{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:OPSS7L5HFX7AESPVUUBFKNDJOD","short_pith_number":"pith:OPSS7L5H","schema_version":"1.0","canonical_sha256":"73e52fafa72dfe0249f5a50255346970cffa8c69f5699f83363b91acb046a4eb","source":{"kind":"arxiv","id":"1412.4842","version":1},"attestation_state":"computed","paper":{"title":"Similarity Group-by Operators for Multi-dimensional Relational Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Mikhail J. Atallah, Mingjie Tang, Mourad Ouzzani, Qutaibah M. Malluhi, Ruby Y.Tahboub, Walid G.Are, Yasin N. Silva","submitted_at":"2014-12-16T00:27:52Z","abstract_excerpt":"The SQL group-by operator plays an important role in summarizing and aggregating large datasets in a data analytic stack.While the standard group-by operator, which is based on equality, is useful in several applications, allowing similarity aware grouping provides a more realistic view on real-world data that could lead to better insights. The Similarity SQL-based Group-By operator (SGB, for short) extends the semantics of the standard SQL Group-by by grouping data with similar but not necessarily equal values. While existing similarity-based grouping operators efficiently materialize this ap"},"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":"1412.4842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-12-16T00:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"850c32a05166cef8edf8992d4865380d066e6a661e58a48befe6d7d80b838967","abstract_canon_sha256":"fbdbc3fa635fd0357d1a17a58877eaaf622f1c9ec70d37c1c2ae981d9caab6a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:10.351576Z","signature_b64":"CbrpOzRirBAMnZI17aGXtn8jyP0kcdJWX3ylgPZYGOKF3kNynhg1ejxGdnjdvplTjvwYVandPXUqqQ8EGojTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e52fafa72dfe0249f5a50255346970cffa8c69f5699f83363b91acb046a4eb","last_reissued_at":"2026-05-18T02:31:10.351117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:10.351117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similarity Group-by Operators for Multi-dimensional Relational Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Mikhail J. Atallah, Mingjie Tang, Mourad Ouzzani, Qutaibah M. Malluhi, Ruby Y.Tahboub, Walid G.Are, Yasin N. Silva","submitted_at":"2014-12-16T00:27:52Z","abstract_excerpt":"The SQL group-by operator plays an important role in summarizing and aggregating large datasets in a data analytic stack.While the standard group-by operator, which is based on equality, is useful in several applications, allowing similarity aware grouping provides a more realistic view on real-world data that could lead to better insights. The Similarity SQL-based Group-By operator (SGB, for short) extends the semantics of the standard SQL Group-by by grouping data with similar but not necessarily equal values. While existing similarity-based grouping operators efficiently materialize this ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4842","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":"1412.4842","created_at":"2026-05-18T02:31:10.351183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.4842v1","created_at":"2026-05-18T02:31:10.351183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4842","created_at":"2026-05-18T02:31:10.351183+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPSS7L5HFX7A","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPSS7L5HFX7AESPV","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPSS7L5H","created_at":"2026-05-18T12:28:41.024544+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/OPSS7L5HFX7AESPVUUBFKNDJOD","json":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD.json","graph_json":"https://pith.science/api/pith-number/OPSS7L5HFX7AESPVUUBFKNDJOD/graph.json","events_json":"https://pith.science/api/pith-number/OPSS7L5HFX7AESPVUUBFKNDJOD/events.json","paper":"https://pith.science/paper/OPSS7L5H"},"agent_actions":{"view_html":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD","download_json":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD.json","view_paper":"https://pith.science/paper/OPSS7L5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.4842&json=true","fetch_graph":"https://pith.science/api/pith-number/OPSS7L5HFX7AESPVUUBFKNDJOD/graph.json","fetch_events":"https://pith.science/api/pith-number/OPSS7L5HFX7AESPVUUBFKNDJOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/action/storage_attestation","attest_author":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/action/author_attestation","sign_citation":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/action/citation_signature","submit_replication":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/action/replication_record"}},"created_at":"2026-05-18T02:31:10.351183+00:00","updated_at":"2026-05-18T02:31:10.351183+00:00"}