha256":"16ba8e394235b1c1ca041f6b41059c8e96be90842faa23658740328d8d3009f9"},"schema_version":"1.0"},"canonical_sha256":"7b367e1354f7a09bd0a76bec477dfa54daee19f5d706d5ed63890f23dbc63c4c","source":{"kind":"arxiv","id":"2506.06034","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06034","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06034v1","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06034","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"PM3H4E2U66QJ","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"PM3H4E2U66QJXUFH","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"PM3H4E2U","created_at":"2026-07-05T11:17:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PM3H4E2U66QJXUFHNPWEO7P2KT","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T12:33:12Z","cross_cats_sorted":[],"title_canon_sha256":"932c12b6aa27ac14fc3b5ce9666ec0779479c807f7bdc95e70236218d6d8b29c","abstract_canon_sha256":"16ba8e394235b1c1ca041f6b41059c8e96be90842faa23658740328d8d3009f9"},"schema_version":"1.0"},"canonical_sha256":"7b367e1354f7a09bd0a76bec477dfa54daee19f5d706d5ed63890f23dbc63c4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:16.271011Z","signature_b64":"67iN6IT05olHbP9sDS0M7zzVpzv9QQFrMAq7s6d1URuh07M4V25ijOfSQ3nIluTaFb1MnFH2axDU4Gog5TvZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b367e1354f7a09bd0a76bec477dfa54daee19f5d706d5ed63890f23dbc63c4c","last_reissued_at":"2026-07-05T11:17:16.270475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:16.270475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06034","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":"2026-07-05T11:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lpR7MI5QqdPRVC3VKv7YthaAXI/dIyuBQH+TxyB5Nun/B/HLLA56EmgovQCY97BpSrP8wU/JpKy9G9ssAnXwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:47:55.986758Z"},"content_sha256":"d0c4b272bbe0cac852c9208137a4f60fa498b7c7c0a54ba26919da8acb17c2a9","schema_version":"1.0","event_id":"sha256:d0c4b272bbe0cac852c9208137a4f60fa498b7c7c0a54ba26919da8acb17c2a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PM3H4E2U66QJXUFHNPWEO7P2KT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dadi Guo, Dazhong Chen, Yi R. Fung, Zhitao He, Zongwei Lyu","submitted_at":"2025-06-06T12:33:12Z","abstract_excerpt":"Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guide the proof process. Modern Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in solving a wide range of mathematical problems. However, the potential of MLLMs as Automated Theorem Provers (ATPs), specifically in the multimodal domain, remains underexplored. In this paper, we introduce the Multimodal Automated Theorem Proving benchmark (MATP-BENCH), a new Multimoda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06034","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/2506.06034/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":"2026-07-05T11:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D3Eb9ekq8pVK4pzK4nDZh33B3mTZscpRU0exZ89lIYfY0wPSCBkBMAzLdvKZl4CkMYg0Uk0VL8WxB08/uJfRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:47:55.987693Z"},"content_sha256":"c22b358bede01d2810ac1a68c4d600ef530d3b29594cbaa722b2c2e56eccb259","schema_version":"1.0","event_id":"sha256:c22b358bede01d2810ac1a68c4d600ef530d3b29594cbaa722b2c2e56eccb259"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PM3H4E2U66QJXUFHNPWEO7P2KT/bundle.json","state_url":"https://pith.science/pith/PM3H4E2U66QJXUFHNPWEO7P2KT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PM3H4E2U66QJXUFHNPWEO7P2KT/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":"2026-08-08T19:47:55Z","links":{"resolver":"https://pith.science/pith/PM3H4E2U66QJXUFHNPWEO7P2KT","bundle":"https://pith.science/pith/PM3H4E2U66QJXUFHNPWEO7P2KT/bundle.json","state":"https://pith.science/pith/PM3H4E2U66QJXUFHNPWEO7P2KT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PM3H4E2U66QJXUFHNPWEO7P2KT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PM3H4E2U66QJXUFHNPWEO7P2KT","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":"16ba8e394235b1c1ca041f6b41059c8e96be90842faa23658740328d8d3009f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T12:33:12Z","title_canon_sha256":"932c12b6aa27ac14fc3b5ce9666ec0779479c807f7bdc95e70236218d6d8b29c"},"schema_version":"1.0","source":{"id":"2506.06034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06034","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06034v1","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06034","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"PM3H4E2U66QJ","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"PM3H4E2U66QJXUFH","created_at":"2026-07-05T11:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"PM3H4E2U","created_at":"2026-07-05T11:17:16Z"}],"graph_snapshots":[{"event_id":"sha256:c22b358bede01d2810ac1a68c4d600ef530d3b29594cbaa722b2c2e56eccb259","target":"graph","created_at":"2026-07-05T11:17:16Z","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/2506.06034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guide the proof process. Modern Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in solving a wide range of mathematical problems. However, the potential of MLLMs as Automated Theorem Provers (ATPs), specifically in the multimodal domain, remains underexplored. In this paper, we introduce the Multimodal Automated Theorem Proving benchmark (MATP-BENCH), a new Multimoda","authors_text":"Dadi Guo, Dazhong Chen, Yi R. Fung, Zhitao He, Zongwei Lyu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T12:33:12Z","title":"MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06034","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:d0c4b272bbe0cac852c9208137a4f60fa498b7c7c0a54ba26919da8acb17c2a9","target":"record","created_at":"2026-07-05T11:17:16Z","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":"16ba8e394235b1c1ca041f6b41059c8e96be90842faa23658740328d8d3009f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T12:33:12Z","title_canon_sha256":"932c12b6aa27ac14fc3b5ce9666ec0779479c807f7bdc95e70236218d6d8b29c"},"schema_version":"1.0","source":{"id":"2506.06034","kind":"arxiv","version":1}},"canonical_sha256":"7b367e1354f7a09bd0a76bec477dfa54daee19f5d706d5ed63890f23dbc63c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b367e1354f7a09bd0a76bec477dfa54daee19f5d706d5ed63890f23dbc63c4c","first_computed_at":"2026-07-05T11:17:16.270475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:16.270475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67iN6IT05olHbP9sDS0M7zzVpzv9QQFrMAq7s6d1URuh07M4V25ijOfSQ3nIluTaFb1MnFH2axDU4Gog5TvZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:16.271011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0c4b272bbe0cac852c9208137a4f60fa498b7c7c0a54ba26919da8acb17c2a9","sha256:c22b358bede01d2810ac1a68c4d600ef530d3b29594cbaa722b2c2e56eccb259"],"state_sha256":"822a3f7a533ec2ea4bee8839d003ba7f16b000dca2bc3ea3da233a543de0c732"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSIJJEO1pLeeGNdmQ9AsqyqOfc3gGIui9zJzgYhmeJJvxpdGpMAfFR6DNJkdjUPzTlXowyxaunMpaAktpp5mDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:47:55.993662Z","bundle_sha256":"2f83edb38a134d956eb0134c6464f9e3b864b804678667813e02a933b54547fc"}}