{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JCGHQ4Q6JOAYPDK7SBO2VH7F4D","short_pith_number":"pith:JCGHQ4Q6","schema_version":"1.0","canonical_sha256":"488c78721e4b81878d5f905daa9fe5e0cf6dbfa3bd3fc9c256f4a71c29216ae2","source":{"kind":"arxiv","id":"1709.04747","version":1},"attestation_state":"computed","paper":{"title":"T${}^2$K${}^2$: The Twitter Top-K Keywords Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Ciprian-Octavian Truic\\u{a} (UPB), J\\'er\\^ome Darmont (ERIC)","submitted_at":"2017-09-14T13:01:51Z","abstract_excerpt":"Information retrieval from textual data focuses on the construction of vocabularies that contain weighted term tuples. Such vocabularies can then be exploited by various text analysis algorithms to extract new knowledge, e.g., top-k keywords, top-k documents, etc. Top-k keywords are casually used for various purposes, are often computed on-the-fly, and thus must be efficiently computed. To compare competing weighting schemes and database implementations, benchmarking is customary. To the best of our knowledge, no benchmark currently addresses these problems. Hence, in this paper, we present a "},"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":"1709.04747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-14T13:01:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a37d886d96d535b96220c0dc1e3d955d8580b5b6cdfb4061c6e41712fb16f3ee","abstract_canon_sha256":"f40ee199dfe5c809e4659c78adabe912a5bb888546360be29e9b7f719a3670e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:10.265937Z","signature_b64":"Evp1ME0FyOH0kKcHOE9dqZSHlVtEXnN3yYejnOP61f7sodg7WWVdihRs4MX6qzctENVReWo2DileTvRzgTA7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488c78721e4b81878d5f905daa9fe5e0cf6dbfa3bd3fc9c256f4a71c29216ae2","last_reissued_at":"2026-05-18T00:35:10.265482Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:10.265482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T${}^2$K${}^2$: The Twitter Top-K Keywords Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Ciprian-Octavian Truic\\u{a} (UPB), J\\'er\\^ome Darmont (ERIC)","submitted_at":"2017-09-14T13:01:51Z","abstract_excerpt":"Information retrieval from textual data focuses on the construction of vocabularies that contain weighted term tuples. Such vocabularies can then be exploited by various text analysis algorithms to extract new knowledge, e.g., top-k keywords, top-k documents, etc. Top-k keywords are casually used for various purposes, are often computed on-the-fly, and thus must be efficiently computed. To compare competing weighting schemes and database implementations, benchmarking is customary. To the best of our knowledge, no benchmark currently addresses these problems. Hence, in this paper, we present a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04747","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":"1709.04747","created_at":"2026-05-18T00:35:10.265559+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04747v1","created_at":"2026-05-18T00:35:10.265559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04747","created_at":"2026-05-18T00:35:10.265559+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCGHQ4Q6JOAY","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCGHQ4Q6JOAYPDK7","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCGHQ4Q6","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/JCGHQ4Q6JOAYPDK7SBO2VH7F4D","json":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D.json","graph_json":"https://pith.science/api/pith-number/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/graph.json","events_json":"https://pith.science/api/pith-number/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/events.json","paper":"https://pith.science/paper/JCGHQ4Q6"},"agent_actions":{"view_html":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D","download_json":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D.json","view_paper":"https://pith.science/paper/JCGHQ4Q6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04747&json=true","fetch_graph":"https://pith.science/api/pith-number/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/graph.json","fetch_events":"https://pith.science/api/pith-number/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/action/storage_attestation","attest_author":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/action/author_attestation","sign_citation":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/action/citation_signature","submit_replication":"https://pith.science/pith/JCGHQ4Q6JOAYPDK7SBO2VH7F4D/action/replication_record"}},"created_at":"2026-05-18T00:35:10.265559+00:00","updated_at":"2026-05-18T00:35:10.265559+00:00"}