{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XINJFHBUE3FOE5PWJFHIUDYJ62","short_pith_number":"pith:XINJFHBU","canonical_record":{"source":{"id":"2507.21340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T21:20:44Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"title_canon_sha256":"43db15972d7a920e166ad3a9d4342831efec92daafa59cd015de758b04a56936","abstract_canon_sha256":"ed4a7f1938a0c44ccef3ef4fe667e34da0be4bffce076b3336a8ee9d57b1f152"},"schema_version":"1.0"},"canonical_sha256":"ba1a929c3426cae275f6494e8a0f09f685e3651a68debf39fadd7368e92c59bf","source":{"kind":"arxiv","id":"2507.21340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21340","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21340v1","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21340","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"XINJFHBUE3FO","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"pith_short_16","alias_value":"XINJFHBUE3FOE5PW","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"pith_short_8","alias_value":"XINJFHBU","created_at":"2026-07-05T11:44:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XINJFHBUE3FOE5PWJFHIUDYJ62","target":"record","payload":{"canonical_record":{"source":{"id":"2507.21340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T21:20:44Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"title_canon_sha256":"43db15972d7a920e166ad3a9d4342831efec92daafa59cd015de758b04a56936","abstract_canon_sha256":"ed4a7f1938a0c44ccef3ef4fe667e34da0be4bffce076b3336a8ee9d57b1f152"},"schema_version":"1.0"},"canonical_sha256":"ba1a929c3426cae275f6494e8a0f09f685e3651a68debf39fadd7368e92c59bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:58.011146Z","signature_b64":"BDMQNdNZAhSqTj9iOcTuzwaxReBbEl3ftohgjETOLQmLDtFz+G2q0i5JpKNwRNbT3g/YnfMTpHrxzNHsucawBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba1a929c3426cae275f6494e8a0f09f685e3651a68debf39fadd7368e92c59bf","last_reissued_at":"2026-07-05T11:44:58.010726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:58.010726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.21340","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DUDuf3wH5WOVWclwwmdTgRwLxWiL8tmW7BE/Si0sCXAdgWcFkXTIPeVbvkZcommUpmYk+MwgFQz15fa04zp7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:58:16.896147Z"},"content_sha256":"aa7f71b9f9e8cf2365849db363aaeb7a24c11dcd5f5ead385aeb493cdcd1cf61","schema_version":"1.0","event_id":"sha256:aa7f71b9f9e8cf2365849db363aaeb7a24c11dcd5f5ead385aeb493cdcd1cf61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XINJFHBUE3FOE5PWJFHIUDYJ62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Horst Samulowitz, Nandana Mihindukulasooriya, Satyananda Kashyap, Sola Shirai","submitted_at":"2025-07-28T21:20:44Z","abstract_excerpt":"Extracting structured information from text, such as key-value pairs that could augment tabular data, is quite useful in many enterprise use cases. Although large language models (LLMs) have enabled numerous automated pipelines for converting natural language into structured formats, there is still a lack of benchmarks for evaluating their extraction quality, especially in specific domains or focused documents specific to a given organization. Building such benchmarks by manual annotations is labour-intensive and limits the size and scalability of the benchmarks. In this work, we present Struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21340","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/2507.21340/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kxI8vlJvqEM5tRF1Y3SQ6F2+zFjIzPIQY0G2gJ46zwC1jlwUSZGqvXTG4ETyKPLgf8I6GD9NMWiPntxs2ReFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:58:16.896673Z"},"content_sha256":"d48532bf975ae230ac1cb6ee01f7b1b74db890e3088ab2caf0c05ebea0313d93","schema_version":"1.0","event_id":"sha256:d48532bf975ae230ac1cb6ee01f7b1b74db890e3088ab2caf0c05ebea0313d93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XINJFHBUE3FOE5PWJFHIUDYJ62/bundle.json","state_url":"https://pith.science/pith/XINJFHBUE3FOE5PWJFHIUDYJ62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XINJFHBUE3FOE5PWJFHIUDYJ62/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T06:58:16Z","links":{"resolver":"https://pith.science/pith/XINJFHBUE3FOE5PWJFHIUDYJ62","bundle":"https://pith.science/pith/XINJFHBUE3FOE5PWJFHIUDYJ62/bundle.json","state":"https://pith.science/pith/XINJFHBUE3FOE5PWJFHIUDYJ62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XINJFHBUE3FOE5PWJFHIUDYJ62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XINJFHBUE3FOE5PWJFHIUDYJ62","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":"ed4a7f1938a0c44ccef3ef4fe667e34da0be4bffce076b3336a8ee9d57b1f152","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T21:20:44Z","title_canon_sha256":"43db15972d7a920e166ad3a9d4342831efec92daafa59cd015de758b04a56936"},"schema_version":"1.0","source":{"id":"2507.21340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21340","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21340v1","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21340","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"XINJFHBUE3FO","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"pith_short_16","alias_value":"XINJFHBUE3FOE5PW","created_at":"2026-07-05T11:44:58Z"},{"alias_kind":"pith_short_8","alias_value":"XINJFHBU","created_at":"2026-07-05T11:44:58Z"}],"graph_snapshots":[{"event_id":"sha256:d48532bf975ae230ac1cb6ee01f7b1b74db890e3088ab2caf0c05ebea0313d93","target":"graph","created_at":"2026-07-05T11:44:58Z","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/2507.21340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured information from text, such as key-value pairs that could augment tabular data, is quite useful in many enterprise use cases. Although large language models (LLMs) have enabled numerous automated pipelines for converting natural language into structured formats, there is still a lack of benchmarks for evaluating their extraction quality, especially in specific domains or focused documents specific to a given organization. Building such benchmarks by manual annotations is labour-intensive and limits the size and scalability of the benchmarks. In this work, we present Struc","authors_text":"Horst Samulowitz, Nandana Mihindukulasooriya, Satyananda Kashyap, Sola Shirai","cross_cats":["cs.AI","cs.DB","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T21:20:44Z","title":"StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21340","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:aa7f71b9f9e8cf2365849db363aaeb7a24c11dcd5f5ead385aeb493cdcd1cf61","target":"record","created_at":"2026-07-05T11:44:58Z","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":"ed4a7f1938a0c44ccef3ef4fe667e34da0be4bffce076b3336a8ee9d57b1f152","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T21:20:44Z","title_canon_sha256":"43db15972d7a920e166ad3a9d4342831efec92daafa59cd015de758b04a56936"},"schema_version":"1.0","source":{"id":"2507.21340","kind":"arxiv","version":1}},"canonical_sha256":"ba1a929c3426cae275f6494e8a0f09f685e3651a68debf39fadd7368e92c59bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba1a929c3426cae275f6494e8a0f09f685e3651a68debf39fadd7368e92c59bf","first_computed_at":"2026-07-05T11:44:58.010726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:58.010726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDMQNdNZAhSqTj9iOcTuzwaxReBbEl3ftohgjETOLQmLDtFz+G2q0i5JpKNwRNbT3g/YnfMTpHrxzNHsucawBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:58.011146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa7f71b9f9e8cf2365849db363aaeb7a24c11dcd5f5ead385aeb493cdcd1cf61","sha256:d48532bf975ae230ac1cb6ee01f7b1b74db890e3088ab2caf0c05ebea0313d93"],"state_sha256":"faebd784ca5177b11e7e0e5266c175cff2d21c1ad75bdf066afc180496d3e0f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WkDSjWMIIulapgLjiBI883QzyG7qKlNpFzpa2/+Jcg4O2K6FDfrvRPFMfmdLj66d/ZuKzKmyE9HKFRD4qiq9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:58:16.901770Z","bundle_sha256":"dbed7c771777d324864e8468aadc9134bc3daf04a2c4baf7c46b23bf0fa35db8"}}