{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UEJSN4GRVU26UAWNYCYNIE3S5L","short_pith_number":"pith:UEJSN4GR","schema_version":"1.0","canonical_sha256":"a11326f0d1ad35ea02cdc0b0d41372ead6b6c274a5aa20cb3a1c38d2edbe3f4b","source":{"kind":"arxiv","id":"2503.12345","version":3},"attestation_state":"computed","paper":{"title":"General Table Question Answering via Answer-Formula Joint Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hangyu Mao, Richong Zhang, Zhijie Nie, Zhongyuan Wang","submitted_at":"2025-03-16T03:51:06Z","abstract_excerpt":"Advanced table question answering (TableQA) methods prompt large language models (LLMs) to generate answer text, SQL query, Python code, or custom operation, which impressively improve the complex reasoning problems in the TableQA task. However, these methods lack the versatility to cope with specific question types or table structures. In contrast, the Spreadsheet Formula, the widely used and well-defined operation language for tabular data, has not been thoroughly explored to solve TableQA. In this paper, we first attempt to use the Formula as the executable representation for solving comple"},"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":"2503.12345","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-16T03:51:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5892260b148ac67c5311a5ca9692f49aa58fe3dd186581a5c95208bd069db434","abstract_canon_sha256":"4dd23e88c708e4aacaece4f445c49193e173ef04e30f591b52261bfe657c776b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:58.745981Z","signature_b64":"2E21JkzkbqCfJDAeLYm13jNd3rkclYowTnlT2l1HLdmv73W+uAzNPTlNnedYISEBEeVqTIE+59I+UPgCuwXoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a11326f0d1ad35ea02cdc0b0d41372ead6b6c274a5aa20cb3a1c38d2edbe3f4b","last_reissued_at":"2026-07-05T12:01:58.745288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:58.745288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General Table Question Answering via Answer-Formula Joint Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hangyu Mao, Richong Zhang, Zhijie Nie, Zhongyuan Wang","submitted_at":"2025-03-16T03:51:06Z","abstract_excerpt":"Advanced table question answering (TableQA) methods prompt large language models (LLMs) to generate answer text, SQL query, Python code, or custom operation, which impressively improve the complex reasoning problems in the TableQA task. However, these methods lack the versatility to cope with specific question types or table structures. In contrast, the Spreadsheet Formula, the widely used and well-defined operation language for tabular data, has not been thoroughly explored to solve TableQA. In this paper, we first attempt to use the Formula as the executable representation for solving comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12345","kind":"arxiv","version":3},"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/2503.12345/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":"2503.12345","created_at":"2026-07-05T12:01:58.745390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12345v3","created_at":"2026-07-05T12:01:58.745390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12345","created_at":"2026-07-05T12:01:58.745390+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEJSN4GRVU26","created_at":"2026-07-05T12:01:58.745390+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEJSN4GRVU26UAWN","created_at":"2026-07-05T12:01:58.745390+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEJSN4GR","created_at":"2026-07-05T12:01:58.745390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11537","citing_title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30518","citing_title":"Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10335","citing_title":"PowerStep: Memory-Efficient Adaptive Optimization via $\\ell_p$-Norm Steepest Descent","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L","json":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L.json","graph_json":"https://pith.science/api/pith-number/UEJSN4GRVU26UAWNYCYNIE3S5L/graph.json","events_json":"https://pith.science/api/pith-number/UEJSN4GRVU26UAWNYCYNIE3S5L/events.json","paper":"https://pith.science/paper/UEJSN4GR"},"agent_actions":{"view_html":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L","download_json":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L.json","view_paper":"https://pith.science/paper/UEJSN4GR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12345&json=true","fetch_graph":"https://pith.science/api/pith-number/UEJSN4GRVU26UAWNYCYNIE3S5L/graph.json","fetch_events":"https://pith.science/api/pith-number/UEJSN4GRVU26UAWNYCYNIE3S5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L/action/storage_attestation","attest_author":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L/action/author_attestation","sign_citation":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L/action/citation_signature","submit_replication":"https://pith.science/pith/UEJSN4GRVU26UAWNYCYNIE3S5L/action/replication_record"}},"created_at":"2026-07-05T12:01:58.745390+00:00","updated_at":"2026-07-05T12:01:58.745390+00:00"}