{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:7RU6BHWL2XV2IJTW6UQX3BPDJ2","short_pith_number":"pith:7RU6BHWL","schema_version":"1.0","canonical_sha256":"fc69e09ecbd5eba42676f5217d85e34eba3360264ce91306ed019fc461b50226","source":{"kind":"arxiv","id":"1201.6224","version":2},"attestation_state":"computed","paper":{"title":"Wikipedia Arborification and Stratified Explicit Semantic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Vitaly Klyuev, Yannis Haralambous","submitted_at":"2012-01-30T14:26:31Z","abstract_excerpt":"[This is the translation of paper \"Arborification de Wikip\\'edia et analyse s\\'emantique explicite stratifi\\'ee\" submitted to TALN 2012.]\n  We present an extension of the Explicit Semantic Analysis method by Gabrilovich and Markovitch. Using their semantic relatedness measure, we weight the Wikipedia categories graph. Then, we extract a minimal spanning tree, using Chu-Liu & Edmonds' algorithm. We define a notion of stratified tfidf where the stratas, for a given Wikipedia page and a given term, are the classical tfidf and categorical tfidfs of the term in the ancestor categories of the page ("},"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":"1201.6224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-01-30T14:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"858b2aeca2631356dbe6291ba5e545d77c5a5b4fa0bc561882205721506346e0","abstract_canon_sha256":"00e3f592447d4019dd42e62b2f9d10bbb714aa7bb553445b6003bae097349eed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:03:18.860965Z","signature_b64":"8fbrGTP+5/9P2oh0LPnWlKgApLInEoI/lHx1RKQq+Wdwe0ByNTzyrqZ9n+wy1aYvWc2W8Lr89RKZWWhtR5ZfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc69e09ecbd5eba42676f5217d85e34eba3360264ce91306ed019fc461b50226","last_reissued_at":"2026-05-18T04:03:18.860459Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:03:18.860459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wikipedia Arborification and Stratified Explicit Semantic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Vitaly Klyuev, Yannis Haralambous","submitted_at":"2012-01-30T14:26:31Z","abstract_excerpt":"[This is the translation of paper \"Arborification de Wikip\\'edia et analyse s\\'emantique explicite stratifi\\'ee\" submitted to TALN 2012.]\n  We present an extension of the Explicit Semantic Analysis method by Gabrilovich and Markovitch. Using their semantic relatedness measure, we weight the Wikipedia categories graph. Then, we extract a minimal spanning tree, using Chu-Liu & Edmonds' algorithm. We define a notion of stratified tfidf where the stratas, for a given Wikipedia page and a given term, are the classical tfidf and categorical tfidfs of the term in the ancestor categories of the page ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.6224","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":"1201.6224","created_at":"2026-05-18T04:03:18.860539+00:00"},{"alias_kind":"arxiv_version","alias_value":"1201.6224v2","created_at":"2026-05-18T04:03:18.860539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.6224","created_at":"2026-05-18T04:03:18.860539+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RU6BHWL2XV2","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RU6BHWL2XV2IJTW","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RU6BHWL","created_at":"2026-05-18T12:26:58.693483+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/7RU6BHWL2XV2IJTW6UQX3BPDJ2","json":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2.json","graph_json":"https://pith.science/api/pith-number/7RU6BHWL2XV2IJTW6UQX3BPDJ2/graph.json","events_json":"https://pith.science/api/pith-number/7RU6BHWL2XV2IJTW6UQX3BPDJ2/events.json","paper":"https://pith.science/paper/7RU6BHWL"},"agent_actions":{"view_html":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2","download_json":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2.json","view_paper":"https://pith.science/paper/7RU6BHWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1201.6224&json=true","fetch_graph":"https://pith.science/api/pith-number/7RU6BHWL2XV2IJTW6UQX3BPDJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/7RU6BHWL2XV2IJTW6UQX3BPDJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2/action/storage_attestation","attest_author":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2/action/author_attestation","sign_citation":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2/action/citation_signature","submit_replication":"https://pith.science/pith/7RU6BHWL2XV2IJTW6UQX3BPDJ2/action/replication_record"}},"created_at":"2026-05-18T04:03:18.860539+00:00","updated_at":"2026-05-18T04:03:18.860539+00:00"}