{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZJWVGWCYGS47TRD2PLX2ZWGDRT","short_pith_number":"pith:ZJWVGWCY","schema_version":"1.0","canonical_sha256":"ca6d53585834b9f9c47a7aefacd8c38cc5807acc81a8623e7098e62e341e0175","source":{"kind":"arxiv","id":"1606.06142","version":1},"attestation_state":"computed","paper":{"title":"Comparing the hierarchy of keywords in on-line news portals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"physics.soc-ph","authors_text":"David Sousa-Rodrigues, Gergely Palla, Gergely Tib\\'ely, P\\'eter Pollner","submitted_at":"2016-06-20T14:34:55Z","abstract_excerpt":"The tagging of on-line content with informative keywords is a widespread phenomenon from scientific article repositories through blogs to on-line news portals. In most of the cases, the tags on a given item are free words chosen by the authors independently. Therefore, relations among keywords in a collection of news items is unknown. However, in most cases the topics and concepts described by these keywords are forming a latent hierarchy, with the more general topics and categories at the top, and more specialised ones at the bottom. Here we apply a recent, cooccurrence-based tag hierarchy ex"},"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":"1606.06142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.soc-ph","submitted_at":"2016-06-20T14:34:55Z","cross_cats_sorted":["cs.CL","cs.SI"],"title_canon_sha256":"dc4ef1760db67424301e3d9d27ec86def686006f4e75f3a3993961a97abfe306","abstract_canon_sha256":"ebb361dbd1651ec057fe65119e42144ff5db095c0b733682eba97651f9824983"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:17.146597Z","signature_b64":"MqA8PkoMrDF7QiplMZ8VqphLTgp1d+ailSf35ZwLXdzG4hW93ZZGg1lN9tjvdXkKMhgvCSYbhG7/CLxkejlJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6d53585834b9f9c47a7aefacd8c38cc5807acc81a8623e7098e62e341e0175","last_reissued_at":"2026-05-18T00:51:17.145899Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:17.145899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing the hierarchy of keywords in on-line news portals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"physics.soc-ph","authors_text":"David Sousa-Rodrigues, Gergely Palla, Gergely Tib\\'ely, P\\'eter Pollner","submitted_at":"2016-06-20T14:34:55Z","abstract_excerpt":"The tagging of on-line content with informative keywords is a widespread phenomenon from scientific article repositories through blogs to on-line news portals. In most of the cases, the tags on a given item are free words chosen by the authors independently. Therefore, relations among keywords in a collection of news items is unknown. However, in most cases the topics and concepts described by these keywords are forming a latent hierarchy, with the more general topics and categories at the top, and more specialised ones at the bottom. Here we apply a recent, cooccurrence-based tag hierarchy ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.06142","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":"1606.06142","created_at":"2026-05-18T00:51:17.146016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.06142v1","created_at":"2026-05-18T00:51:17.146016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.06142","created_at":"2026-05-18T00:51:17.146016+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJWVGWCYGS47","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJWVGWCYGS47TRD2","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJWVGWCY","created_at":"2026-05-18T12:30:53.716459+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/ZJWVGWCYGS47TRD2PLX2ZWGDRT","json":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT.json","graph_json":"https://pith.science/api/pith-number/ZJWVGWCYGS47TRD2PLX2ZWGDRT/graph.json","events_json":"https://pith.science/api/pith-number/ZJWVGWCYGS47TRD2PLX2ZWGDRT/events.json","paper":"https://pith.science/paper/ZJWVGWCY"},"agent_actions":{"view_html":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT","download_json":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT.json","view_paper":"https://pith.science/paper/ZJWVGWCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.06142&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJWVGWCYGS47TRD2PLX2ZWGDRT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJWVGWCYGS47TRD2PLX2ZWGDRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT/action/storage_attestation","attest_author":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT/action/author_attestation","sign_citation":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT/action/citation_signature","submit_replication":"https://pith.science/pith/ZJWVGWCYGS47TRD2PLX2ZWGDRT/action/replication_record"}},"created_at":"2026-05-18T00:51:17.146016+00:00","updated_at":"2026-05-18T00:51:17.146016+00:00"}