{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MUOQ3FOCG7C3RGUCPRSWVPJBN2","short_pith_number":"pith:MUOQ3FOC","schema_version":"1.0","canonical_sha256":"651d0d95c237c5b89a827c656abd216e9c8042856f906b019b7da9980b51ee0e","source":{"kind":"arxiv","id":"2508.05002","version":1},"attestation_state":"computed","paper":{"title":"AgenticData: An Agentic Data Analytics System for Heterogeneous Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Guoliang Li, Jingzhe Xu, Ji Sun, Peiyao Zhou, Yihui Ma, Yuan Li","submitted_at":"2025-08-07T03:33:59Z","abstract_excerpt":"Existing unstructured data analytics systems rely on experts to write code and manage complex analysis workflows, making them both expensive and time-consuming. To address these challenges, we introduce AgenticData, an innovative agentic data analytics system that allows users to simply pose natural language (NL) questions while autonomously analyzing data sources across multiple domains, including both unstructured and structured data. First, AgenticData employs a feedback-driven planning technique that automatically converts an NL query into a semantic plan composed of relational and semanti"},"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":"2508.05002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-08-07T03:33:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed2f5d23d8aa2ecaffaf9a44379f2e990d9c8b6c7f91521c3369a73ece9bfbaf","abstract_canon_sha256":"6b77c7cd94ee2037eda3bbd798f8d35a190c529ba01d0f37e4e77a6b798c2162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:05.400227Z","signature_b64":"fqjIbQoGIu0jElKOisaW6BS7/5lMswllUC1YMBP31xFd50YIMGy7KccdJ0CSfbbCkL+56MU1zfEKKteUUExpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"651d0d95c237c5b89a827c656abd216e9c8042856f906b019b7da9980b51ee0e","last_reissued_at":"2026-07-05T11:50:05.399787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:05.399787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgenticData: An Agentic Data Analytics System for Heterogeneous Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Guoliang Li, Jingzhe Xu, Ji Sun, Peiyao Zhou, Yihui Ma, Yuan Li","submitted_at":"2025-08-07T03:33:59Z","abstract_excerpt":"Existing unstructured data analytics systems rely on experts to write code and manage complex analysis workflows, making them both expensive and time-consuming. To address these challenges, we introduce AgenticData, an innovative agentic data analytics system that allows users to simply pose natural language (NL) questions while autonomously analyzing data sources across multiple domains, including both unstructured and structured data. First, AgenticData employs a feedback-driven planning technique that automatically converts an NL query into a semantic plan composed of relational and semanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05002","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/2508.05002/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":"2508.05002","created_at":"2026-07-05T11:50:05.399848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05002v1","created_at":"2026-07-05T11:50:05.399848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05002","created_at":"2026-07-05T11:50:05.399848+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUOQ3FOCG7C3","created_at":"2026-07-05T11:50:05.399848+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUOQ3FOCG7C3RGUC","created_at":"2026-07-05T11:50:05.399848+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUOQ3FOC","created_at":"2026-07-05T11:50:05.399848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2606.26627","citing_title":"Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01647","citing_title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04641","citing_title":"Bridge the Last-Mile Gap to Semantic Analytics: Compiling Natural-Language Queries into Semantic Operator Pipelines","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27571","citing_title":"Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06416","citing_title":"Unsupervised Skill Discovery for Agentic Data Analysis","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2509.00303","citing_title":"Access Paths for Efficient Ordering with Large Language Models","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2","json":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2.json","graph_json":"https://pith.science/api/pith-number/MUOQ3FOCG7C3RGUCPRSWVPJBN2/graph.json","events_json":"https://pith.science/api/pith-number/MUOQ3FOCG7C3RGUCPRSWVPJBN2/events.json","paper":"https://pith.science/paper/MUOQ3FOC"},"agent_actions":{"view_html":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2","download_json":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2.json","view_paper":"https://pith.science/paper/MUOQ3FOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05002&json=true","fetch_graph":"https://pith.science/api/pith-number/MUOQ3FOCG7C3RGUCPRSWVPJBN2/graph.json","fetch_events":"https://pith.science/api/pith-number/MUOQ3FOCG7C3RGUCPRSWVPJBN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2/action/storage_attestation","attest_author":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2/action/author_attestation","sign_citation":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2/action/citation_signature","submit_replication":"https://pith.science/pith/MUOQ3FOCG7C3RGUCPRSWVPJBN2/action/replication_record"}},"created_at":"2026-07-05T11:50:05.399848+00:00","updated_at":"2026-07-05T11:50:05.399848+00:00"}