{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YHPCQ5QQBRE3IHGLXRVBA2IEZD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3a88895d66a62243fc135255a6055ff246821c26cdb31344a74ffbeda43049b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T10:47:22Z","title_canon_sha256":"e0c5b973d13f145254f51c779b9799f4c30a91c3dce43007af590fdcaa8d8d73"},"schema_version":"1.0","source":{"id":"2606.20072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20072","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20072v1","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20072","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"YHPCQ5QQBRE3","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"YHPCQ5QQBRE3IHGL","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"YHPCQ5QQ","created_at":"2026-06-19T16:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:893a8b3288244653abe6034aaed9abe986443b00a17bdb6c283c4ba88f145ff0","target":"graph","created_at":"2026-06-19T16:13:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.20072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guijin Son, Sunghee Ahn, Youngjae Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T10:47:22Z","title":"Source-Grounded Data Generation for Text-to-JSON Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20072","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3251ea72e846d327092192ba5003a65aae57c264b8d2df1351cb4c90aca5adef","target":"record","created_at":"2026-06-19T16:13:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3a88895d66a62243fc135255a6055ff246821c26cdb31344a74ffbeda43049b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T10:47:22Z","title_canon_sha256":"e0c5b973d13f145254f51c779b9799f4c30a91c3dce43007af590fdcaa8d8d73"},"schema_version":"1.0","source":{"id":"2606.20072","kind":"arxiv","version":1}},"canonical_sha256":"c1de2876100c49b41ccbbc6a106904c8eacd877240e1c484d9dbe6e6608eafe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1de2876100c49b41ccbbc6a106904c8eacd877240e1c484d9dbe6e6608eafe2","first_computed_at":"2026-06-19T16:13:02.100850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:02.100850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6nAE2rXXLt6xxYP2gxVCowU+5qkLiRtFoJzW6hakGyK3qxRYJzjhzRRKzvwQF5rBzqx1GG7PwSQeK+tLDSz8Dg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:02.101191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3251ea72e846d327092192ba5003a65aae57c264b8d2df1351cb4c90aca5adef","sha256:893a8b3288244653abe6034aaed9abe986443b00a17bdb6c283c4ba88f145ff0"],"state_sha256":"ee1b27a55de2c3c854044196012c6a805f928c50649e235745d35fdf27b89dc4"}