{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IIOSYNPODDSZAN2FNYZCXSC6PB","short_pith_number":"pith:IIOSYNPO","schema_version":"1.0","canonical_sha256":"421d2c35ee18e59037456e322bc85e787d0d6d6cfad1d1c7cb798c73ad0c3540","source":{"kind":"arxiv","id":"1703.03923","version":1},"attestation_state":"computed","paper":{"title":"A German Corpus for Text Similarity Detection Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Gerardo Sierra, Juan-Manuel Torres-Moreno, Peter Peinl","submitted_at":"2017-03-11T07:35:28Z","abstract_excerpt":"Text similarity detection aims at measuring the degree of similarity between a pair of texts. Corpora available for text similarity detection are designed to evaluate the algorithms to assess the paraphrase level among documents. In this paper we present a textual German corpus for similarity detection. The purpose of this corpus is to automatically assess the similarity between a pair of texts and to evaluate different similarity measures, both for whole documents or for individual sentences. Therefore we have calculated several simple measures on our corpus based on a library of similarity f"},"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":"1703.03923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-11T07:35:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e41a44e0bbf8c7d108c96a24a05ae1e04fe1719ec24685a0ced522e9c8ffd47b","abstract_canon_sha256":"38fd3338b40bf9dc750705cef29826580ab7a8bea2a4223c32ee655be6cdcdda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:52.765375Z","signature_b64":"RRRe0V9ZYnS4xC1Dpk7Ql/QhV5NWUN+psC4M1KtlxnNs5Q0VO2t1AoNGY2nVcCuKB0kma05etXissBabAnLYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421d2c35ee18e59037456e322bc85e787d0d6d6cfad1d1c7cb798c73ad0c3540","last_reissued_at":"2026-05-18T00:48:52.764669Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:52.764669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A German Corpus for Text Similarity Detection Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Gerardo Sierra, Juan-Manuel Torres-Moreno, Peter Peinl","submitted_at":"2017-03-11T07:35:28Z","abstract_excerpt":"Text similarity detection aims at measuring the degree of similarity between a pair of texts. Corpora available for text similarity detection are designed to evaluate the algorithms to assess the paraphrase level among documents. In this paper we present a textual German corpus for similarity detection. The purpose of this corpus is to automatically assess the similarity between a pair of texts and to evaluate different similarity measures, both for whole documents or for individual sentences. Therefore we have calculated several simple measures on our corpus based on a library of similarity f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03923","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":""},"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":"1703.03923","created_at":"2026-05-18T00:48:52.764783+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03923v1","created_at":"2026-05-18T00:48:52.764783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03923","created_at":"2026-05-18T00:48:52.764783+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIOSYNPODDSZ","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIOSYNPODDSZAN2F","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIOSYNPO","created_at":"2026-05-18T12:31:21.493067+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/IIOSYNPODDSZAN2FNYZCXSC6PB","json":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB.json","graph_json":"https://pith.science/api/pith-number/IIOSYNPODDSZAN2FNYZCXSC6PB/graph.json","events_json":"https://pith.science/api/pith-number/IIOSYNPODDSZAN2FNYZCXSC6PB/events.json","paper":"https://pith.science/paper/IIOSYNPO"},"agent_actions":{"view_html":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB","download_json":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB.json","view_paper":"https://pith.science/paper/IIOSYNPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03923&json=true","fetch_graph":"https://pith.science/api/pith-number/IIOSYNPODDSZAN2FNYZCXSC6PB/graph.json","fetch_events":"https://pith.science/api/pith-number/IIOSYNPODDSZAN2FNYZCXSC6PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB/action/storage_attestation","attest_author":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB/action/author_attestation","sign_citation":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB/action/citation_signature","submit_replication":"https://pith.science/pith/IIOSYNPODDSZAN2FNYZCXSC6PB/action/replication_record"}},"created_at":"2026-05-18T00:48:52.764783+00:00","updated_at":"2026-05-18T00:48:52.764783+00:00"}