{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MEDZI7HQ75OYPGFDRAES42JFT4","short_pith_number":"pith:MEDZI7HQ","schema_version":"1.0","canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","source":{"kind":"arxiv","id":"2204.12070","version":1},"attestation_state":"computed","paper":{"title":"Symlink: A New Dataset for Scientific Symbol-Description Linking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2022-04-26T04:36:14Z","abstract_excerpt":"Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup. In this paper, we present a new large-scale dataset that emphasizes extracting symbols and descriptions in scientific documents. Symlink annotates scientific papers of 5 different domains (i.e., computer science, biology, physics, mathematics, and economics). Our experiments on Symlink demonstrate the challenges of the symbol-description linking task for existing models and call for further research effort in this area. We will publicly release Symlink to facilitate future "},"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":"2204.12070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T04:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"2a61c047930a87d083996577c069ffbe8f56879ba6da865d2ddec047825e40b2","abstract_canon_sha256":"34acb8d155c2ab338b804c52437d095b8a19ff0adef9e3609dac40496cf7ab8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:44.135250Z","signature_b64":"HMO06JAzccuk4LrLZK+wutXduHlnLNhLboimAd18dQKJZ/oiUSH0ZzlOlvWrISz0d6g7pPVz1lqP3cb2dslhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","last_reissued_at":"2026-07-05T04:17:44.134708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:44.134708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symlink: A New Dataset for Scientific Symbol-Description Linking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2022-04-26T04:36:14Z","abstract_excerpt":"Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup. In this paper, we present a new large-scale dataset that emphasizes extracting symbols and descriptions in scientific documents. Symlink annotates scientific papers of 5 different domains (i.e., computer science, biology, physics, mathematics, and economics). Our experiments on Symlink demonstrate the challenges of the symbol-description linking task for existing models and call for further research effort in this area. We will publicly release Symlink to facilitate future "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12070","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/2204.12070/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":"2204.12070","created_at":"2026-07-05T04:17:44.134786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.12070v1","created_at":"2026-07-05T04:17:44.134786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12070","created_at":"2026-07-05T04:17:44.134786+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEDZI7HQ75OY","created_at":"2026-07-05T04:17:44.134786+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEDZI7HQ75OYPGFD","created_at":"2026-07-05T04:17:44.134786+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEDZI7HQ","created_at":"2026-07-05T04:17:44.134786+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/MEDZI7HQ75OYPGFDRAES42JFT4","json":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4.json","graph_json":"https://pith.science/api/pith-number/MEDZI7HQ75OYPGFDRAES42JFT4/graph.json","events_json":"https://pith.science/api/pith-number/MEDZI7HQ75OYPGFDRAES42JFT4/events.json","paper":"https://pith.science/paper/MEDZI7HQ"},"agent_actions":{"view_html":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4","download_json":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4.json","view_paper":"https://pith.science/paper/MEDZI7HQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.12070&json=true","fetch_graph":"https://pith.science/api/pith-number/MEDZI7HQ75OYPGFDRAES42JFT4/graph.json","fetch_events":"https://pith.science/api/pith-number/MEDZI7HQ75OYPGFDRAES42JFT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/action/storage_attestation","attest_author":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/action/author_attestation","sign_citation":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/action/citation_signature","submit_replication":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/action/replication_record"}},"created_at":"2026-07-05T04:17:44.134786+00:00","updated_at":"2026-07-05T04:17:44.134786+00:00"}