{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XSNSQWLIB76MR4C4M3TKMKQZOF","short_pith_number":"pith:XSNSQWLI","schema_version":"1.0","canonical_sha256":"bc9b2859680ffcc8f05c66e6a62a19717652d755370f2db01b5d7d9ad53bd2d1","source":{"kind":"arxiv","id":"2507.08283","version":1},"attestation_state":"computed","paper":{"title":"TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Gang Chen, Guanyu Jiang, Huan Li, Ke Chen, Lidan Shou, Lingxi Cui","submitted_at":"2025-07-11T03:16:55Z","abstract_excerpt":"The rise of LLM has enabled natural language-based table assistants, but existing systems assume users already have a well-formed table, neglecting the challenge of table discovery in large-scale table pools. To address this, we introduce TableCopilot, an LLM-powered assistant for interactive, precise, and personalized table discovery and analysis. We define a novel scenario, nlcTD, where users provide both a natural language condition and a query table, enabling intuitive and flexible table discovery for users of all expertise levels. To handle this, we propose Crofuma, a cross-fusion-based a"},"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":"2507.08283","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-11T03:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"1e3e447d91c353968be55ae7e4fd82f500fa4bed67e740fc56e46ec62d7337fd","abstract_canon_sha256":"5306ed4c0f332852d5978d4d299c6ba25be188000af48c42d78b4a9cdbd3f4df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:20.710963Z","signature_b64":"aazsZW1JgD2ug68jN/zSAIwPUngfUqePLFVIlSwfb0MqrFSJxpmkSgzH9xM7vESoHitHP041mzgQZhdXkldhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc9b2859680ffcc8f05c66e6a62a19717652d755370f2db01b5d7d9ad53bd2d1","last_reissued_at":"2026-07-05T11:35:20.710478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:20.710478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Gang Chen, Guanyu Jiang, Huan Li, Ke Chen, Lidan Shou, Lingxi Cui","submitted_at":"2025-07-11T03:16:55Z","abstract_excerpt":"The rise of LLM has enabled natural language-based table assistants, but existing systems assume users already have a well-formed table, neglecting the challenge of table discovery in large-scale table pools. To address this, we introduce TableCopilot, an LLM-powered assistant for interactive, precise, and personalized table discovery and analysis. We define a novel scenario, nlcTD, where users provide both a natural language condition and a query table, enabling intuitive and flexible table discovery for users of all expertise levels. To handle this, we propose Crofuma, a cross-fusion-based a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08283","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/2507.08283/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":"2507.08283","created_at":"2026-07-05T11:35:20.710536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08283v1","created_at":"2026-07-05T11:35:20.710536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08283","created_at":"2026-07-05T11:35:20.710536+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSNSQWLIB76M","created_at":"2026-07-05T11:35:20.710536+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSNSQWLIB76MR4C4","created_at":"2026-07-05T11:35:20.710536+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSNSQWLI","created_at":"2026-07-05T11:35:20.710536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22758","citing_title":"RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF","json":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF.json","graph_json":"https://pith.science/api/pith-number/XSNSQWLIB76MR4C4M3TKMKQZOF/graph.json","events_json":"https://pith.science/api/pith-number/XSNSQWLIB76MR4C4M3TKMKQZOF/events.json","paper":"https://pith.science/paper/XSNSQWLI"},"agent_actions":{"view_html":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF","download_json":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF.json","view_paper":"https://pith.science/paper/XSNSQWLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08283&json=true","fetch_graph":"https://pith.science/api/pith-number/XSNSQWLIB76MR4C4M3TKMKQZOF/graph.json","fetch_events":"https://pith.science/api/pith-number/XSNSQWLIB76MR4C4M3TKMKQZOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF/action/storage_attestation","attest_author":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF/action/author_attestation","sign_citation":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF/action/citation_signature","submit_replication":"https://pith.science/pith/XSNSQWLIB76MR4C4M3TKMKQZOF/action/replication_record"}},"created_at":"2026-07-05T11:35:20.710536+00:00","updated_at":"2026-07-05T11:35:20.710536+00:00"}