{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7HKIEKX37RP5R64S66SAVT3MVO","short_pith_number":"pith:7HKIEKX3","canonical_record":{"source":{"id":"2002.09799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-02-23T00:53:04Z","cross_cats_sorted":[],"title_canon_sha256":"9e46bbc9aea7273512d7871fbb7db90bb978bf00fd98bf3393762170eb270cbb","abstract_canon_sha256":"1ba2d4f5d96d9ab3bea239b0e17a5d47d360490fd1729141bd8fbd9b73cc04d5"},"schema_version":"1.0"},"canonical_sha256":"f9d4822afbfc5fd8fb92f7a40acf6cab9f7ad51e8b717331e8b64b46cb21a84a","source":{"kind":"arxiv","id":"2002.09799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09799","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09799v2","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09799","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"7HKIEKX37RP5","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"pith_short_16","alias_value":"7HKIEKX37RP5R64S","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"pith_short_8","alias_value":"7HKIEKX3","created_at":"2026-07-05T00:44:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7HKIEKX37RP5R64S66SAVT3MVO","target":"record","payload":{"canonical_record":{"source":{"id":"2002.09799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-02-23T00:53:04Z","cross_cats_sorted":[],"title_canon_sha256":"9e46bbc9aea7273512d7871fbb7db90bb978bf00fd98bf3393762170eb270cbb","abstract_canon_sha256":"1ba2d4f5d96d9ab3bea239b0e17a5d47d360490fd1729141bd8fbd9b73cc04d5"},"schema_version":"1.0"},"canonical_sha256":"f9d4822afbfc5fd8fb92f7a40acf6cab9f7ad51e8b717331e8b64b46cb21a84a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:42.923652Z","signature_b64":"qVdN/L/fEyhRoPndCQ74MJDedpeV5BuDMESikwI5UHU+1CwR1rKpylY79/LYvQQdANXrOrWxbf1kLnd9YCMjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d4822afbfc5fd8fb92f7a40acf6cab9f7ad51e8b717331e8b64b46cb21a84a","last_reissued_at":"2026-07-05T00:44:42.923234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:42.923234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.09799","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G553DkAT6KVy/9YYWi7VLd503tNumLpbAAMR0oRMAxXaA2J+qRBZ5Tkh2G2WfFs7uOSWXRd5qOFflQq+BPkuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:07:52.440127Z"},"content_sha256":"8543f48f8a17b04fa9815922303e3ca19c98201b0114d53f2a66b93f1a97ac56","schema_version":"1.0","event_id":"sha256:8543f48f8a17b04fa9815922303e3ca19c98201b0114d53f2a66b93f1a97ac56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7HKIEKX37RP5R64S66SAVT3MVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Debiasing in the Themis Open World Database System (Extended Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dan Suciu, Laurel Orr, Magda Balazinska","submitted_at":"2020-02-23T00:53:04Z","abstract_excerpt":"Open world database management systems assume tuples not in the database still exist and are becoming an increasingly important area of research. We present Themis, the first open world database that automatically rebalances arbitrarily biased samples to approximately answer queries as if they were issued over the entire population. We leverage apriori population aggregate information to develop and combine two different approaches for automatic debiasing: sample reweighting and Bayesian network probabilistic modeling. We build a prototype of Themis and demonstrate that Themis achieves higher "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09799","kind":"arxiv","version":2},"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/2002.09799/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":"2026-07-05T00:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fPOl5ZZJa7nTi6sJ9aE4G2v6fEXKEocUCg2LJKhy3NSy1WeeGhR/Mmkkw/ffwxyoVSO8FgKiquSeckqTA81JAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:07:52.441000Z"},"content_sha256":"00dfc79a8463a106e76017478c61334f08a4cf3303dbc8b0359ee9d955ceb36d","schema_version":"1.0","event_id":"sha256:00dfc79a8463a106e76017478c61334f08a4cf3303dbc8b0359ee9d955ceb36d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HKIEKX37RP5R64S66SAVT3MVO/bundle.json","state_url":"https://pith.science/pith/7HKIEKX37RP5R64S66SAVT3MVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HKIEKX37RP5R64S66SAVT3MVO/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":"2026-08-05T06:07:52Z","links":{"resolver":"https://pith.science/pith/7HKIEKX37RP5R64S66SAVT3MVO","bundle":"https://pith.science/pith/7HKIEKX37RP5R64S66SAVT3MVO/bundle.json","state":"https://pith.science/pith/7HKIEKX37RP5R64S66SAVT3MVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HKIEKX37RP5R64S66SAVT3MVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7HKIEKX37RP5R64S66SAVT3MVO","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":"1ba2d4f5d96d9ab3bea239b0e17a5d47d360490fd1729141bd8fbd9b73cc04d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-02-23T00:53:04Z","title_canon_sha256":"9e46bbc9aea7273512d7871fbb7db90bb978bf00fd98bf3393762170eb270cbb"},"schema_version":"1.0","source":{"id":"2002.09799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09799","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09799v2","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09799","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"7HKIEKX37RP5","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"pith_short_16","alias_value":"7HKIEKX37RP5R64S","created_at":"2026-07-05T00:44:42Z"},{"alias_kind":"pith_short_8","alias_value":"7HKIEKX3","created_at":"2026-07-05T00:44:42Z"}],"graph_snapshots":[{"event_id":"sha256:00dfc79a8463a106e76017478c61334f08a4cf3303dbc8b0359ee9d955ceb36d","target":"graph","created_at":"2026-07-05T00:44:42Z","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/2002.09799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open world database management systems assume tuples not in the database still exist and are becoming an increasingly important area of research. We present Themis, the first open world database that automatically rebalances arbitrarily biased samples to approximately answer queries as if they were issued over the entire population. We leverage apriori population aggregate information to develop and combine two different approaches for automatic debiasing: sample reweighting and Bayesian network probabilistic modeling. We build a prototype of Themis and demonstrate that Themis achieves higher ","authors_text":"Dan Suciu, Laurel Orr, Magda Balazinska","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-02-23T00:53:04Z","title":"Sample Debiasing in the Themis Open World Database System (Extended Version)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09799","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":"sha256:8543f48f8a17b04fa9815922303e3ca19c98201b0114d53f2a66b93f1a97ac56","target":"record","created_at":"2026-07-05T00:44:42Z","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":"1ba2d4f5d96d9ab3bea239b0e17a5d47d360490fd1729141bd8fbd9b73cc04d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-02-23T00:53:04Z","title_canon_sha256":"9e46bbc9aea7273512d7871fbb7db90bb978bf00fd98bf3393762170eb270cbb"},"schema_version":"1.0","source":{"id":"2002.09799","kind":"arxiv","version":2}},"canonical_sha256":"f9d4822afbfc5fd8fb92f7a40acf6cab9f7ad51e8b717331e8b64b46cb21a84a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9d4822afbfc5fd8fb92f7a40acf6cab9f7ad51e8b717331e8b64b46cb21a84a","first_computed_at":"2026-07-05T00:44:42.923234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:42.923234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qVdN/L/fEyhRoPndCQ74MJDedpeV5BuDMESikwI5UHU+1CwR1rKpylY79/LYvQQdANXrOrWxbf1kLnd9YCMjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:42.923652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8543f48f8a17b04fa9815922303e3ca19c98201b0114d53f2a66b93f1a97ac56","sha256:00dfc79a8463a106e76017478c61334f08a4cf3303dbc8b0359ee9d955ceb36d"],"state_sha256":"e1d951a7f0f5d7518cc7bb87d02c3103710e8646ebb1857efb2e6b58ee36b082"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gf/HNa7ZbfZy2kO/zJOamMcvH85q51hq+2/Eq11mh9h1Aq+D8AJIcsFWpWS9fAQdVEXGEVyDE5qMb6KA2mLZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:07:52.484508Z","bundle_sha256":"1e430ada682ea38f3d5467821cb35a2c5b672e5e8ecccc8fc3db24bd23d160d9"}}