{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWG2DE5DS2EBGDAZDWF44NMO6G","short_pith_number":"pith:WWG2DE5D","schema_version":"1.0","canonical_sha256":"b58da193a39688130c191d8bce358ef1986411bc2e12df3929e549dcb819c87f","source":{"kind":"arxiv","id":"2402.14361","version":2},"attestation_state":"computed","paper":{"title":"OpenTab: Advancing Large Language Models as Open-domain Table Reasoners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balasubramaniam Srinivasan, Christos Faloutsos, Chuan Lei, George Karypis, Huzefa Rangwala, Jiani Zhang, Kezhi Kong, Zhengyuan Shen","submitted_at":"2024-02-22T08:01:01Z","abstract_excerpt":"Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches relevant information to expand LLM's knowledge scope. However, existing textual-oriented retrieval-based LLMs are not ideal on structured table data due to diversified data modalities and large table sizes. In this work, we propose OpenTab, an open-domain table reasoning framework powered by LLMs. Overall, OpenTab leverages table retriever to fetch relevant"},"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":"2402.14361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T08:01:01Z","cross_cats_sorted":[],"title_canon_sha256":"8f60d8f857c59ae19c098e7f389a6494e4882899531c89880e0a0188f1230163","abstract_canon_sha256":"b561c3c3739168fd3e0976e89f6e5980014f4084164a315e0414bde1b95a13ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:33.931745Z","signature_b64":"pUrJ1dlJu9n6plpMfycKxCutX41Av+hLk2oDuBrcaXQKONvelKt9b2PsGVTVqVVXteuLrx7I6HhOhglWbONWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58da193a39688130c191d8bce358ef1986411bc2e12df3929e549dcb819c87f","last_reissued_at":"2026-07-05T08:07:33.931207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:33.931207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenTab: Advancing Large Language Models as Open-domain Table Reasoners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balasubramaniam Srinivasan, Christos Faloutsos, Chuan Lei, George Karypis, Huzefa Rangwala, Jiani Zhang, Kezhi Kong, Zhengyuan Shen","submitted_at":"2024-02-22T08:01:01Z","abstract_excerpt":"Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches relevant information to expand LLM's knowledge scope. However, existing textual-oriented retrieval-based LLMs are not ideal on structured table data due to diversified data modalities and large table sizes. In this work, we propose OpenTab, an open-domain table reasoning framework powered by LLMs. Overall, OpenTab leverages table retriever to fetch relevant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14361","kind":"arxiv","version":2},"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/2402.14361/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":"2402.14361","created_at":"2026-07-05T08:07:33.931269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14361v2","created_at":"2026-07-05T08:07:33.931269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14361","created_at":"2026-07-05T08:07:33.931269+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWG2DE5DS2EB","created_at":"2026-07-05T08:07:33.931269+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWG2DE5DS2EBGDAZ","created_at":"2026-07-05T08:07:33.931269+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWG2DE5D","created_at":"2026-07-05T08:07:33.931269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27164","citing_title":"Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18766","citing_title":"Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17225","citing_title":"A Multi-Agent Approach for Claim Verification from Tabular Data Documents","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G","json":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G.json","graph_json":"https://pith.science/api/pith-number/WWG2DE5DS2EBGDAZDWF44NMO6G/graph.json","events_json":"https://pith.science/api/pith-number/WWG2DE5DS2EBGDAZDWF44NMO6G/events.json","paper":"https://pith.science/paper/WWG2DE5D"},"agent_actions":{"view_html":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G","download_json":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G.json","view_paper":"https://pith.science/paper/WWG2DE5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14361&json=true","fetch_graph":"https://pith.science/api/pith-number/WWG2DE5DS2EBGDAZDWF44NMO6G/graph.json","fetch_events":"https://pith.science/api/pith-number/WWG2DE5DS2EBGDAZDWF44NMO6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G/action/storage_attestation","attest_author":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G/action/author_attestation","sign_citation":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G/action/citation_signature","submit_replication":"https://pith.science/pith/WWG2DE5DS2EBGDAZDWF44NMO6G/action/replication_record"}},"created_at":"2026-07-05T08:07:33.931269+00:00","updated_at":"2026-07-05T08:07:33.931269+00:00"}