{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5FNFXKPCXFGMDO5QJD7HRKVN6R","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":"e30b4462a873290d5fbcc3270c3d436e820694b2798f59c66723c281609b4b14","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T07:58:30Z","title_canon_sha256":"9e8a1892752c87544827be95c3c4c02239e191d0aaee0f61687f1bfe947f3a15"},"schema_version":"1.0","source":{"id":"2505.05864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05864","created_at":"2026-07-05T11:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05864v1","created_at":"2026-07-05T11:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05864","created_at":"2026-07-05T11:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"5FNFXKPCXFGM","created_at":"2026-07-05T11:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"5FNFXKPCXFGMDO5Q","created_at":"2026-07-05T11:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"5FNFXKPC","created_at":"2026-07-05T11:00:48Z"}],"graph_snapshots":[{"event_id":"sha256:73dbe1a9cb25038b7ad10ee57ed8b30127bbfebde80f55650af7c03baf7ad6d4","target":"graph","created_at":"2026-07-05T11:00:48Z","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/2505.05864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The construction of experimental datasets is essential for expanding the scope of data-driven scientific discovery. Recent advances in natural language processing (NLP) have facilitated automatic extraction of structured data from unstructured scientific literature. While existing approaches-multi-step and direct methods-offer valuable capabilities, they also come with limitations when applied independently. Here, we propose a novel hybrid text-mining framework that integrates the advantages of both methods to convert unstructured scientific text into structured data. Our approach first transf","authors_text":"Chan-Woo Lee, Jong Min Yuk, Junhyeong Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T07:58:30Z","title":"Symbol-based entity marker highlighting for enhanced text mining in materials science with generative AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05864","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":"sha256:58e3400766ac414c87655e8441b8e5dc93d1dd4922f4f44e0bec108ae488d91b","target":"record","created_at":"2026-07-05T11:00:48Z","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":"e30b4462a873290d5fbcc3270c3d436e820694b2798f59c66723c281609b4b14","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T07:58:30Z","title_canon_sha256":"9e8a1892752c87544827be95c3c4c02239e191d0aaee0f61687f1bfe947f3a15"},"schema_version":"1.0","source":{"id":"2505.05864","kind":"arxiv","version":1}},"canonical_sha256":"e95a5ba9e2b94cc1bbb048fe78aaadf444f6da9e7a5f13220453d295557eef7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e95a5ba9e2b94cc1bbb048fe78aaadf444f6da9e7a5f13220453d295557eef7d","first_computed_at":"2026-07-05T11:00:48.991652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:48.991652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wCSa2Fru2QFhWR5uFxZsi5umIJ7aV6jUziKSVAIh7K9NFHIhoboRaQa7vxs1UdKS2Ug74H3AI2bMPO0huJfyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:48.992258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58e3400766ac414c87655e8441b8e5dc93d1dd4922f4f44e0bec108ae488d91b","sha256:73dbe1a9cb25038b7ad10ee57ed8b30127bbfebde80f55650af7c03baf7ad6d4"],"state_sha256":"82ded9503c5a34df191312903a4ca9a0ea24ba2df976bb39efdb08ec98590fd8"}