{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JMFEBPZM57DBLGZ76BNTPZNKJF","short_pith_number":"pith:JMFEBPZM","schema_version":"1.0","canonical_sha256":"4b0a40bf2cefc6159b3ff05b37e5aa4971ee402a2a06495137875df6a0bdad00","source":{"kind":"arxiv","id":"2506.15883","version":1},"attestation_state":"computed","paper":{"title":"Semantic Scaffolding: Augmenting Textual Structures with Domain-Specific Groupings for Accessible Data Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Arvind Satyanarayan, Daniel Hajas, Isabella Pedraza Pineros, Jonathan Zong, Mengzhu Katie Chen","submitted_at":"2025-06-18T21:18:10Z","abstract_excerpt":"Drawing connections between interesting groupings of data and their real-world meaning is an important, yet difficult, part of encountering a new dataset. A lay reader might see an interesting visual pattern in a chart but lack the domain expertise to explain its meaning. Or, a reader might be familiar with a real-world concept but struggle to express it in terms of a dataset's fields. In response, we developed semantic scaffolding, a technique for using domain-specific information from large language models (LLMs) to identify, explain, and formalize semantically meaningful data groupings. We "},"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":"2506.15883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-18T21:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"d39007d7dd96dd5f56d190d5aebe4303a7f89fce4074b218cc0ddc110dea415c","abstract_canon_sha256":"94bdb3646b85e253487cb84b3356176e647e3848476ce598b3fa5dfa754162b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:25.732545Z","signature_b64":"DgsRtlEigB6TSPm9oqCfxM5OvIWlII1Yoc/C7BSXg9PDOLUTbBlW2xYDAIjwogCVe4NzndwPX4QncJ0/M81lAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0a40bf2cefc6159b3ff05b37e5aa4971ee402a2a06495137875df6a0bdad00","last_reissued_at":"2026-07-05T11:24:25.732064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:25.732064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Scaffolding: Augmenting Textual Structures with Domain-Specific Groupings for Accessible Data Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Arvind Satyanarayan, Daniel Hajas, Isabella Pedraza Pineros, Jonathan Zong, Mengzhu Katie Chen","submitted_at":"2025-06-18T21:18:10Z","abstract_excerpt":"Drawing connections between interesting groupings of data and their real-world meaning is an important, yet difficult, part of encountering a new dataset. A lay reader might see an interesting visual pattern in a chart but lack the domain expertise to explain its meaning. Or, a reader might be familiar with a real-world concept but struggle to express it in terms of a dataset's fields. In response, we developed semantic scaffolding, a technique for using domain-specific information from large language models (LLMs) to identify, explain, and formalize semantically meaningful data groupings. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15883","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/2506.15883/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":"2506.15883","created_at":"2026-07-05T11:24:25.732122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15883v1","created_at":"2026-07-05T11:24:25.732122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15883","created_at":"2026-07-05T11:24:25.732122+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMFEBPZM57DB","created_at":"2026-07-05T11:24:25.732122+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMFEBPZM57DBLGZ7","created_at":"2026-07-05T11:24:25.732122+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMFEBPZM","created_at":"2026-07-05T11:24:25.732122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09782","citing_title":"Cohort-based Semantic Labeling: AI-Enabled Recovery of Visualization Semantics from Deployed SVGs","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF","json":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF.json","graph_json":"https://pith.science/api/pith-number/JMFEBPZM57DBLGZ76BNTPZNKJF/graph.json","events_json":"https://pith.science/api/pith-number/JMFEBPZM57DBLGZ76BNTPZNKJF/events.json","paper":"https://pith.science/paper/JMFEBPZM"},"agent_actions":{"view_html":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF","download_json":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF.json","view_paper":"https://pith.science/paper/JMFEBPZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15883&json=true","fetch_graph":"https://pith.science/api/pith-number/JMFEBPZM57DBLGZ76BNTPZNKJF/graph.json","fetch_events":"https://pith.science/api/pith-number/JMFEBPZM57DBLGZ76BNTPZNKJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF/action/storage_attestation","attest_author":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF/action/author_attestation","sign_citation":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF/action/citation_signature","submit_replication":"https://pith.science/pith/JMFEBPZM57DBLGZ76BNTPZNKJF/action/replication_record"}},"created_at":"2026-07-05T11:24:25.732122+00:00","updated_at":"2026-07-05T11:24:25.732122+00:00"}