{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:E32NJ2AC5IWBA74CCA7LA5LZUJ","short_pith_number":"pith:E32NJ2AC","canonical_record":{"source":{"id":"1703.03856","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-10T22:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"816351a84dc285df309495d9fba4cf5a695caef72534f28ce84490f4d9a40b93","abstract_canon_sha256":"961ed6b51d1d381394715c5fa12741bab20d9d064b21e297ad7f2cdb0b5fd209"},"schema_version":"1.0"},"canonical_sha256":"26f4d4e802ea2c107f82103eb07579a26e1ae0dedadf3acd84f0fb4394a964e9","source":{"kind":"arxiv","id":"1703.03856","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03856","created_at":"2026-05-18T00:43:47Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03856v2","created_at":"2026-05-18T00:43:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03856","created_at":"2026-05-18T00:43:47Z"},{"alias_kind":"pith_short_12","alias_value":"E32NJ2AC5IWB","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"E32NJ2AC5IWBA74C","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"E32NJ2AC","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:E32NJ2AC5IWBA74CCA7LA5LZUJ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.03856","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-10T22:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"816351a84dc285df309495d9fba4cf5a695caef72534f28ce84490f4d9a40b93","abstract_canon_sha256":"961ed6b51d1d381394715c5fa12741bab20d9d064b21e297ad7f2cdb0b5fd209"},"schema_version":"1.0"},"canonical_sha256":"26f4d4e802ea2c107f82103eb07579a26e1ae0dedadf3acd84f0fb4394a964e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:47.910416Z","signature_b64":"aFhphOZLSGtIPGIHdj5hF2B2BGChghnnACYlARqqmRv7SO/LJJ64CSf/6+2s201YUddV3BKdELGaaaj1iBoBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26f4d4e802ea2c107f82103eb07579a26e1ae0dedadf3acd84f0fb4394a964e9","last_reissued_at":"2026-05-18T00:43:47.909966Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:47.909966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.03856","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":"2026-05-18T00:43:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lTtkwVM7OOmCBDPCZhJ19iqNG5jpNekeLLDS4BugEk9aTukeMMTT75459ZpZ9ejJ9Wkt+OrLZxTSUjXHz6SWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:55:34.897984Z"},"content_sha256":"9afadd473d415117a36acd0a8ae0d98e365546b9ed13f53cfc6358d3fdd3308a","schema_version":"1.0","event_id":"sha256:9afadd473d415117a36acd0a8ae0d98e365546b9ed13f53cfc6358d3fdd3308a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:E32NJ2AC5IWBA74CCA7LA5LZUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Database Summarization for Interactive Data Exploration","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":"2017-03-10T22:17:22Z","abstract_excerpt":"We present a probabilistic approach to generate a small, query-able summary of a dataset for interactive data exploration. Departing from traditional summarization techniques, we use the Principle of Maximum Entropy to generate a probabilistic representation of the data that can be used to give approximate query answers. We develop the theoretical framework and formulation of our probabilistic representation and show how to use it to answer queries. We then present solving techniques and give three critical optimizations to improve preprocessing time and query accuracy. Lastly, we experimental"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03856","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":""},"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":"2026-05-18T00:43:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tZsgaf+3kq5ZKNQskO6cUgXNikIzmcIhJwBS4Cg+elRQX+HAkWMwWlSuL9M32Ul8XuS6fzqiR+zcq+2jPnHIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:55:34.898616Z"},"content_sha256":"b5d485992c27ee8f76c060c6922015e8573cacb3a95b27483a4b772b33f3c1c3","schema_version":"1.0","event_id":"sha256:b5d485992c27ee8f76c060c6922015e8573cacb3a95b27483a4b772b33f3c1c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ/bundle.json","state_url":"https://pith.science/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ/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":"2026-05-25T19:55:34Z","links":{"resolver":"https://pith.science/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ","bundle":"https://pith.science/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ/bundle.json","state":"https://pith.science/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E32NJ2AC5IWBA74CCA7LA5LZUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:E32NJ2AC5IWBA74CCA7LA5LZUJ","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":"961ed6b51d1d381394715c5fa12741bab20d9d064b21e297ad7f2cdb0b5fd209","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-10T22:17:22Z","title_canon_sha256":"816351a84dc285df309495d9fba4cf5a695caef72534f28ce84490f4d9a40b93"},"schema_version":"1.0","source":{"id":"1703.03856","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03856","created_at":"2026-05-18T00:43:47Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03856v2","created_at":"2026-05-18T00:43:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03856","created_at":"2026-05-18T00:43:47Z"},{"alias_kind":"pith_short_12","alias_value":"E32NJ2AC5IWB","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"E32NJ2AC5IWBA74C","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"E32NJ2AC","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:b5d485992c27ee8f76c060c6922015e8573cacb3a95b27483a4b772b33f3c1c3","target":"graph","created_at":"2026-05-18T00:43:47Z","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":"We present a probabilistic approach to generate a small, query-able summary of a dataset for interactive data exploration. Departing from traditional summarization techniques, we use the Principle of Maximum Entropy to generate a probabilistic representation of the data that can be used to give approximate query answers. We develop the theoretical framework and formulation of our probabilistic representation and show how to use it to answer queries. We then present solving techniques and give three critical optimizations to improve preprocessing time and query accuracy. Lastly, we experimental","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":"2017-03-10T22:17:22Z","title":"Probabilistic Database Summarization for Interactive Data Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03856","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":"sha256:9afadd473d415117a36acd0a8ae0d98e365546b9ed13f53cfc6358d3fdd3308a","target":"record","created_at":"2026-05-18T00:43:47Z","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":"961ed6b51d1d381394715c5fa12741bab20d9d064b21e297ad7f2cdb0b5fd209","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-10T22:17:22Z","title_canon_sha256":"816351a84dc285df309495d9fba4cf5a695caef72534f28ce84490f4d9a40b93"},"schema_version":"1.0","source":{"id":"1703.03856","kind":"arxiv","version":2}},"canonical_sha256":"26f4d4e802ea2c107f82103eb07579a26e1ae0dedadf3acd84f0fb4394a964e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26f4d4e802ea2c107f82103eb07579a26e1ae0dedadf3acd84f0fb4394a964e9","first_computed_at":"2026-05-18T00:43:47.909966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:47.909966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aFhphOZLSGtIPGIHdj5hF2B2BGChghnnACYlARqqmRv7SO/LJJ64CSf/6+2s201YUddV3BKdELGaaaj1iBoBDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:47.910416Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.03856","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9afadd473d415117a36acd0a8ae0d98e365546b9ed13f53cfc6358d3fdd3308a","sha256:b5d485992c27ee8f76c060c6922015e8573cacb3a95b27483a4b772b33f3c1c3"],"state_sha256":"e0ae261a1c7ec2d9f75fe3e6b10ee008febd793ef89a92f8aec5ef0a7be758b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1x8BwM+3xD0fTwDZsk+Tr7Lv1m4vN1h3Laqg+guOBCT0Sx5wrSehECgkk0QTLMqICulAHqQHHNateQ1pcMlDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:55:34.901800Z","bundle_sha256":"95d2c9c98b6010d358b865393d4be000410a53cfb6b09c4d48c15bddbddab9ec"}}