{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:I2DIA2MDELH7WUP2A6CUYWUFA2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"61f00d3532ac7abdd6a1d6bb1994c739afa8572685381ece6fbb24aae59a05ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-08-07T09:19:50Z","title_canon_sha256":"4e331cc7c78074a97dd03f27d34bd36970284be143bcfe74d1c2d4486853b0df"},"schema_version":"1.0","source":{"id":"2008.03053","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03053","created_at":"2026-07-05T03:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03053v2","created_at":"2026-07-05T03:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03053","created_at":"2026-07-05T03:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"I2DIA2MDELH7","created_at":"2026-07-05T03:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"I2DIA2MDELH7WUP2","created_at":"2026-07-05T03:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"I2DIA2MD","created_at":"2026-07-05T03:22:32Z"}],"graph_snapshots":[{"event_id":"sha256:bdb3aeb1c421fc709b4dbed03174562d069248c4639aab368bce47f1048017c6","target":"graph","created_at":"2026-07-05T03:22:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.03053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data summarization that presents a small subset of a dataset to users has been widely applied in numerous applications and systems. Many datasets are coded with hierarchical terminologies, e.g., the international classification of Diseases-9, Medical Subject Heading, and Gene Ontology, to name a few. In this paper, we study the problem of selecting a diverse set of k elements to summarize an input dataset with hierarchical terminologies, and visualize the summary in an ontology structure. We propose an efficient greedy algorithm to solve the problem with (1-1/e) = 62% -approximation guarantee.","authors_text":"Byron Choi, Jianliang Xu, Jiming Liu, William K. Cheung, Xin Huang, Xuliang Zhu, Yanchun Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-08-07T09:19:50Z","title":"Efficient and Optimal Algorithms for Tree Summarization with Weighted Terminologies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03053","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f53e6989da0b1408b533eb814183ec0d4f3dff5a5f827f2f539104d86bceaf26","target":"record","created_at":"2026-07-05T03:22:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"61f00d3532ac7abdd6a1d6bb1994c739afa8572685381ece6fbb24aae59a05ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-08-07T09:19:50Z","title_canon_sha256":"4e331cc7c78074a97dd03f27d34bd36970284be143bcfe74d1c2d4486853b0df"},"schema_version":"1.0","source":{"id":"2008.03053","kind":"arxiv","version":2}},"canonical_sha256":"468680698322cffb51fa07854c5a850682e4d591811609edb657b4a9704d0ead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"468680698322cffb51fa07854c5a850682e4d591811609edb657b4a9704d0ead","first_computed_at":"2026-07-05T03:22:32.630702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:32.630702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z7FwPdBeBPb0jWCZwg4Em9/3OhmwJOtcv7JUyr/PwJ9nKO2KMB2oFgoUOOUQDShWols1DPf1oxWXY3IFU4waCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:32.631107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03053","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f53e6989da0b1408b533eb814183ec0d4f3dff5a5f827f2f539104d86bceaf26","sha256:bdb3aeb1c421fc709b4dbed03174562d069248c4639aab368bce47f1048017c6"],"state_sha256":"ed457620263d662cb20c43d89bbcdb6c729664f96dbbdb43ebd57a3a7de2b67a"}