{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WK4XO7IFCRGPNDONVHWWGR3UXA","short_pith_number":"pith:WK4XO7IF","schema_version":"1.0","canonical_sha256":"b2b9777d05144cf68dcda9ed634774b83b82252f0c829318d1caf80bf6702474","source":{"kind":"arxiv","id":"2607.11207","version":1},"attestation_state":"computed","paper":{"title":"ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Hu, Enjie Liu, Jianxin Zhang, Juntao Li, Mochi Gao, Pei Guo, Ruichao Zhong, Yunzhi Tan, Zang Li","submitted_at":"2026-07-13T07:58:57Z","abstract_excerpt":"Table-based reasoning with large language models (LLMs), which requires reasoning based on natural language questions and structured tabular data, has gained widespread attention. However, a series of issues still constrain the application of this task. The previous approaches suffered from significant performance degradation when faced with large tables due to the difficulty of long text modeling and the limitation of input length for LLMs. The text-to-SQL approach is used to efficiently extract key information from tables and generate smaller sub-tables. However, tabular data, especially web"},"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":"2607.11207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-13T07:58:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54bd3ad878ab5e2969c97b665db4f909e2395c191eeff55252f4c8571238d6e2","abstract_canon_sha256":"bb9ed988d149ec0326fa937f214c003678e5948af06be0aa847799a8038772e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:22.396526Z","signature_b64":"hzAt2GETzcxqrRhEn/W/oM/gag4NDqVMfUq2dF1Wd+YyHIXmhm+LbjpcbzCztfpq4Ir1DF1eFJKArGm4Pxb4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b9777d05144cf68dcda9ed634774b83b82252f0c829318d1caf80bf6702474","last_reissued_at":"2026-07-14T01:22:22.395215Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:22.395215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Hu, Enjie Liu, Jianxin Zhang, Juntao Li, Mochi Gao, Pei Guo, Ruichao Zhong, Yunzhi Tan, Zang Li","submitted_at":"2026-07-13T07:58:57Z","abstract_excerpt":"Table-based reasoning with large language models (LLMs), which requires reasoning based on natural language questions and structured tabular data, has gained widespread attention. However, a series of issues still constrain the application of this task. The previous approaches suffered from significant performance degradation when faced with large tables due to the difficulty of long text modeling and the limitation of input length for LLMs. The text-to-SQL approach is used to efficiently extract key information from tables and generate smaller sub-tables. However, tabular data, especially web"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11207","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/2607.11207/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":"2607.11207","created_at":"2026-07-14T01:22:22.395704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11207v1","created_at":"2026-07-14T01:22:22.395704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11207","created_at":"2026-07-14T01:22:22.395704+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK4XO7IFCRGP","created_at":"2026-07-14T01:22:22.395704+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK4XO7IFCRGPNDON","created_at":"2026-07-14T01:22:22.395704+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK4XO7IF","created_at":"2026-07-14T01:22:22.395704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA","json":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA.json","graph_json":"https://pith.science/api/pith-number/WK4XO7IFCRGPNDONVHWWGR3UXA/graph.json","events_json":"https://pith.science/api/pith-number/WK4XO7IFCRGPNDONVHWWGR3UXA/events.json","paper":"https://pith.science/paper/WK4XO7IF"},"agent_actions":{"view_html":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA","download_json":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA.json","view_paper":"https://pith.science/paper/WK4XO7IF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11207&json=true","fetch_graph":"https://pith.science/api/pith-number/WK4XO7IFCRGPNDONVHWWGR3UXA/graph.json","fetch_events":"https://pith.science/api/pith-number/WK4XO7IFCRGPNDONVHWWGR3UXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA/action/storage_attestation","attest_author":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA/action/author_attestation","sign_citation":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA/action/citation_signature","submit_replication":"https://pith.science/pith/WK4XO7IFCRGPNDONVHWWGR3UXA/action/replication_record"}},"created_at":"2026-07-14T01:22:22.395704+00:00","updated_at":"2026-07-14T01:22:22.395704+00:00"}