{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UHMZMEWOBTW576I5WDVI5AZ2OC","short_pith_number":"pith:UHMZMEWO","schema_version":"1.0","canonical_sha256":"a1d99612ce0ceddff91db0ea8e833a7082b4ce87cd9543d0bb8fef202bf38c1c","source":{"kind":"arxiv","id":"2506.11684","version":1},"attestation_state":"computed","paper":{"title":"MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anshul Singh, Chris Biemann, Jan Strich","submitted_at":"2025-06-13T11:21:00Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable capabilities in interpreting visual layouts and text. However, a significant challenge remains in their ability to interpret robustly and reason over multi-tabular data presented as images, a common occurrence in real-world scenarios like web pages and digital documents. Existing benchmarks typically address single tables or non-visual data (text/structured). This leaves a critical gap: they don't assess the ability to parse diverse table images, correlate information across them, and perform multi-hop reasoning on the combined visual "},"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":"2506.11684","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T11:21:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78264f41cd4ba5127a0846c93e29cc84088127951fdd4ba03c8616045a814ba7","abstract_canon_sha256":"8b079a220cc8101e29487de0b296217f2c65d9a3fb7a5c2752d433a3b22f331d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:09.146198Z","signature_b64":"k/QwNb6D1nt4pijmIX4IOPPxBmTSoey6Rfx7g7Y/7ikvAzlayQXX097jBeMnL7jtaKoKohg4qVRuVUqiwV4bAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d99612ce0ceddff91db0ea8e833a7082b4ce87cd9543d0bb8fef202bf38c1c","last_reissued_at":"2026-07-05T11:21:09.145705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:09.145705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anshul Singh, Chris Biemann, Jan Strich","submitted_at":"2025-06-13T11:21:00Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable capabilities in interpreting visual layouts and text. However, a significant challenge remains in their ability to interpret robustly and reason over multi-tabular data presented as images, a common occurrence in real-world scenarios like web pages and digital documents. Existing benchmarks typically address single tables or non-visual data (text/structured). This leaves a critical gap: they don't assess the ability to parse diverse table images, correlate information across them, and perform multi-hop reasoning on the combined visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11684","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/2506.11684/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":"2506.11684","created_at":"2026-07-05T11:21:09.145766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11684v1","created_at":"2026-07-05T11:21:09.145766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11684","created_at":"2026-07-05T11:21:09.145766+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHMZMEWOBTW5","created_at":"2026-07-05T11:21:09.145766+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHMZMEWOBTW576I5","created_at":"2026-07-05T11:21:09.145766+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHMZMEWO","created_at":"2026-07-05T11:21:09.145766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23997","citing_title":"ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09671","citing_title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08146","citing_title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC","json":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC.json","graph_json":"https://pith.science/api/pith-number/UHMZMEWOBTW576I5WDVI5AZ2OC/graph.json","events_json":"https://pith.science/api/pith-number/UHMZMEWOBTW576I5WDVI5AZ2OC/events.json","paper":"https://pith.science/paper/UHMZMEWO"},"agent_actions":{"view_html":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC","download_json":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC.json","view_paper":"https://pith.science/paper/UHMZMEWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11684&json=true","fetch_graph":"https://pith.science/api/pith-number/UHMZMEWOBTW576I5WDVI5AZ2OC/graph.json","fetch_events":"https://pith.science/api/pith-number/UHMZMEWOBTW576I5WDVI5AZ2OC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/action/storage_attestation","attest_author":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/action/author_attestation","sign_citation":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/action/citation_signature","submit_replication":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/action/replication_record"}},"created_at":"2026-07-05T11:21:09.145766+00:00","updated_at":"2026-07-05T11:21:09.145766+00:00"}