{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WGZ2EZLYPKWU5V5D3UDNNB7NCB","short_pith_number":"pith:WGZ2EZLY","schema_version":"1.0","canonical_sha256":"b1b3a265787aad4ed7a3dd06d687ed107482f20c3d38dbfd25317fac5ab1621b","source":{"kind":"arxiv","id":"1710.02365","version":2},"attestation_state":"computed","paper":{"title":"Czech Text Document Corpus v 2.0","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ladislav Lenc, Pavel Kr\\'al","submitted_at":"2017-10-06T12:22:44Z","abstract_excerpt":"This paper introduces \"Czech Text Document Corpus v 2.0\", a collection of text documents for automatic document classification in Czech language. It is composed of the text documents provided by the Czech News Agency and is freely available for research purposes at http://ctdc.kiv.zcu.cz/. This corpus was created in order to facilitate a straightforward comparison of the document classification approaches on Czech data. It is particularly dedicated to evaluation of multi-label document classification approaches, because one document is usually labelled with more than one label. Besides the inf"},"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":"1710.02365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-06T12:22:44Z","cross_cats_sorted":[],"title_canon_sha256":"025632d894e593e2198e9ccf2ac3bfeb42627c9ded2e32e214f13b41de994453","abstract_canon_sha256":"31be6692d0a4c6cbd18b0fdf37e877ed127cb08793409b6caafe9fad25ec833f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:42.283770Z","signature_b64":"vOzkzN6jt4tiPDkQcKCLDECSitZ71dYSl05iQUOk9V+rGLU5dRdFHinfGjfBiehngPe5GfavQfMiiG7uBZPmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1b3a265787aad4ed7a3dd06d687ed107482f20c3d38dbfd25317fac5ab1621b","last_reissued_at":"2026-05-18T00:24:42.283126Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:42.283126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Czech Text Document Corpus v 2.0","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ladislav Lenc, Pavel Kr\\'al","submitted_at":"2017-10-06T12:22:44Z","abstract_excerpt":"This paper introduces \"Czech Text Document Corpus v 2.0\", a collection of text documents for automatic document classification in Czech language. It is composed of the text documents provided by the Czech News Agency and is freely available for research purposes at http://ctdc.kiv.zcu.cz/. This corpus was created in order to facilitate a straightforward comparison of the document classification approaches on Czech data. It is particularly dedicated to evaluation of multi-label document classification approaches, because one document is usually labelled with more than one label. Besides the inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02365","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.02365","created_at":"2026-05-18T00:24:42.283217+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.02365v2","created_at":"2026-05-18T00:24:42.283217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02365","created_at":"2026-05-18T00:24:42.283217+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGZ2EZLYPKWU","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGZ2EZLYPKWU5V5D","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGZ2EZLY","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07856","citing_title":"Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB","json":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB.json","graph_json":"https://pith.science/api/pith-number/WGZ2EZLYPKWU5V5D3UDNNB7NCB/graph.json","events_json":"https://pith.science/api/pith-number/WGZ2EZLYPKWU5V5D3UDNNB7NCB/events.json","paper":"https://pith.science/paper/WGZ2EZLY"},"agent_actions":{"view_html":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB","download_json":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB.json","view_paper":"https://pith.science/paper/WGZ2EZLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.02365&json=true","fetch_graph":"https://pith.science/api/pith-number/WGZ2EZLYPKWU5V5D3UDNNB7NCB/graph.json","fetch_events":"https://pith.science/api/pith-number/WGZ2EZLYPKWU5V5D3UDNNB7NCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB/action/storage_attestation","attest_author":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB/action/author_attestation","sign_citation":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB/action/citation_signature","submit_replication":"https://pith.science/pith/WGZ2EZLYPKWU5V5D3UDNNB7NCB/action/replication_record"}},"created_at":"2026-05-18T00:24:42.283217+00:00","updated_at":"2026-05-18T00:24:42.283217+00:00"}