{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:42RLSRF535L3WF2ZKZGVLROH4T","short_pith_number":"pith:42RLSRF5","schema_version":"1.0","canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","source":{"kind":"arxiv","id":"2304.08352","version":1},"attestation_state":"computed","paper":{"title":"What Makes a Good Dataset for Symbol Description Reading?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bradley Eck, Joern Ploennigs, Karol Lynch","submitted_at":"2023-04-17T15:14:27Z","abstract_excerpt":"The usage of mathematical formulas as concise representations of a document's key ideas is common practice. Correctly interpreting these formulas, by identifying mathematical symbols and extracting their descriptions, is an important task in document understanding. This paper makes the following contributions to the mathematical identifier description reading (MIDR) task:\n  (i) introduces the Math Formula Question Answering Dataset (MFQuAD) with $7508$ annotated identifier occurrences;\n  (ii) describes novel variations of the noun phrase ranking approach for the MIDR task;\n  (iii) reports expe"},"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":"2304.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T15:14:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0317f643e76cafaef3507dd0f35ac8eb816027617a2c3342754c0cbf2970c8c1","abstract_canon_sha256":"e8c7c3ccf426b2f8fd264bf11210df6fed1cd574864bc818073fd47b0e8cbb9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:42.234974Z","signature_b64":"xaf5NQb6ctAJT6t/cwydptNJlI5glSD1BoFfKvS0M3kytkITGtBltKfpp0pkH4SLvHi9ZnYm86FpjbtV1/23Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","last_reissued_at":"2026-07-05T06:01:42.234581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:42.234581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes a Good Dataset for Symbol Description Reading?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bradley Eck, Joern Ploennigs, Karol Lynch","submitted_at":"2023-04-17T15:14:27Z","abstract_excerpt":"The usage of mathematical formulas as concise representations of a document's key ideas is common practice. Correctly interpreting these formulas, by identifying mathematical symbols and extracting their descriptions, is an important task in document understanding. This paper makes the following contributions to the mathematical identifier description reading (MIDR) task:\n  (i) introduces the Math Formula Question Answering Dataset (MFQuAD) with $7508$ annotated identifier occurrences;\n  (ii) describes novel variations of the noun phrase ranking approach for the MIDR task;\n  (iii) reports expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08352","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/2304.08352/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":"2304.08352","created_at":"2026-07-05T06:01:42.234642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08352v1","created_at":"2026-07-05T06:01:42.234642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08352","created_at":"2026-07-05T06:01:42.234642+00:00"},{"alias_kind":"pith_short_12","alias_value":"42RLSRF535L3","created_at":"2026-07-05T06:01:42.234642+00:00"},{"alias_kind":"pith_short_16","alias_value":"42RLSRF535L3WF2Z","created_at":"2026-07-05T06:01:42.234642+00:00"},{"alias_kind":"pith_short_8","alias_value":"42RLSRF5","created_at":"2026-07-05T06:01:42.234642+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/42RLSRF535L3WF2ZKZGVLROH4T","json":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T.json","graph_json":"https://pith.science/api/pith-number/42RLSRF535L3WF2ZKZGVLROH4T/graph.json","events_json":"https://pith.science/api/pith-number/42RLSRF535L3WF2ZKZGVLROH4T/events.json","paper":"https://pith.science/paper/42RLSRF5"},"agent_actions":{"view_html":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T","download_json":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T.json","view_paper":"https://pith.science/paper/42RLSRF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08352&json=true","fetch_graph":"https://pith.science/api/pith-number/42RLSRF535L3WF2ZKZGVLROH4T/graph.json","fetch_events":"https://pith.science/api/pith-number/42RLSRF535L3WF2ZKZGVLROH4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/action/storage_attestation","attest_author":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/action/author_attestation","sign_citation":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/action/citation_signature","submit_replication":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/action/replication_record"}},"created_at":"2026-07-05T06:01:42.234642+00:00","updated_at":"2026-07-05T06:01:42.234642+00:00"}