{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YRXD3RIUJPFRUTMEMJXO76P72N","short_pith_number":"pith:YRXD3RIU","schema_version":"1.0","canonical_sha256":"c46e3dc5144bcb1a4d84626eeff9ffd34c6dad7dae6b1d06740cafc58fce31c6","source":{"kind":"arxiv","id":"2501.14877","version":1},"attestation_state":"computed","paper":{"title":"DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alice Ng, Kyle Lo, Li Lucy, Luca Soldaini, Neil T. Heffernan, Ryan Knight, Sami Baral","submitted_at":"2025-01-24T19:03:42Z","abstract_excerpt":"In real-world settings, vision language models (VLMs) should robustly handle naturalistic, noisy visual content as well as domain-specific language and concepts. For example, K-12 educators using digital learning platforms may need to examine and provide feedback across many images of students' math work. To assess the potential of VLMs to support educators in settings like this one, we introduce DrawEduMath, an English-language dataset of 2,030 images of students' handwritten responses to K-12 math problems. Teachers provided detailed annotations, including free-form descriptions of each imag"},"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":"2501.14877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T19:03:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f58dc4ac168dba230b2729b61ffd3fe960876521d07eb49723957ed44c773f8e","abstract_canon_sha256":"b517a1d958fce2160db8d3435cf61f9f33f4986411ed34bbd5edac9e850c5544"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:20.191462Z","signature_b64":"Mj1pY5MXO5pnKOiN6syJTXOb3UZ2u2e1JyO7pngUfgFNxYCpyL3SWyDTqUUfQwi61Vlf74q/srnHi62oGZJFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c46e3dc5144bcb1a4d84626eeff9ffd34c6dad7dae6b1d06740cafc58fce31c6","last_reissued_at":"2026-07-05T10:05:20.191040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:20.191040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alice Ng, Kyle Lo, Li Lucy, Luca Soldaini, Neil T. Heffernan, Ryan Knight, Sami Baral","submitted_at":"2025-01-24T19:03:42Z","abstract_excerpt":"In real-world settings, vision language models (VLMs) should robustly handle naturalistic, noisy visual content as well as domain-specific language and concepts. For example, K-12 educators using digital learning platforms may need to examine and provide feedback across many images of students' math work. To assess the potential of VLMs to support educators in settings like this one, we introduce DrawEduMath, an English-language dataset of 2,030 images of students' handwritten responses to K-12 math problems. Teachers provided detailed annotations, including free-form descriptions of each imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14877","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/2501.14877/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":"2501.14877","created_at":"2026-07-05T10:05:20.191099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14877v1","created_at":"2026-07-05T10:05:20.191099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14877","created_at":"2026-07-05T10:05:20.191099+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRXD3RIUJPFR","created_at":"2026-07-05T10:05:20.191099+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRXD3RIUJPFRUTME","created_at":"2026-07-05T10:05:20.191099+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRXD3RIU","created_at":"2026-07-05T10:05:20.191099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00868","citing_title":"MIDAL: A Dataset of Math Image Descriptions for Accessible Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N","json":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N.json","graph_json":"https://pith.science/api/pith-number/YRXD3RIUJPFRUTMEMJXO76P72N/graph.json","events_json":"https://pith.science/api/pith-number/YRXD3RIUJPFRUTMEMJXO76P72N/events.json","paper":"https://pith.science/paper/YRXD3RIU"},"agent_actions":{"view_html":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N","download_json":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N.json","view_paper":"https://pith.science/paper/YRXD3RIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14877&json=true","fetch_graph":"https://pith.science/api/pith-number/YRXD3RIUJPFRUTMEMJXO76P72N/graph.json","fetch_events":"https://pith.science/api/pith-number/YRXD3RIUJPFRUTMEMJXO76P72N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N/action/storage_attestation","attest_author":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N/action/author_attestation","sign_citation":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N/action/citation_signature","submit_replication":"https://pith.science/pith/YRXD3RIUJPFRUTMEMJXO76P72N/action/replication_record"}},"created_at":"2026-07-05T10:05:20.191099+00:00","updated_at":"2026-07-05T10:05:20.191099+00:00"}