{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:LJ3HNF3IPS32ZDFGQEW5X2HXHP","short_pith_number":"pith:LJ3HNF3I","schema_version":"1.0","canonical_sha256":"5a767697687cb7ac8ca6812ddbe8f73bfafe84e684796d348f9eb9c8cdf6e8f2","source":{"kind":"arxiv","id":"1406.3188","version":1},"attestation_state":"computed","paper":{"title":"Assessing the Quality of Web Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Elisabeth Lex, Horst Bischof, Inayat Khan, Michael Granitzer","submitted_at":"2014-06-12T10:40:15Z","abstract_excerpt":"This paper describes our approach towards the ECML/PKDD Discovery Challenge 2010. The challenge consists of three tasks: (1) a Web genre and facet classification task for English hosts, (2) an English quality task, and (3) a multilingual quality task (German and French). In our approach, we create an ensemble of three classifiers to predict unseen Web hosts whereas each classifier is trained on a different feature set. Our final NDCG on the whole test set is 0:575 for Task 1, 0:852 for Task 2, and 0:81 (French) and 0:77 (German) for Task 3, which ranks second place in the ECML/PKDD Discovery C"},"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":"1406.3188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-12T10:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"f8e622a1c4306991024312adf7ac57bd94b1461e37b07ea5ee36acf34ed93f0e","abstract_canon_sha256":"d9340d34907e98cfe363af80017de448141e0592f4d2fe665dc176e39024e11b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:52.834507Z","signature_b64":"oRzO1+7jV7dyeqVheJ2qBZbP6w8Bbzw4rJR9VcB22O7W+vxxUMcv7zWpwbK3ZokuyWWqYm92+kKwCRc4+f68Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a767697687cb7ac8ca6812ddbe8f73bfafe84e684796d348f9eb9c8cdf6e8f2","last_reissued_at":"2026-05-18T02:49:52.833937Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:52.833937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Quality of Web Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Elisabeth Lex, Horst Bischof, Inayat Khan, Michael Granitzer","submitted_at":"2014-06-12T10:40:15Z","abstract_excerpt":"This paper describes our approach towards the ECML/PKDD Discovery Challenge 2010. The challenge consists of three tasks: (1) a Web genre and facet classification task for English hosts, (2) an English quality task, and (3) a multilingual quality task (German and French). In our approach, we create an ensemble of three classifiers to predict unseen Web hosts whereas each classifier is trained on a different feature set. Our final NDCG on the whole test set is 0:575 for Task 1, 0:852 for Task 2, and 0:81 (French) and 0:77 (German) for Task 3, which ranks second place in the ECML/PKDD Discovery C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3188","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":"1406.3188","created_at":"2026-05-18T02:49:52.834029+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.3188v1","created_at":"2026-05-18T02:49:52.834029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3188","created_at":"2026-05-18T02:49:52.834029+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJ3HNF3IPS32","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJ3HNF3IPS32ZDFG","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJ3HNF3I","created_at":"2026-05-18T12:28:38.356838+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/LJ3HNF3IPS32ZDFGQEW5X2HXHP","json":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP.json","graph_json":"https://pith.science/api/pith-number/LJ3HNF3IPS32ZDFGQEW5X2HXHP/graph.json","events_json":"https://pith.science/api/pith-number/LJ3HNF3IPS32ZDFGQEW5X2HXHP/events.json","paper":"https://pith.science/paper/LJ3HNF3I"},"agent_actions":{"view_html":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP","download_json":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP.json","view_paper":"https://pith.science/paper/LJ3HNF3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.3188&json=true","fetch_graph":"https://pith.science/api/pith-number/LJ3HNF3IPS32ZDFGQEW5X2HXHP/graph.json","fetch_events":"https://pith.science/api/pith-number/LJ3HNF3IPS32ZDFGQEW5X2HXHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP/action/storage_attestation","attest_author":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP/action/author_attestation","sign_citation":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP/action/citation_signature","submit_replication":"https://pith.science/pith/LJ3HNF3IPS32ZDFGQEW5X2HXHP/action/replication_record"}},"created_at":"2026-05-18T02:49:52.834029+00:00","updated_at":"2026-05-18T02:49:52.834029+00:00"}