{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5FNFXKPCXFGMDO5QJD7HRKVN6R","short_pith_number":"pith:5FNFXKPC","schema_version":"1.0","canonical_sha256":"e95a5ba9e2b94cc1bbb048fe78aaadf444f6da9e7a5f13220453d295557eef7d","source":{"kind":"arxiv","id":"2505.05864","version":1},"attestation_state":"computed","paper":{"title":"Symbol-based entity marker highlighting for enhanced text mining in materials science with generative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chan-Woo Lee, Jong Min Yuk, Junhyeong Lee","submitted_at":"2025-05-09T07:58:30Z","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"},"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":"2505.05864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T07:58:30Z","cross_cats_sorted":[],"title_canon_sha256":"9e8a1892752c87544827be95c3c4c02239e191d0aaee0f61687f1bfe947f3a15","abstract_canon_sha256":"e30b4462a873290d5fbcc3270c3d436e820694b2798f59c66723c281609b4b14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:48.992258Z","signature_b64":"wCSa2Fru2QFhWR5uFxZsi5umIJ7aV6jUziKSVAIh7K9NFHIhoboRaQa7vxs1UdKS2Ug74H3AI2bMPO0huJfyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e95a5ba9e2b94cc1bbb048fe78aaadf444f6da9e7a5f13220453d295557eef7d","last_reissued_at":"2026-07-05T11:00:48.991652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:48.991652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbol-based entity marker highlighting for enhanced text mining in materials science with generative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chan-Woo Lee, Jong Min Yuk, Junhyeong Lee","submitted_at":"2025-05-09T07:58:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05864","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/2505.05864/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":"2505.05864","created_at":"2026-07-05T11:00:48.991720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05864v1","created_at":"2026-07-05T11:00:48.991720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05864","created_at":"2026-07-05T11:00:48.991720+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FNFXKPCXFGM","created_at":"2026-07-05T11:00:48.991720+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FNFXKPCXFGMDO5Q","created_at":"2026-07-05T11:00:48.991720+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FNFXKPC","created_at":"2026-07-05T11:00:48.991720+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/5FNFXKPCXFGMDO5QJD7HRKVN6R","json":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R.json","graph_json":"https://pith.science/api/pith-number/5FNFXKPCXFGMDO5QJD7HRKVN6R/graph.json","events_json":"https://pith.science/api/pith-number/5FNFXKPCXFGMDO5QJD7HRKVN6R/events.json","paper":"https://pith.science/paper/5FNFXKPC"},"agent_actions":{"view_html":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R","download_json":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R.json","view_paper":"https://pith.science/paper/5FNFXKPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05864&json=true","fetch_graph":"https://pith.science/api/pith-number/5FNFXKPCXFGMDO5QJD7HRKVN6R/graph.json","fetch_events":"https://pith.science/api/pith-number/5FNFXKPCXFGMDO5QJD7HRKVN6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R/action/storage_attestation","attest_author":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R/action/author_attestation","sign_citation":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R/action/citation_signature","submit_replication":"https://pith.science/pith/5FNFXKPCXFGMDO5QJD7HRKVN6R/action/replication_record"}},"created_at":"2026-07-05T11:00:48.991720+00:00","updated_at":"2026-07-05T11:00:48.991720+00:00"}