{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X7RF5DOTJGSWFFHUPLUAM5Y2U7","short_pith_number":"pith:X7RF5DOT","canonical_record":{"source":{"id":"2408.08640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T10:11:05Z","cross_cats_sorted":[],"title_canon_sha256":"1dd03a8b0dce924814de3e5217b519a570944be39d7b0ee9f6fae3211444d75c","abstract_canon_sha256":"d7462c16cf43094086ec8a7afe2ae7254a54d9a5ebc49014a5f087226f5401be"},"schema_version":"1.0"},"canonical_sha256":"bfe25e8dd349a56294f47ae806771aa7cf94a63b53a37161a9db927697138430","source":{"kind":"arxiv","id":"2408.08640","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08640","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08640v2","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08640","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"X7RF5DOTJGSW","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"pith_short_16","alias_value":"X7RF5DOTJGSWFFHU","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"pith_short_8","alias_value":"X7RF5DOT","created_at":"2026-07-05T09:11:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X7RF5DOTJGSWFFHUPLUAM5Y2U7","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T10:11:05Z","cross_cats_sorted":[],"title_canon_sha256":"1dd03a8b0dce924814de3e5217b519a570944be39d7b0ee9f6fae3211444d75c","abstract_canon_sha256":"d7462c16cf43094086ec8a7afe2ae7254a54d9a5ebc49014a5f087226f5401be"},"schema_version":"1.0"},"canonical_sha256":"bfe25e8dd349a56294f47ae806771aa7cf94a63b53a37161a9db927697138430","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:28.630970Z","signature_b64":"KGMxDe5NkhVwwLVoPa5CshFGMiFpK/arv+kirtYa0/Wj5V8cekYS3JjxKGeS6FZc6rZUAOM+dzVW5xKq0ZyHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfe25e8dd349a56294f47ae806771aa7cf94a63b53a37161a9db927697138430","last_reissued_at":"2026-07-05T09:11:28.630457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:28.630457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08640","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":"2026-07-05T09:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M1my8GhMdYRRZj2DNMaEvk+Q/a3SlXgXcp5qm6xYq9Lu7PU77J4LZnbeMuuXXXpbzTiyIcezoLE+KD13slB6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T02:55:59.174305Z"},"content_sha256":"a25d859aa6b7515925ac07da48c1e90412dfbe43fedb80fc9b87f9dc8bc12e54","schema_version":"1.0","event_id":"sha256:a25d859aa6b7515925ac07da48c1e90412dfbe43fedb80fc9b87f9dc8bc12e54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X7RF5DOTJGSWFFHUPLUAM5Y2U7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jin Zeng, Wenwen Zhuang, Xiantao Zhang, Xin Huang","submitted_at":"2024-08-16T10:11:05Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solving, but MLLMs perform worse as information shifts from textual to visual modality. This decline is mainly due to their shortcomings in aligning images and text. To tackle aforementioned challenges, we propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment. This approach is designed to improve the mathematical reasoning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08640","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/2408.08640/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":"2026-07-05T09:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pN7dujGXjHvv6/TNFE+iWzXOE+ttCJbo++22ipLlxpvHnkIhO2x/Owk1DDHTY7GawdrOE21cFLuz3KI95wt/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T02:55:59.174698Z"},"content_sha256":"809ca1f1b235098ff8f072eedffe87f67626640b39ee718c8c3c71eff180619e","schema_version":"1.0","event_id":"sha256:809ca1f1b235098ff8f072eedffe87f67626640b39ee718c8c3c71eff180619e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7/bundle.json","state_url":"https://pith.science/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7/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":"2026-07-25T02:55:59Z","links":{"resolver":"https://pith.science/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7","bundle":"https://pith.science/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7/bundle.json","state":"https://pith.science/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7RF5DOTJGSWFFHUPLUAM5Y2U7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X7RF5DOTJGSWFFHUPLUAM5Y2U7","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":"d7462c16cf43094086ec8a7afe2ae7254a54d9a5ebc49014a5f087226f5401be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T10:11:05Z","title_canon_sha256":"1dd03a8b0dce924814de3e5217b519a570944be39d7b0ee9f6fae3211444d75c"},"schema_version":"1.0","source":{"id":"2408.08640","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08640","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08640v2","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08640","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"X7RF5DOTJGSW","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"pith_short_16","alias_value":"X7RF5DOTJGSWFFHU","created_at":"2026-07-05T09:11:28Z"},{"alias_kind":"pith_short_8","alias_value":"X7RF5DOT","created_at":"2026-07-05T09:11:28Z"}],"graph_snapshots":[{"event_id":"sha256:809ca1f1b235098ff8f072eedffe87f67626640b39ee718c8c3c71eff180619e","target":"graph","created_at":"2026-07-05T09:11:28Z","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/2408.08640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solving, but MLLMs perform worse as information shifts from textual to visual modality. This decline is mainly due to their shortcomings in aligning images and text. To tackle aforementioned challenges, we propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment. This approach is designed to improve the mathematical reasoning ","authors_text":"Jin Zeng, Wenwen Zhuang, Xiantao Zhang, Xin Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T10:11:05Z","title":"Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08640","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:a25d859aa6b7515925ac07da48c1e90412dfbe43fedb80fc9b87f9dc8bc12e54","target":"record","created_at":"2026-07-05T09:11:28Z","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":"d7462c16cf43094086ec8a7afe2ae7254a54d9a5ebc49014a5f087226f5401be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T10:11:05Z","title_canon_sha256":"1dd03a8b0dce924814de3e5217b519a570944be39d7b0ee9f6fae3211444d75c"},"schema_version":"1.0","source":{"id":"2408.08640","kind":"arxiv","version":2}},"canonical_sha256":"bfe25e8dd349a56294f47ae806771aa7cf94a63b53a37161a9db927697138430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfe25e8dd349a56294f47ae806771aa7cf94a63b53a37161a9db927697138430","first_computed_at":"2026-07-05T09:11:28.630457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:28.630457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KGMxDe5NkhVwwLVoPa5CshFGMiFpK/arv+kirtYa0/Wj5V8cekYS3JjxKGeS6FZc6rZUAOM+dzVW5xKq0ZyHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:28.630970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08640","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a25d859aa6b7515925ac07da48c1e90412dfbe43fedb80fc9b87f9dc8bc12e54","sha256:809ca1f1b235098ff8f072eedffe87f67626640b39ee718c8c3c71eff180619e"],"state_sha256":"a0413fb5cd114e63742a2e6f895fba3e69bdcc814289a84addc4a0933e8d2b44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qCx6DKKvN2UlJyeopuv8IMEBrZP2pocNTL1e7lRE+4iWS938mG8JulY1dOAEvY1QGKBIoHVcyzrzTpBbv/s0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T02:55:59.176830Z","bundle_sha256":"d60d9fe93c7b4a570fabf668e02d44c1a0e8640e0855940e71c8cd277d377546"}}