{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:E4OG6OMOYZVOSVUZ4MEIDXGSOM","short_pith_number":"pith:E4OG6OMO","schema_version":"1.0","canonical_sha256":"271c6f398ec66ae95699e30881dcd27302423c7212fe7455f73158b68e79dbdc","source":{"kind":"arxiv","id":"2006.03039","version":1},"attestation_state":"computed","paper":{"title":"The SOFC-Exp Corpus and Neural Approaches to Information Extraction in the Materials Science Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anika Maruscyk, Annemarie Friedrich, Federico Tomazic, Heike Adel, Johannes Hingerl, Lukas Lange, Renou Benteau","submitted_at":"2020-06-04T17:49:34Z","abstract_excerpt":"This paper presents a new challenging information extraction task in the domain of materials science. We develop an annotation scheme for marking information on experiments related to solid oxide fuel cells in scientific publications, such as involved materials and measurement conditions. With this paper, we publish our annotation guidelines, as well as our SOFC-Exp corpus consisting of 45 open-access scholarly articles annotated by domain experts. A corpus and an inter-annotator agreement study demonstrate the complexity of the suggested named entity recognition and slot filling tasks as well"},"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":"2006.03039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T17:49:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eee6f1de44b706970217a40dc9dc1307d458f39e087dc240a2fc1d70a6856abb","abstract_canon_sha256":"d5a700e77eb5d7c8afb0ae3cc1ad6d25d858b1de117af45ef16df1b764c80a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:02.626062Z","signature_b64":"uyhyRkX1dnZi8XqOwdVJfLPGvr3JsmBHQvnd6IaebQaIj0VxWp0F//ikVl0JsR2FQxCHTW17de3zOl1bOFZWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"271c6f398ec66ae95699e30881dcd27302423c7212fe7455f73158b68e79dbdc","last_reissued_at":"2026-07-05T01:08:02.625423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:02.625423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The SOFC-Exp Corpus and Neural Approaches to Information Extraction in the Materials Science Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anika Maruscyk, Annemarie Friedrich, Federico Tomazic, Heike Adel, Johannes Hingerl, Lukas Lange, Renou Benteau","submitted_at":"2020-06-04T17:49:34Z","abstract_excerpt":"This paper presents a new challenging information extraction task in the domain of materials science. We develop an annotation scheme for marking information on experiments related to solid oxide fuel cells in scientific publications, such as involved materials and measurement conditions. With this paper, we publish our annotation guidelines, as well as our SOFC-Exp corpus consisting of 45 open-access scholarly articles annotated by domain experts. A corpus and an inter-annotator agreement study demonstrate the complexity of the suggested named entity recognition and slot filling tasks as well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03039","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/2006.03039/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":"2006.03039","created_at":"2026-07-05T01:08:02.625504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03039v1","created_at":"2026-07-05T01:08:02.625504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03039","created_at":"2026-07-05T01:08:02.625504+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4OG6OMOYZVO","created_at":"2026-07-05T01:08:02.625504+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4OG6OMOYZVOSVUZ","created_at":"2026-07-05T01:08:02.625504+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4OG6OMO","created_at":"2026-07-05T01:08:02.625504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11115","citing_title":"Incorporating Domain Knowledge into Materials Tokenization","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM","json":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM.json","graph_json":"https://pith.science/api/pith-number/E4OG6OMOYZVOSVUZ4MEIDXGSOM/graph.json","events_json":"https://pith.science/api/pith-number/E4OG6OMOYZVOSVUZ4MEIDXGSOM/events.json","paper":"https://pith.science/paper/E4OG6OMO"},"agent_actions":{"view_html":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM","download_json":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM.json","view_paper":"https://pith.science/paper/E4OG6OMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03039&json=true","fetch_graph":"https://pith.science/api/pith-number/E4OG6OMOYZVOSVUZ4MEIDXGSOM/graph.json","fetch_events":"https://pith.science/api/pith-number/E4OG6OMOYZVOSVUZ4MEIDXGSOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM/action/storage_attestation","attest_author":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM/action/author_attestation","sign_citation":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM/action/citation_signature","submit_replication":"https://pith.science/pith/E4OG6OMOYZVOSVUZ4MEIDXGSOM/action/replication_record"}},"created_at":"2026-07-05T01:08:02.625504+00:00","updated_at":"2026-07-05T01:08:02.625504+00:00"}