{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2VUQAIRSOJVUW6KFF5EEFFZI5O","short_pith_number":"pith:2VUQAIRS","schema_version":"1.0","canonical_sha256":"d569002232726b4b79452f48429728eba8dd93f1e07363466f7833069360038d","source":{"kind":"arxiv","id":"2501.01631","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Data Analysis with Pre-trained Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Boyu Xiao, Chen Liang, Donghua Yang, Hongzhi Wang, Tianle Zhang, Wenqi Wang, Yuqing Yang, Zheng Liang, Zhiyu Liang","submitted_at":"2025-01-03T04:38:51Z","abstract_excerpt":"Data analysis focuses on harnessing advanced statistics, programming, and machine learning techniques to extract valuable insights from vast datasets. An increasing volume and variety of research emerged, addressing datasets of diverse modalities, formats, scales, and resolutions across various industries. However, experienced data analysts often find themselves overwhelmed by intricate details in ad-hoc solutions or attempts to extract the semantics of grounded data properly. This makes it difficult to maintain and scale to more complex systems. Pre-trained foundation models (PFMs), grounded "},"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":"2501.01631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-01-03T04:38:51Z","cross_cats_sorted":[],"title_canon_sha256":"f045facf7f293fd1c1d708bf7b0da33572618c4c2e2109e7f7920a2cf15438c4","abstract_canon_sha256":"b88f7ab769b14cda8dfd7e858bfbf38a12c53329bca8c8b61e4b88f7ac4794ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:27.955065Z","signature_b64":"HvOeNY4ulAKWWukplMN9q3+Sqm7Bh8jLnxGr/CxBrppVrGxMtnpVuz2z6ar5lS9mqH49Osm11JdvLrpY5l95Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d569002232726b4b79452f48429728eba8dd93f1e07363466f7833069360038d","last_reissued_at":"2026-07-05T09:56:27.954633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:27.954633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Data Analysis with Pre-trained Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Boyu Xiao, Chen Liang, Donghua Yang, Hongzhi Wang, Tianle Zhang, Wenqi Wang, Yuqing Yang, Zheng Liang, Zhiyu Liang","submitted_at":"2025-01-03T04:38:51Z","abstract_excerpt":"Data analysis focuses on harnessing advanced statistics, programming, and machine learning techniques to extract valuable insights from vast datasets. An increasing volume and variety of research emerged, addressing datasets of diverse modalities, formats, scales, and resolutions across various industries. However, experienced data analysts often find themselves overwhelmed by intricate details in ad-hoc solutions or attempts to extract the semantics of grounded data properly. This makes it difficult to maintain and scale to more complex systems. Pre-trained foundation models (PFMs), grounded "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01631","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/2501.01631/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":"2501.01631","created_at":"2026-07-05T09:56:27.954689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01631v1","created_at":"2026-07-05T09:56:27.954689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01631","created_at":"2026-07-05T09:56:27.954689+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VUQAIRSOJVU","created_at":"2026-07-05T09:56:27.954689+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VUQAIRSOJVUW6KF","created_at":"2026-07-05T09:56:27.954689+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VUQAIRS","created_at":"2026-07-05T09:56:27.954689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O","json":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O.json","graph_json":"https://pith.science/api/pith-number/2VUQAIRSOJVUW6KFF5EEFFZI5O/graph.json","events_json":"https://pith.science/api/pith-number/2VUQAIRSOJVUW6KFF5EEFFZI5O/events.json","paper":"https://pith.science/paper/2VUQAIRS"},"agent_actions":{"view_html":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O","download_json":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O.json","view_paper":"https://pith.science/paper/2VUQAIRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01631&json=true","fetch_graph":"https://pith.science/api/pith-number/2VUQAIRSOJVUW6KFF5EEFFZI5O/graph.json","fetch_events":"https://pith.science/api/pith-number/2VUQAIRSOJVUW6KFF5EEFFZI5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O/action/storage_attestation","attest_author":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O/action/author_attestation","sign_citation":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O/action/citation_signature","submit_replication":"https://pith.science/pith/2VUQAIRSOJVUW6KFF5EEFFZI5O/action/replication_record"}},"created_at":"2026-07-05T09:56:27.954689+00:00","updated_at":"2026-07-05T09:56:27.954689+00:00"}