{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RGAZL6Y3TXRPHISY3OQZZ65YAL","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":"882d2403fc3f3636639630f3865bf95e12e2359f6e6d6e6e99882083de2f906f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T02:40:19Z","title_canon_sha256":"d86aff7e2f7a1a20b274adaa45d18a8551aaaba93184415a32a177c01465bbe4"},"schema_version":"1.0","source":{"id":"2412.20662","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20662","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20662v3","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20662","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"RGAZL6Y3TXRP","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"RGAZL6Y3TXRPHISY","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"RGAZL6Y3","created_at":"2026-07-05T11:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:d3cd55579ee894d55fa26bf245b34da1b5a95289f2005d5e93fb3cc893627d61","target":"graph","created_at":"2026-07-05T11:12:23Z","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/2412.20662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained foundation models have recently made significant progress in table-related tasks such as table understanding and reasoning. However, recognizing the structure and content of unstructured tables using Vision Large Language Models (VLLMs) remains under-explored. To bridge this gap, we propose a benchmark based on a hierarchical design philosophy to evaluate the recognition capabilities of VLLMs in training-free scenarios. Through in-depth evaluations, we find that low-quality image input is a significant bottleneck in the recognition process. Drawing inspiration from this, we propose","authors_text":"Feiyang Xu, Mingyue Cheng, Qingyang Mao, Xin Li, Yitong Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T02:40:19Z","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20662","kind":"arxiv","version":3},"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":"sha256:44e57bf315858c975f95c5f216505e40f25665aa509fbfbb80ffa0f302aa8369","target":"record","created_at":"2026-07-05T11:12:23Z","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":"882d2403fc3f3636639630f3865bf95e12e2359f6e6d6e6e99882083de2f906f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T02:40:19Z","title_canon_sha256":"d86aff7e2f7a1a20b274adaa45d18a8551aaaba93184415a32a177c01465bbe4"},"schema_version":"1.0","source":{"id":"2412.20662","kind":"arxiv","version":3}},"canonical_sha256":"898195fb1b9de2f3a258dba19cfbb802d7105d59fe378cde4652ce180712d6bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"898195fb1b9de2f3a258dba19cfbb802d7105d59fe378cde4652ce180712d6bf","first_computed_at":"2026-07-05T11:12:23.819671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:23.819671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HagdMaBIvP8XcTGm2fev5EB2uujJ0/CO7rFWJ/V4fQUiye/LA8FSeKk/HOp4Tb+smoFZUGgs+MiQfdiLAGH7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:23.820224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20662","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44e57bf315858c975f95c5f216505e40f25665aa509fbfbb80ffa0f302aa8369","sha256:d3cd55579ee894d55fa26bf245b34da1b5a95289f2005d5e93fb3cc893627d61"],"state_sha256":"c232ccf65e4d0d7829714c717d413ab90658bc63c5956bc13c66a18a850c1ff2"}