{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HLVORLZO7NAMO2P35ZNZG2BFGM","short_pith_number":"pith:HLVORLZO","canonical_record":{"source":{"id":"1810.04361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T04:12:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"126e75cc97a6bb469ea828ac952b8b2e68f0fea15c753b9223f3831ec17b80d1","abstract_canon_sha256":"347e4225ad8524f5b7c75dc30593d56f276c2cbd1dca25dc3b4a79001be11d0b"},"schema_version":"1.0"},"canonical_sha256":"3aeae8af2efb40c769fbee5b93682533099fe52c199462d4a9ba37a95dc48529","source":{"kind":"arxiv","id":"1810.04361","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04361","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04361v1","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04361","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"HLVORLZO7NAM","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"HLVORLZO7NAMO2P3","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"HLVORLZO","created_at":"2026-07-05T01:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HLVORLZO7NAMO2P35ZNZG2BFGM","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T04:12:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"126e75cc97a6bb469ea828ac952b8b2e68f0fea15c753b9223f3831ec17b80d1","abstract_canon_sha256":"347e4225ad8524f5b7c75dc30593d56f276c2cbd1dca25dc3b4a79001be11d0b"},"schema_version":"1.0"},"canonical_sha256":"3aeae8af2efb40c769fbee5b93682533099fe52c199462d4a9ba37a95dc48529","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:33.714209Z","signature_b64":"1/T60OCXCC1TobysmkL4rd6eCbbPFSPPHNAFbOPKkbcfLWqLtmUwmu0mLP6cJe5BCOkwlmgjtYHcbZJwnTCZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aeae8af2efb40c769fbee5b93682533099fe52c199462d4a9ba37a95dc48529","last_reissued_at":"2026-07-05T01:05:33.713784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:33.713784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04361","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":"2026-07-05T01:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DmLybQXRIvXWpIy6iom4yhyJD1vWfiFx+QaGjb+JyNP1/+7SttWeJpUJ5le+JTS0+IAZWcU9S9TZWU2RnlcVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:23:23.963742Z"},"content_sha256":"de90e5ec0137f20e57aaf0bae901a111a52965fce125253095a3cf296d7afb23","schema_version":"1.0","event_id":"sha256:de90e5ec0137f20e57aaf0bae901a111a52965fce125253095a3cf296d7afb23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HLVORLZO7NAMO2P35ZNZG2BFGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised clustering for de-duplication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ihab Ilyas, Shai Ben-David, Shrinu Kushagra","submitted_at":"2018-10-10T04:12:50Z","abstract_excerpt":"Data de-duplication is the task of detecting multiple records that correspond to the same real-world entity in a database. In this work, we view de-duplication as a clustering problem where the goal is to put records corresponding to the same physical entity in the same cluster and putting records corresponding to different physical entities into different clusters.\n  We introduce a framework which we call promise correlation clustering. Given a complete graph $G$ with the edges labelled $0$ and $1$, the goal is to find a clustering that minimizes the number of $0$ edges within a cluster plus "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04361","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.04361/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sNrSK6iWkjLA8F01Dj0hsGH/yeRp6HtMLXxbhWXU/v7V5nNMZ18V6Tdl1oKdcsqWARgtCcs7fjwJlnfqfRzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:23:23.964112Z"},"content_sha256":"ee40f3b35ca07ba26aa2edc38a8ca9b3c88843a777223d72e90d4fd5c82a41e6","schema_version":"1.0","event_id":"sha256:ee40f3b35ca07ba26aa2edc38a8ca9b3c88843a777223d72e90d4fd5c82a41e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLVORLZO7NAMO2P35ZNZG2BFGM/bundle.json","state_url":"https://pith.science/pith/HLVORLZO7NAMO2P35ZNZG2BFGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLVORLZO7NAMO2P35ZNZG2BFGM/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":"2026-07-09T23:23:23Z","links":{"resolver":"https://pith.science/pith/HLVORLZO7NAMO2P35ZNZG2BFGM","bundle":"https://pith.science/pith/HLVORLZO7NAMO2P35ZNZG2BFGM/bundle.json","state":"https://pith.science/pith/HLVORLZO7NAMO2P35ZNZG2BFGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLVORLZO7NAMO2P35ZNZG2BFGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HLVORLZO7NAMO2P35ZNZG2BFGM","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":"347e4225ad8524f5b7c75dc30593d56f276c2cbd1dca25dc3b4a79001be11d0b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T04:12:50Z","title_canon_sha256":"126e75cc97a6bb469ea828ac952b8b2e68f0fea15c753b9223f3831ec17b80d1"},"schema_version":"1.0","source":{"id":"1810.04361","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04361","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04361v1","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04361","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"HLVORLZO7NAM","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"HLVORLZO7NAMO2P3","created_at":"2026-07-05T01:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"HLVORLZO","created_at":"2026-07-05T01:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:ee40f3b35ca07ba26aa2edc38a8ca9b3c88843a777223d72e90d4fd5c82a41e6","target":"graph","created_at":"2026-07-05T01:05:33Z","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/1810.04361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data de-duplication is the task of detecting multiple records that correspond to the same real-world entity in a database. In this work, we view de-duplication as a clustering problem where the goal is to put records corresponding to the same physical entity in the same cluster and putting records corresponding to different physical entities into different clusters.\n  We introduce a framework which we call promise correlation clustering. Given a complete graph $G$ with the edges labelled $0$ and $1$, the goal is to find a clustering that minimizes the number of $0$ edges within a cluster plus ","authors_text":"Ihab Ilyas, Shai Ben-David, Shrinu Kushagra","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T04:12:50Z","title":"Semi-supervised clustering for de-duplication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04361","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:de90e5ec0137f20e57aaf0bae901a111a52965fce125253095a3cf296d7afb23","target":"record","created_at":"2026-07-05T01:05:33Z","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":"347e4225ad8524f5b7c75dc30593d56f276c2cbd1dca25dc3b4a79001be11d0b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T04:12:50Z","title_canon_sha256":"126e75cc97a6bb469ea828ac952b8b2e68f0fea15c753b9223f3831ec17b80d1"},"schema_version":"1.0","source":{"id":"1810.04361","kind":"arxiv","version":1}},"canonical_sha256":"3aeae8af2efb40c769fbee5b93682533099fe52c199462d4a9ba37a95dc48529","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3aeae8af2efb40c769fbee5b93682533099fe52c199462d4a9ba37a95dc48529","first_computed_at":"2026-07-05T01:05:33.713784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:33.713784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1/T60OCXCC1TobysmkL4rd6eCbbPFSPPHNAFbOPKkbcfLWqLtmUwmu0mLP6cJe5BCOkwlmgjtYHcbZJwnTCZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:33.714209Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04361","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de90e5ec0137f20e57aaf0bae901a111a52965fce125253095a3cf296d7afb23","sha256:ee40f3b35ca07ba26aa2edc38a8ca9b3c88843a777223d72e90d4fd5c82a41e6"],"state_sha256":"4873b837d89180f89a17c78dc53ee647ef3ffba820b78c25a9cde4fd6f0713b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O1QLAcaMTQQdjj0cs6n37Pc/huJknFe0Lck1GFKRgRh6TCn8ft3l4g2r/H3mFgiq1M4jPTyZvul48+KWgtGtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:23:23.966084Z","bundle_sha256":"0236b7beea2b570e8d6cabd89b902f65e2b46e634b2820a9b032cb4e7917ad33"}}