{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JI4L5RVKMSXS3NHQX47CWTQHO3","short_pith_number":"pith:JI4L5RVK","schema_version":"1.0","canonical_sha256":"4a38bec6aa64af2db4f0bf3e2b4e0776cb401138a2acd2bb46a1641132ef7ce5","source":{"kind":"arxiv","id":"2412.00846","version":1},"attestation_state":"computed","paper":{"title":"Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Dharmadhikari, Atharva Marathe, Avinash Anand, Harshil Mital, Harsh Parimal Popat, Kritarth Prasad, Rajiv Ratn Shah, Raj Jaiswal, Roger Zimmermann","submitted_at":"2024-12-01T15:19:23Z","abstract_excerpt":"This paper presents GPSM4K, a comprehensive geometry multimodal dataset tailored to augment the problem-solving capabilities of Large Vision Language Models (LVLMs). GPSM4K encompasses 2157 multimodal question-answer pairs manually extracted from mathematics textbooks spanning grades 7-12 and is further augmented to 5340 problems, consisting of both numerical and theorem-proving questions. In contrast to PGPS9k, Geometry3K, and Geo170K which feature only objective-type questions, GPSM4K offers detailed step-by-step solutions in a consistent format, facilitating a comprehensive evaluation of pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.00846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-01T15:19:23Z","cross_cats_sorted":[],"title_canon_sha256":"dffdccebbb468b1c25b12210f3c6c66dd9f988dd3b08f54ac22762ae5f0dbd06","abstract_canon_sha256":"e30f671151f58a891f474ec49a003aba038778898a10f76346574769fedea5d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:49.180279Z","signature_b64":"zcYvrmGzlVuJAPnnInSFZpf7n/7pHT3R7LpN2CFhJg+NVTvAyyjSzunk0IE2lQ//Pa5fm1c8YJtT+XkCdI0sAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a38bec6aa64af2db4f0bf3e2b4e0776cb401138a2acd2bb46a1641132ef7ce5","last_reissued_at":"2026-07-05T09:42:49.179740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:49.179740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Dharmadhikari, Atharva Marathe, Avinash Anand, Harshil Mital, Harsh Parimal Popat, Kritarth Prasad, Rajiv Ratn Shah, Raj Jaiswal, Roger Zimmermann","submitted_at":"2024-12-01T15:19:23Z","abstract_excerpt":"This paper presents GPSM4K, a comprehensive geometry multimodal dataset tailored to augment the problem-solving capabilities of Large Vision Language Models (LVLMs). GPSM4K encompasses 2157 multimodal question-answer pairs manually extracted from mathematics textbooks spanning grades 7-12 and is further augmented to 5340 problems, consisting of both numerical and theorem-proving questions. In contrast to PGPS9k, Geometry3K, and Geo170K which feature only objective-type questions, GPSM4K offers detailed step-by-step solutions in a consistent format, facilitating a comprehensive evaluation of pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00846","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/2412.00846/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.00846","created_at":"2026-07-05T09:42:49.179807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00846v1","created_at":"2026-07-05T09:42:49.179807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00846","created_at":"2026-07-05T09:42:49.179807+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI4L5RVKMSXS","created_at":"2026-07-05T09:42:49.179807+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI4L5RVKMSXS3NHQ","created_at":"2026-07-05T09:42:49.179807+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI4L5RVK","created_at":"2026-07-05T09:42:49.179807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.06226","citing_title":"GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3","json":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3.json","graph_json":"https://pith.science/api/pith-number/JI4L5RVKMSXS3NHQX47CWTQHO3/graph.json","events_json":"https://pith.science/api/pith-number/JI4L5RVKMSXS3NHQX47CWTQHO3/events.json","paper":"https://pith.science/paper/JI4L5RVK"},"agent_actions":{"view_html":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3","download_json":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3.json","view_paper":"https://pith.science/paper/JI4L5RVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00846&json=true","fetch_graph":"https://pith.science/api/pith-number/JI4L5RVKMSXS3NHQX47CWTQHO3/graph.json","fetch_events":"https://pith.science/api/pith-number/JI4L5RVKMSXS3NHQX47CWTQHO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3/action/storage_attestation","attest_author":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3/action/author_attestation","sign_citation":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3/action/citation_signature","submit_replication":"https://pith.science/pith/JI4L5RVKMSXS3NHQX47CWTQHO3/action/replication_record"}},"created_at":"2026-07-05T09:42:49.179807+00:00","updated_at":"2026-07-05T09:42:49.179807+00:00"}