{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YQ2DWLP7SMTCV3C42D2VMXIIGJ","short_pith_number":"pith:YQ2DWLP7","schema_version":"1.0","canonical_sha256":"c4343b2dff93262aec5cd0f5565d083261c5761afaa17c0c9a22fb8c2df20a04","source":{"kind":"arxiv","id":"2506.21393","version":1},"attestation_state":"computed","paper":{"title":"TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Junwen Zhang, Pu Chen, Yin Zhang","submitted_at":"2025-06-26T15:41:34Z","abstract_excerpt":"Multimodal understanding of tables in real-world contexts is challenging due to the complexity of structure, symbolic density, and visual degradation (blur, skew, watermarking, incomplete structures or fonts, multi-span or hierarchically nested layouts). Existing multimodal large language models (MLLMs) struggle with such WildStruct conditions, resulting in limited performance and poor generalization. To address these challenges, we propose TableMoE, a neuro-symbolic Mixture-of-Connector-Experts (MoCE) architecture specifically designed for robust, structured reasoning over multimodal table da"},"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":"2506.21393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-26T15:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d87f86a50f6c590cb276ace511d8919608ed695520c5fc2db53a24a957a0de1","abstract_canon_sha256":"6309eaf0c60be2f79ccfba01494e4b18c1a1469caf5f324e93a232495bd15886"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:44.896622Z","signature_b64":"+jeu5dLeWSGp1R2dk36K/jcreYKyB/2Y/GF8G0GI4+ziQ/mks3h1ZoUE1c27lwEw5/PTB3nqPGJ5uNd3FeUpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4343b2dff93262aec5cd0f5565d083261c5761afaa17c0c9a22fb8c2df20a04","last_reissued_at":"2026-07-05T11:27:44.896098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:44.896098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Junwen Zhang, Pu Chen, Yin Zhang","submitted_at":"2025-06-26T15:41:34Z","abstract_excerpt":"Multimodal understanding of tables in real-world contexts is challenging due to the complexity of structure, symbolic density, and visual degradation (blur, skew, watermarking, incomplete structures or fonts, multi-span or hierarchically nested layouts). Existing multimodal large language models (MLLMs) struggle with such WildStruct conditions, resulting in limited performance and poor generalization. To address these challenges, we propose TableMoE, a neuro-symbolic Mixture-of-Connector-Experts (MoCE) architecture specifically designed for robust, structured reasoning over multimodal table da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21393","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/2506.21393/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":"2506.21393","created_at":"2026-07-05T11:27:44.896157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21393v1","created_at":"2026-07-05T11:27:44.896157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21393","created_at":"2026-07-05T11:27:44.896157+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQ2DWLP7SMTC","created_at":"2026-07-05T11:27:44.896157+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQ2DWLP7SMTCV3C4","created_at":"2026-07-05T11:27:44.896157+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQ2DWLP7","created_at":"2026-07-05T11:27:44.896157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05955","citing_title":"TableVista: Benchmarking Multimodal Table Reasoning under Visual and Structural Complexity","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ","json":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ.json","graph_json":"https://pith.science/api/pith-number/YQ2DWLP7SMTCV3C42D2VMXIIGJ/graph.json","events_json":"https://pith.science/api/pith-number/YQ2DWLP7SMTCV3C42D2VMXIIGJ/events.json","paper":"https://pith.science/paper/YQ2DWLP7"},"agent_actions":{"view_html":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ","download_json":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ.json","view_paper":"https://pith.science/paper/YQ2DWLP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21393&json=true","fetch_graph":"https://pith.science/api/pith-number/YQ2DWLP7SMTCV3C42D2VMXIIGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YQ2DWLP7SMTCV3C42D2VMXIIGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ/action/storage_attestation","attest_author":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ/action/author_attestation","sign_citation":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ/action/citation_signature","submit_replication":"https://pith.science/pith/YQ2DWLP7SMTCV3C42D2VMXIIGJ/action/replication_record"}},"created_at":"2026-07-05T11:27:44.896157+00:00","updated_at":"2026-07-05T11:27:44.896157+00:00"}