{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YHPCQ5QQBRE3IHGLXRVBA2IEZD","short_pith_number":"pith:YHPCQ5QQ","schema_version":"1.0","canonical_sha256":"c1de2876100c49b41ccbbc6a106904c8eacd877240e1c484d9dbe6e6608eafe2","source":{"kind":"arxiv","id":"2606.20072","version":1},"attestation_state":"computed","paper":{"title":"Source-Grounded Data Generation for Text-to-JSON Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guijin Son, Sunghee Ahn, Youngjae Yu","submitted_at":"2026-06-18T10:47:22Z","abstract_excerpt":"From financial filings to clinical records, legacy industries rely heavily on long, unstructured documents to store high-value information. Reliably extracting this information into structured, machine-readable representations is a key prerequisite to making the contents accessible to automated systems. JSON is a natural target for such structured extraction, yet constructing reliable and scalable text-to-JSON training data remains challenging. To address this gap, we propose STAGE (Spreadsheet-grounded Text-to-JSON Artifact GEneration), a source-grounded data generation pipeline that construc"},"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":"2606.20072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T10:47:22Z","cross_cats_sorted":[],"title_canon_sha256":"e0c5b973d13f145254f51c779b9799f4c30a91c3dce43007af590fdcaa8d8d73","abstract_canon_sha256":"b3a88895d66a62243fc135255a6055ff246821c26cdb31344a74ffbeda43049b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:02.101191Z","signature_b64":"6nAE2rXXLt6xxYP2gxVCowU+5qkLiRtFoJzW6hakGyK3qxRYJzjhzRRKzvwQF5rBzqx1GG7PwSQeK+tLDSz8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1de2876100c49b41ccbbc6a106904c8eacd877240e1c484d9dbe6e6608eafe2","last_reissued_at":"2026-06-19T16:13:02.100850Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:02.100850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Source-Grounded Data Generation for Text-to-JSON Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guijin Son, Sunghee Ahn, Youngjae Yu","submitted_at":"2026-06-18T10:47:22Z","abstract_excerpt":"From financial filings to clinical records, legacy industries rely heavily on long, unstructured documents to store high-value information. Reliably extracting this information into structured, machine-readable representations is a key prerequisite to making the contents accessible to automated systems. JSON is a natural target for such structured extraction, yet constructing reliable and scalable text-to-JSON training data remains challenging. To address this gap, we propose STAGE (Spreadsheet-grounded Text-to-JSON Artifact GEneration), a source-grounded data generation pipeline that construc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20072","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/2606.20072/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":"2606.20072","created_at":"2026-06-19T16:13:02.100911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20072v1","created_at":"2026-06-19T16:13:02.100911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20072","created_at":"2026-06-19T16:13:02.100911+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHPCQ5QQBRE3","created_at":"2026-06-19T16:13:02.100911+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHPCQ5QQBRE3IHGL","created_at":"2026-06-19T16:13:02.100911+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHPCQ5QQ","created_at":"2026-06-19T16:13:02.100911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD","json":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD.json","graph_json":"https://pith.science/api/pith-number/YHPCQ5QQBRE3IHGLXRVBA2IEZD/graph.json","events_json":"https://pith.science/api/pith-number/YHPCQ5QQBRE3IHGLXRVBA2IEZD/events.json","paper":"https://pith.science/paper/YHPCQ5QQ"},"agent_actions":{"view_html":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD","download_json":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD.json","view_paper":"https://pith.science/paper/YHPCQ5QQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20072&json=true","fetch_graph":"https://pith.science/api/pith-number/YHPCQ5QQBRE3IHGLXRVBA2IEZD/graph.json","fetch_events":"https://pith.science/api/pith-number/YHPCQ5QQBRE3IHGLXRVBA2IEZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD/action/storage_attestation","attest_author":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD/action/author_attestation","sign_citation":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD/action/citation_signature","submit_replication":"https://pith.science/pith/YHPCQ5QQBRE3IHGLXRVBA2IEZD/action/replication_record"}},"created_at":"2026-06-19T16:13:02.100911+00:00","updated_at":"2026-06-19T16:13:02.100911+00:00"}