{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:OPSS7L5HFX7AESPVUUBFKNDJOD","short_pith_number":"pith:OPSS7L5H","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"},"canonical_sha256":"73e52fafa72dfe0249f5a50255346970cffa8c69f5699f83363b91acb046a4eb","source":{"kind":"arxiv","id":"1412.4842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4842","created_at":"2026-05-18T02:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4842v1","created_at":"2026-05-18T02:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4842","created_at":"2026-05-18T02:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"OPSS7L5HFX7A","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"OPSS7L5HFX7AESPV","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"OPSS7L5H","created_at":"2026-05-18T12:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:OPSS7L5HFX7AESPVUUBFKNDJOD","target":"record","payload":{"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"},"canonical_sha256":"73e52fafa72dfe0249f5a50255346970cffa8c69f5699f83363b91acb046a4eb","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"},"source_kind":"arxiv","source_id":"1412.4842","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:31:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijCuLS8HyzpoRdsHPdrd6KTCNn2uT833qaWoyrbIjCoCYggLy8tf2VVd+FcsqTzwTFK7P2cShfTu2ppdDTaxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:00:22.053453Z"},"content_sha256":"1bcf579f1a4d28462b730014d66694483ce03920543b7cea5e5a751f137a4488","schema_version":"1.0","event_id":"sha256:1bcf579f1a4d28462b730014d66694483ce03920543b7cea5e5a751f137a4488"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:OPSS7L5HFX7AESPVUUBFKNDJOD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:31:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZyKzckD48M8UjVctelHbSugf/ZT8+Mwvu8KyF+38NIQoVpT7NkWCSxRe7QMkt8jjVXlJaq16n1wHUys7PAACBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:00:22.054041Z"},"content_sha256":"a3cfa3a25f2a7f9f4b39dd4f2d99c787b85f5d9107b0439f3e42a6db26bc7b62","schema_version":"1.0","event_id":"sha256:a3cfa3a25f2a7f9f4b39dd4f2d99c787b85f5d9107b0439f3e42a6db26bc7b62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/bundle.json","state_url":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T19:00:22Z","links":{"resolver":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD","bundle":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/bundle.json","state":"https://pith.science/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPSS7L5HFX7AESPVUUBFKNDJOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:OPSS7L5HFX7AESPVUUBFKNDJOD","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":"fbdbc3fa635fd0357d1a17a58877eaaf622f1c9ec70d37c1c2ae981d9caab6a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-12-16T00:27:52Z","title_canon_sha256":"850c32a05166cef8edf8992d4865380d066e6a661e58a48befe6d7d80b838967"},"schema_version":"1.0","source":{"id":"1412.4842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4842","created_at":"2026-05-18T02:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4842v1","created_at":"2026-05-18T02:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4842","created_at":"2026-05-18T02:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"OPSS7L5HFX7A","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"OPSS7L5HFX7AESPV","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"OPSS7L5H","created_at":"2026-05-18T12:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:a3cfa3a25f2a7f9f4b39dd4f2d99c787b85f5d9107b0439f3e42a6db26bc7b62","target":"graph","created_at":"2026-05-18T02:31:10Z","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"},"paper":{"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","authors_text":"Mikhail J. Atallah, Mingjie Tang, Mourad Ouzzani, Qutaibah M. Malluhi, Ruby Y.Tahboub, Walid G.Are, Yasin N. Silva","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-12-16T00:27:52Z","title":"Similarity Group-by Operators for Multi-dimensional Relational Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4842","kind":"arxiv","version":1},"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":"sha256:1bcf579f1a4d28462b730014d66694483ce03920543b7cea5e5a751f137a4488","target":"record","created_at":"2026-05-18T02:31:10Z","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":"fbdbc3fa635fd0357d1a17a58877eaaf622f1c9ec70d37c1c2ae981d9caab6a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-12-16T00:27:52Z","title_canon_sha256":"850c32a05166cef8edf8992d4865380d066e6a661e58a48befe6d7d80b838967"},"schema_version":"1.0","source":{"id":"1412.4842","kind":"arxiv","version":1}},"canonical_sha256":"73e52fafa72dfe0249f5a50255346970cffa8c69f5699f83363b91acb046a4eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73e52fafa72dfe0249f5a50255346970cffa8c69f5699f83363b91acb046a4eb","first_computed_at":"2026-05-18T02:31:10.351117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:31:10.351117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CbrpOzRirBAMnZI17aGXtn8jyP0kcdJWX3ylgPZYGOKF3kNynhg1ejxGdnjdvplTjvwYVandPXUqqQ8EGojTCw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:31:10.351576Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.4842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bcf579f1a4d28462b730014d66694483ce03920543b7cea5e5a751f137a4488","sha256:a3cfa3a25f2a7f9f4b39dd4f2d99c787b85f5d9107b0439f3e42a6db26bc7b62"],"state_sha256":"109e25ba4f4c9250f9647ddef5e7b1c282cc4d04b754211273a374d73ae563b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmJ35ewp7ySuJdVE/E6zqvnMZAS5VE0yO9zpJQLOWTZHet+Lmpf/rbSiNeUK2MDT/upx7u1+OoY3NEFcVrXzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:00:22.056539Z","bundle_sha256":"6084b8ec8bb7caa3af583c043c3e370214e9415f1cd8b3bd042bfed645a03fdc"}}