{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLLI3LRFIOS5PEK4HYIRGERKKE","short_pith_number":"pith:WLLI3LRF","schema_version":"1.0","canonical_sha256":"b2d68dae2543a5d7915c3e1113122a510f9d8a09595b4c4207463ea5e3665028","source":{"kind":"arxiv","id":"2508.12257","version":1},"attestation_state":"computed","paper":{"title":"Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunkit Chan, Tianshi Zheng, Wei Fan, Weiqi Wang, Yangqiu Song, Zheye Deng","submitted_at":"2025-08-17T06:41:40Z","abstract_excerpt":"The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical applications from summarization to data mining, current research lacks a comprehensive synthesis of methodologies, datasets, and metrics. This systematic review examines text-to-structure techniques and the encountered challenges, evaluates current datasets and assessment criteria, and outlines potential directions for future research. We also introduce a universal e"},"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":"2508.12257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-17T06:41:40Z","cross_cats_sorted":[],"title_canon_sha256":"45f0406315f1131e271c6e49f6a48e3047afdcaf1e12444b1e15e8ca769b7361","abstract_canon_sha256":"a43ca2184275cefde9284f798b676e3f54035a75f93a1fefaec5a4d877eb8ee6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:02.486369Z","signature_b64":"XSpRdSY4fPKhGUcKXdN+ZcCJJL6WuXJPhFr0Z+/rvoeYuFdjfnJ1sIMljsS3bEzwoeUwHQkJHhgGvC3CfSWHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2d68dae2543a5d7915c3e1113122a510f9d8a09595b4c4207463ea5e3665028","last_reissued_at":"2026-07-05T11:55:02.485947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:02.485947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunkit Chan, Tianshi Zheng, Wei Fan, Weiqi Wang, Yangqiu Song, Zheye Deng","submitted_at":"2025-08-17T06:41:40Z","abstract_excerpt":"The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical applications from summarization to data mining, current research lacks a comprehensive synthesis of methodologies, datasets, and metrics. This systematic review examines text-to-structure techniques and the encountered challenges, evaluates current datasets and assessment criteria, and outlines potential directions for future research. We also introduce a universal e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12257","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/2508.12257/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":"2508.12257","created_at":"2026-07-05T11:55:02.486002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12257v1","created_at":"2026-07-05T11:55:02.486002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12257","created_at":"2026-07-05T11:55:02.486002+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLLI3LRFIOS5","created_at":"2026-07-05T11:55:02.486002+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLLI3LRFIOS5PEK4","created_at":"2026-07-05T11:55:02.486002+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLLI3LRF","created_at":"2026-07-05T11:55:02.486002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14585","citing_title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE","json":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE.json","graph_json":"https://pith.science/api/pith-number/WLLI3LRFIOS5PEK4HYIRGERKKE/graph.json","events_json":"https://pith.science/api/pith-number/WLLI3LRFIOS5PEK4HYIRGERKKE/events.json","paper":"https://pith.science/paper/WLLI3LRF"},"agent_actions":{"view_html":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE","download_json":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE.json","view_paper":"https://pith.science/paper/WLLI3LRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12257&json=true","fetch_graph":"https://pith.science/api/pith-number/WLLI3LRFIOS5PEK4HYIRGERKKE/graph.json","fetch_events":"https://pith.science/api/pith-number/WLLI3LRFIOS5PEK4HYIRGERKKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE/action/storage_attestation","attest_author":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE/action/author_attestation","sign_citation":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE/action/citation_signature","submit_replication":"https://pith.science/pith/WLLI3LRFIOS5PEK4HYIRGERKKE/action/replication_record"}},"created_at":"2026-07-05T11:55:02.486002+00:00","updated_at":"2026-07-05T11:55:02.486002+00:00"}