{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UHMZMEWOBTW576I5WDVI5AZ2OC","short_pith_number":"pith:UHMZMEWO","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"},"canonical_sha256":"a1d99612ce0ceddff91db0ea8e833a7082b4ce87cd9543d0bb8fef202bf38c1c","source":{"kind":"arxiv","id":"2506.11684","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11684","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11684v1","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11684","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"UHMZMEWOBTW5","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"UHMZMEWOBTW576I5","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"UHMZMEWO","created_at":"2026-07-05T11:21:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UHMZMEWOBTW576I5WDVI5AZ2OC","target":"record","payload":{"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"},"canonical_sha256":"a1d99612ce0ceddff91db0ea8e833a7082b4ce87cd9543d0bb8fef202bf38c1c","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"},"source_kind":"arxiv","source_id":"2506.11684","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":"2026-07-05T11:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HSWpCxcFHZQUFvVLDtnCEhYNROxI9nb8rjVoBf73Ovt5Npe3p+7HUF1D+2RULnTmE9C2MymeVIoULxnOGOJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:13:48.740506Z"},"content_sha256":"61601f65c9f1e43b77b3608e7dea425f24559f1af73521162921fb7f65413aa0","schema_version":"1.0","event_id":"sha256:61601f65c9f1e43b77b3608e7dea425f24559f1af73521162921fb7f65413aa0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UHMZMEWOBTW576I5WDVI5AZ2OC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JKGhXfmM7tzr8jOKzfLFBvmAMdyxA/7Nh3gFMPuISg6Fu3f8KVK1SRTcocBsocyQbNqgAUcyGAUTCdx0xxJAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:13:48.741464Z"},"content_sha256":"35a0239e2f28dd5ba654ce40c829d7ba5439e96eccdfb64c9e47ea052565c697","schema_version":"1.0","event_id":"sha256:35a0239e2f28dd5ba654ce40c829d7ba5439e96eccdfb64c9e47ea052565c697"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/bundle.json","state_url":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/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":"2026-08-08T13:13:48Z","links":{"resolver":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC","bundle":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/bundle.json","state":"https://pith.science/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHMZMEWOBTW576I5WDVI5AZ2OC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UHMZMEWOBTW576I5WDVI5AZ2OC","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":"8b079a220cc8101e29487de0b296217f2c65d9a3fb7a5c2752d433a3b22f331d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T11:21:00Z","title_canon_sha256":"78264f41cd4ba5127a0846c93e29cc84088127951fdd4ba03c8616045a814ba7"},"schema_version":"1.0","source":{"id":"2506.11684","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11684","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11684v1","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11684","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"UHMZMEWOBTW5","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"UHMZMEWOBTW576I5","created_at":"2026-07-05T11:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"UHMZMEWO","created_at":"2026-07-05T11:21:09Z"}],"graph_snapshots":[{"event_id":"sha256:35a0239e2f28dd5ba654ce40c829d7ba5439e96eccdfb64c9e47ea052565c697","target":"graph","created_at":"2026-07-05T11:21:09Z","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/2506.11684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Anshul Singh, Chris Biemann, Jan Strich","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T11:21:00Z","title":"MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11684","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":"sha256:61601f65c9f1e43b77b3608e7dea425f24559f1af73521162921fb7f65413aa0","target":"record","created_at":"2026-07-05T11:21:09Z","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":"8b079a220cc8101e29487de0b296217f2c65d9a3fb7a5c2752d433a3b22f331d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T11:21:00Z","title_canon_sha256":"78264f41cd4ba5127a0846c93e29cc84088127951fdd4ba03c8616045a814ba7"},"schema_version":"1.0","source":{"id":"2506.11684","kind":"arxiv","version":1}},"canonical_sha256":"a1d99612ce0ceddff91db0ea8e833a7082b4ce87cd9543d0bb8fef202bf38c1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1d99612ce0ceddff91db0ea8e833a7082b4ce87cd9543d0bb8fef202bf38c1c","first_computed_at":"2026-07-05T11:21:09.145705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:09.145705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k/QwNb6D1nt4pijmIX4IOPPxBmTSoey6Rfx7g7Y/7ikvAzlayQXX097jBeMnL7jtaKoKohg4qVRuVUqiwV4bAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:09.146198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11684","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61601f65c9f1e43b77b3608e7dea425f24559f1af73521162921fb7f65413aa0","sha256:35a0239e2f28dd5ba654ce40c829d7ba5439e96eccdfb64c9e47ea052565c697"],"state_sha256":"67949c98e1095ef7c9e564c68b54cf1b781cf0636709dd7cec884d487dea0516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2pKIMh8BzkaeZd6cJvNgvD7RoV5FdRcsZhzEHctALsQNoYkWpp8SmNWomZ5X3wxV6t5PG+l2zQR0oWntLtiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:13:48.747429Z","bundle_sha256":"5a2d4322b20a91d8e1e73e3b2859f061410fb1fd4af1c152167ebde136d247fa"}}