{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YB5NJQVQFV5L76O2FKSA6PZPYX","short_pith_number":"pith:YB5NJQVQ","canonical_record":{"source":{"id":"2008.10549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T16:41:47Z","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"title_canon_sha256":"1bd9bb76a379f3287361726e3f2522007bc5d2a92daea7685e6cbebdee4e37f3","abstract_canon_sha256":"d2fa0c35960adc4c15a60c1f6c46e9a8d154f52e21c0869ab0499796ee2fecf0"},"schema_version":"1.0"},"canonical_sha256":"c07ad4c2b02d7abff9da2aa40f3f2fc5e72974de184e9bb690f6d887d2e427c5","source":{"kind":"arxiv","id":"2008.10549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.10549","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2008.10549v1","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10549","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"YB5NJQVQFV5L","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"YB5NJQVQFV5L76O2","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"YB5NJQVQ","created_at":"2026-07-05T01:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YB5NJQVQFV5L76O2FKSA6PZPYX","target":"record","payload":{"canonical_record":{"source":{"id":"2008.10549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T16:41:47Z","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"title_canon_sha256":"1bd9bb76a379f3287361726e3f2522007bc5d2a92daea7685e6cbebdee4e37f3","abstract_canon_sha256":"d2fa0c35960adc4c15a60c1f6c46e9a8d154f52e21c0869ab0499796ee2fecf0"},"schema_version":"1.0"},"canonical_sha256":"c07ad4c2b02d7abff9da2aa40f3f2fc5e72974de184e9bb690f6d887d2e427c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:25.460573Z","signature_b64":"fGGGV211eCtnrECQZT3xndHxQ/jOqZ0CFJX4V2b/8YxyCXBvOQBXBFWjYhlUYg/N7mWZvOkWw1GBW8SBVoQPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c07ad4c2b02d7abff9da2aa40f3f2fc5e72974de184e9bb690f6d887d2e427c5","last_reissued_at":"2026-07-05T01:29:25.460117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:25.460117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.10549","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":"2026-07-05T01:29:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PMo+0bSb1eMAPvrJw6EByxL8Nk4fYD5Fh56q2B8VWdf4Eg/xtS+8s9j/gjWPi0kikvMNRRnbvqnrzFipbEFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:59:58.976747Z"},"content_sha256":"586fba6a7b8fbd2ddfd56d50dbdf7c992462ee24e877d9def861e657c8c20456","schema_version":"1.0","event_id":"sha256:586fba6a7b8fbd2ddfd56d50dbdf7c992462ee24e877d9def861e657c8c20456"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YB5NJQVQFV5L76O2FKSA6PZPYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On sampling from data with duplicate records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Heidari, Ihab F. Ilyas, Shrinu Kushagra","submitted_at":"2020-08-24T16:41:47Z","abstract_excerpt":"Data deduplication is the task of detecting records in a database that correspond to the same real-world entity. Our goal is to develop a procedure that samples uniformly from the set of entities present in the database in the presence of duplicates. We accomplish this by a two-stage process. In the first step, we estimate the frequencies of all the entities in the database. In the second step, we use rejection sampling to obtain a (approximately) uniform sample from the set of entities. However, efficiently estimating the frequency of all the entities is a non-trivial task and not attainable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10549","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/2008.10549/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":"2026-07-05T01:29:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zXZWHdVrU8/ikwzKtdIlSLR6WQxJZzMjVyZoOGvB7X0/FnGCaV0t4Y5XmbbVB6TI0FKp58riF/1a3djYfsNFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:59:58.977136Z"},"content_sha256":"d20c920ca326c3696ef9d1a96f45fd956fa65f21908bad155c068943db2c8af8","schema_version":"1.0","event_id":"sha256:d20c920ca326c3696ef9d1a96f45fd956fa65f21908bad155c068943db2c8af8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YB5NJQVQFV5L76O2FKSA6PZPYX/bundle.json","state_url":"https://pith.science/pith/YB5NJQVQFV5L76O2FKSA6PZPYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YB5NJQVQFV5L76O2FKSA6PZPYX/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":"2026-07-09T06:59:58Z","links":{"resolver":"https://pith.science/pith/YB5NJQVQFV5L76O2FKSA6PZPYX","bundle":"https://pith.science/pith/YB5NJQVQFV5L76O2FKSA6PZPYX/bundle.json","state":"https://pith.science/pith/YB5NJQVQFV5L76O2FKSA6PZPYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YB5NJQVQFV5L76O2FKSA6PZPYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YB5NJQVQFV5L76O2FKSA6PZPYX","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":"d2fa0c35960adc4c15a60c1f6c46e9a8d154f52e21c0869ab0499796ee2fecf0","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T16:41:47Z","title_canon_sha256":"1bd9bb76a379f3287361726e3f2522007bc5d2a92daea7685e6cbebdee4e37f3"},"schema_version":"1.0","source":{"id":"2008.10549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.10549","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2008.10549v1","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10549","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"YB5NJQVQFV5L","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"YB5NJQVQFV5L76O2","created_at":"2026-07-05T01:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"YB5NJQVQ","created_at":"2026-07-05T01:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:d20c920ca326c3696ef9d1a96f45fd956fa65f21908bad155c068943db2c8af8","target":"graph","created_at":"2026-07-05T01:29:25Z","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/2008.10549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data deduplication is the task of detecting records in a database that correspond to the same real-world entity. Our goal is to develop a procedure that samples uniformly from the set of entities present in the database in the presence of duplicates. We accomplish this by a two-stage process. In the first step, we estimate the frequencies of all the entities in the database. In the second step, we use rejection sampling to obtain a (approximately) uniform sample from the set of entities. However, efficiently estimating the frequency of all the entities is a non-trivial task and not attainable ","authors_text":"Alireza Heidari, Ihab F. Ilyas, Shrinu Kushagra","cross_cats":["cs.DB","cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T16:41:47Z","title":"On sampling from data with duplicate records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10549","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":"sha256:586fba6a7b8fbd2ddfd56d50dbdf7c992462ee24e877d9def861e657c8c20456","target":"record","created_at":"2026-07-05T01:29:25Z","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":"d2fa0c35960adc4c15a60c1f6c46e9a8d154f52e21c0869ab0499796ee2fecf0","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T16:41:47Z","title_canon_sha256":"1bd9bb76a379f3287361726e3f2522007bc5d2a92daea7685e6cbebdee4e37f3"},"schema_version":"1.0","source":{"id":"2008.10549","kind":"arxiv","version":1}},"canonical_sha256":"c07ad4c2b02d7abff9da2aa40f3f2fc5e72974de184e9bb690f6d887d2e427c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c07ad4c2b02d7abff9da2aa40f3f2fc5e72974de184e9bb690f6d887d2e427c5","first_computed_at":"2026-07-05T01:29:25.460117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:29:25.460117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fGGGV211eCtnrECQZT3xndHxQ/jOqZ0CFJX4V2b/8YxyCXBvOQBXBFWjYhlUYg/N7mWZvOkWw1GBW8SBVoQPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:29:25.460573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.10549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:586fba6a7b8fbd2ddfd56d50dbdf7c992462ee24e877d9def861e657c8c20456","sha256:d20c920ca326c3696ef9d1a96f45fd956fa65f21908bad155c068943db2c8af8"],"state_sha256":"675832372c9f9e007712f75b84cba1fcb69274fc54aa9cee41757a9b121c0b27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qSesaoWCQIH5Ovg6L70pVzzMINKV9fvIdTCrPrjwZ7KELZ508kBTNfn7YCaWODIc0t8O9nSY8ar/U4GdeZ+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:59:58.980718Z","bundle_sha256":"e4a2cb462168cba743622c207831d95463bcdc5a8f490fda5872e865eaf7cd80"}}