{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BAIOG2BR6ZIQP4TLA7MCIFTIOS","short_pith_number":"pith:BAIOG2BR","schema_version":"1.0","canonical_sha256":"0810e36831f65107f26b07d824166874ab2a48f1c3909c58434b1c90398ca4d1","source":{"kind":"arxiv","id":"2005.11021","version":1},"attestation_state":"computed","paper":{"title":"Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.DL","authors_text":"Abdou Youssef, Bela Gipp, Felix Hamborg, Moritz Schubotz, Norman Meuschke, Philipp Scharpf","submitted_at":"2020-05-22T06:16:32Z","abstract_excerpt":"In this paper, we show how selecting and combining encodings of natural and mathematical language affect classification and clustering of documents with mathematical content. We demonstrate this by using sets of documents, sections, and abstracts from the arXiv preprint server that are labeled by their subject class (mathematics, computer science, physics, etc.) to compare different encodings of text and formulae and evaluate the performance and runtimes of selected classification and clustering algorithms. Our encodings achieve classification accuracies up to $82.8\\%$ and cluster purities up "},"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":"2005.11021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2020-05-22T06:16:32Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"29f79c5c5083264733a2e5ab205305b75004948398bbad4ec3c7b2de8efd7aa8","abstract_canon_sha256":"a98ef0d1d50dec77eefe52db80fcbd84c17795b64cd3d8e13b7ab97515efe55b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:04.579261Z","signature_b64":"xcp9xStLArR+pXq+wq9HueXmaR+J7FMLcTxlSEfyp7K7llcfI0t20DI7BUfgZoTBdO0ScQClViJFg8ZI4t14Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0810e36831f65107f26b07d824166874ab2a48f1c3909c58434b1c90398ca4d1","last_reissued_at":"2026-07-05T01:05:04.578694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:04.578694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.DL","authors_text":"Abdou Youssef, Bela Gipp, Felix Hamborg, Moritz Schubotz, Norman Meuschke, Philipp Scharpf","submitted_at":"2020-05-22T06:16:32Z","abstract_excerpt":"In this paper, we show how selecting and combining encodings of natural and mathematical language affect classification and clustering of documents with mathematical content. We demonstrate this by using sets of documents, sections, and abstracts from the arXiv preprint server that are labeled by their subject class (mathematics, computer science, physics, etc.) to compare different encodings of text and formulae and evaluate the performance and runtimes of selected classification and clustering algorithms. Our encodings achieve classification accuracies up to $82.8\\%$ and cluster purities up "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11021","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/2005.11021/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":"2005.11021","created_at":"2026-07-05T01:05:04.578756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.11021v1","created_at":"2026-07-05T01:05:04.578756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11021","created_at":"2026-07-05T01:05:04.578756+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAIOG2BR6ZIQ","created_at":"2026-07-05T01:05:04.578756+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAIOG2BR6ZIQP4TL","created_at":"2026-07-05T01:05:04.578756+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAIOG2BR","created_at":"2026-07-05T01:05:04.578756+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/BAIOG2BR6ZIQP4TLA7MCIFTIOS","json":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS.json","graph_json":"https://pith.science/api/pith-number/BAIOG2BR6ZIQP4TLA7MCIFTIOS/graph.json","events_json":"https://pith.science/api/pith-number/BAIOG2BR6ZIQP4TLA7MCIFTIOS/events.json","paper":"https://pith.science/paper/BAIOG2BR"},"agent_actions":{"view_html":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS","download_json":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS.json","view_paper":"https://pith.science/paper/BAIOG2BR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.11021&json=true","fetch_graph":"https://pith.science/api/pith-number/BAIOG2BR6ZIQP4TLA7MCIFTIOS/graph.json","fetch_events":"https://pith.science/api/pith-number/BAIOG2BR6ZIQP4TLA7MCIFTIOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS/action/storage_attestation","attest_author":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS/action/author_attestation","sign_citation":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS/action/citation_signature","submit_replication":"https://pith.science/pith/BAIOG2BR6ZIQP4TLA7MCIFTIOS/action/replication_record"}},"created_at":"2026-07-05T01:05:04.578756+00:00","updated_at":"2026-07-05T01:05:04.578756+00:00"}