{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CXXVUFO3JIAVMU7XE7MQBHSN3M","short_pith_number":"pith:CXXVUFO3","schema_version":"1.0","canonical_sha256":"15ef5a15db4a015653f727d9009e4ddb2c04a99804e9d2ab585ab8deb9427b8d","source":{"kind":"arxiv","id":"2305.03458","version":1},"attestation_state":"computed","paper":{"title":"Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fangyu Lei, Jun Zhao, Kang Liu, Yifan Wei, Yuanzhe Zhang","submitted_at":"2023-05-05T12:00:58Z","abstract_excerpt":"Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task. Existing methods based on encoder-decoder framework employ a expression tree-based decoder to solve numerical reasoning problems. However, encoders rely more on Machine Reading Comprehension (MRC) methods, which take table serialization and text splicing as input, damaging the granularity relationship between table and text as well as the spatial structure information of table itself. In order to solve"},"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":"2305.03458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-05T12:00:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4225efd0151d11b1b45ee40d5060bdc326a4e56087066b9bdd74f726790da1e2","abstract_canon_sha256":"0f46db02db916c18516336899f1eef9e868d844cd1572807133d16c48974c45b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:23.521003Z","signature_b64":"8NRMI7pcoeAtHR3iKciE4MmafQWLVZChoHq2deAr81iZ6MDham7fea52Un6KTF9PXrlZxoZHIpXz8/DmAAVBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15ef5a15db4a015653f727d9009e4ddb2c04a99804e9d2ab585ab8deb9427b8d","last_reissued_at":"2026-07-05T06:07:23.520458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:23.520458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fangyu Lei, Jun Zhao, Kang Liu, Yifan Wei, Yuanzhe Zhang","submitted_at":"2023-05-05T12:00:58Z","abstract_excerpt":"Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task. Existing methods based on encoder-decoder framework employ a expression tree-based decoder to solve numerical reasoning problems. However, encoders rely more on Machine Reading Comprehension (MRC) methods, which take table serialization and text splicing as input, damaging the granularity relationship between table and text as well as the spatial structure information of table itself. In order to solve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03458","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/2305.03458/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":"2305.03458","created_at":"2026-07-05T06:07:23.520545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03458v1","created_at":"2026-07-05T06:07:23.520545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03458","created_at":"2026-07-05T06:07:23.520545+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXXVUFO3JIAV","created_at":"2026-07-05T06:07:23.520545+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXXVUFO3JIAVMU7X","created_at":"2026-07-05T06:07:23.520545+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXXVUFO3","created_at":"2026-07-05T06:07:23.520545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03489","citing_title":"CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M","json":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M.json","graph_json":"https://pith.science/api/pith-number/CXXVUFO3JIAVMU7XE7MQBHSN3M/graph.json","events_json":"https://pith.science/api/pith-number/CXXVUFO3JIAVMU7XE7MQBHSN3M/events.json","paper":"https://pith.science/paper/CXXVUFO3"},"agent_actions":{"view_html":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M","download_json":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M.json","view_paper":"https://pith.science/paper/CXXVUFO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03458&json=true","fetch_graph":"https://pith.science/api/pith-number/CXXVUFO3JIAVMU7XE7MQBHSN3M/graph.json","fetch_events":"https://pith.science/api/pith-number/CXXVUFO3JIAVMU7XE7MQBHSN3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M/action/storage_attestation","attest_author":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M/action/author_attestation","sign_citation":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M/action/citation_signature","submit_replication":"https://pith.science/pith/CXXVUFO3JIAVMU7XE7MQBHSN3M/action/replication_record"}},"created_at":"2026-07-05T06:07:23.520545+00:00","updated_at":"2026-07-05T06:07:23.520545+00:00"}