{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WXD35XC2R3BBWDU2N3OD4TPGJW","short_pith_number":"pith:WXD35XC2","canonical_record":{"source":{"id":"2203.02754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-03-05T14:19:04Z","cross_cats_sorted":[],"title_canon_sha256":"52207e36b17cfd1be2a82d9ac1bdadea5540ef40e115165135b3be08dcf0c4a6","abstract_canon_sha256":"ea3b80333cd9b70d440a304dc01c2eb41cc3ec901a2e9a0f95c3bc2abc4bc908"},"schema_version":"1.0"},"canonical_sha256":"b5c7bedc5a8ec21b0e9a6edc3e4de64d8fc239864dd20094606cab15671f8ee4","source":{"kind":"arxiv","id":"2203.02754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02754","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02754v1","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02754","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"WXD35XC2R3BB","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"WXD35XC2R3BBWDU2","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"WXD35XC2","created_at":"2026-07-05T04:02:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WXD35XC2R3BBWDU2N3OD4TPGJW","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-03-05T14:19:04Z","cross_cats_sorted":[],"title_canon_sha256":"52207e36b17cfd1be2a82d9ac1bdadea5540ef40e115165135b3be08dcf0c4a6","abstract_canon_sha256":"ea3b80333cd9b70d440a304dc01c2eb41cc3ec901a2e9a0f95c3bc2abc4bc908"},"schema_version":"1.0"},"canonical_sha256":"b5c7bedc5a8ec21b0e9a6edc3e4de64d8fc239864dd20094606cab15671f8ee4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:27.083482Z","signature_b64":"p9g0G/YryYcLTS5tcfoVrp0mPEoQhtBe6e5CkjiDHeLmHBO3WXjncN2l9u+rlBK+aN8bVG1qjmQaEPbXCg20Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5c7bedc5a8ec21b0e9a6edc3e4de64d8fc239864dd20094606cab15671f8ee4","last_reissued_at":"2026-07-05T04:02:27.083048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:27.083048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02754","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":"2026-07-05T04:02:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKvg06fTNQRBqEFZLotel48Tx9cWwlqKvY3Ex53a8BMBaq3sZVVKuY7h12Jdvsc9vlTk0xTq4Eq56gqtQvemAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:46:04.666204Z"},"content_sha256":"214c9ba0cc4390ad3afa395e13a136184e88f636810365dc253dc6804903b614","schema_version":"1.0","event_id":"sha256:214c9ba0cc4390ad3afa395e13a136184e88f636810365dc253dc6804903b614"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WXD35XC2R3BBWDU2N3OD4TPGJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selecting Sub-tables for Data Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Amit Somech, Kathy Razmadze, Susan B. Davidson, Tova Milo, Yael Amsterdamer","submitted_at":"2022-03-05T14:19:04Z","abstract_excerpt":"We present a framework for creating small, informative sub-tables of large data tables to facilitate the first step of data science: data exploration. Given a large data table table T, the goal is to create a sub-table of small, fixed dimensions, by selecting a subset of T's rows and projecting them over a subset of T's columns. The question is: which rows and columns should be selected to yield an informative sub-table?\n  We formalize the notion of \"informativeness\" based on two complementary metrics: cell coverage, which measures how well the sub-table captures prominent association rules in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02754","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/2203.02754/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":"2026-07-05T04:02:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBWE2l+uAScKiEmb978n7kjvL7uYSryT04C9YSSDNz2bc7qi3ArRHncjoLDoa+5eQl9jqSuELM/WeR1luVQkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:46:04.666559Z"},"content_sha256":"135c529c7f37106c8cc26828e61d2e1649f2d945a62c29d0e87847dcbd706f6a","schema_version":"1.0","event_id":"sha256:135c529c7f37106c8cc26828e61d2e1649f2d945a62c29d0e87847dcbd706f6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXD35XC2R3BBWDU2N3OD4TPGJW/bundle.json","state_url":"https://pith.science/pith/WXD35XC2R3BBWDU2N3OD4TPGJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXD35XC2R3BBWDU2N3OD4TPGJW/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":"2026-08-21T18:46:04Z","links":{"resolver":"https://pith.science/pith/WXD35XC2R3BBWDU2N3OD4TPGJW","bundle":"https://pith.science/pith/WXD35XC2R3BBWDU2N3OD4TPGJW/bundle.json","state":"https://pith.science/pith/WXD35XC2R3BBWDU2N3OD4TPGJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXD35XC2R3BBWDU2N3OD4TPGJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WXD35XC2R3BBWDU2N3OD4TPGJW","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":"ea3b80333cd9b70d440a304dc01c2eb41cc3ec901a2e9a0f95c3bc2abc4bc908","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-03-05T14:19:04Z","title_canon_sha256":"52207e36b17cfd1be2a82d9ac1bdadea5540ef40e115165135b3be08dcf0c4a6"},"schema_version":"1.0","source":{"id":"2203.02754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02754","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02754v1","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02754","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"WXD35XC2R3BB","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"WXD35XC2R3BBWDU2","created_at":"2026-07-05T04:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"WXD35XC2","created_at":"2026-07-05T04:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:135c529c7f37106c8cc26828e61d2e1649f2d945a62c29d0e87847dcbd706f6a","target":"graph","created_at":"2026-07-05T04:02:27Z","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/2203.02754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a framework for creating small, informative sub-tables of large data tables to facilitate the first step of data science: data exploration. Given a large data table table T, the goal is to create a sub-table of small, fixed dimensions, by selecting a subset of T's rows and projecting them over a subset of T's columns. The question is: which rows and columns should be selected to yield an informative sub-table?\n  We formalize the notion of \"informativeness\" based on two complementary metrics: cell coverage, which measures how well the sub-table captures prominent association rules in","authors_text":"Amit Somech, Kathy Razmadze, Susan B. Davidson, Tova Milo, Yael Amsterdamer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-03-05T14:19:04Z","title":"Selecting Sub-tables for Data Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02754","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":"sha256:214c9ba0cc4390ad3afa395e13a136184e88f636810365dc253dc6804903b614","target":"record","created_at":"2026-07-05T04:02:27Z","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":"ea3b80333cd9b70d440a304dc01c2eb41cc3ec901a2e9a0f95c3bc2abc4bc908","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-03-05T14:19:04Z","title_canon_sha256":"52207e36b17cfd1be2a82d9ac1bdadea5540ef40e115165135b3be08dcf0c4a6"},"schema_version":"1.0","source":{"id":"2203.02754","kind":"arxiv","version":1}},"canonical_sha256":"b5c7bedc5a8ec21b0e9a6edc3e4de64d8fc239864dd20094606cab15671f8ee4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5c7bedc5a8ec21b0e9a6edc3e4de64d8fc239864dd20094606cab15671f8ee4","first_computed_at":"2026-07-05T04:02:27.083048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:27.083048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p9g0G/YryYcLTS5tcfoVrp0mPEoQhtBe6e5CkjiDHeLmHBO3WXjncN2l9u+rlBK+aN8bVG1qjmQaEPbXCg20Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:27.083482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:214c9ba0cc4390ad3afa395e13a136184e88f636810365dc253dc6804903b614","sha256:135c529c7f37106c8cc26828e61d2e1649f2d945a62c29d0e87847dcbd706f6a"],"state_sha256":"e5acd050d994c3e07357c62aa960015e34290cda8f920d3c4b2533dde62aa177"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3m4LnY6UI9HkEgx9OASBHevo70Y+qPju8LtsDB7NeHPnUyKSzrxm871stnhDAJ64Ml9xxiokO8oRLnM4SlfHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:46:04.669800Z","bundle_sha256":"3e6b9d86926c8bdcfaed2c08e81e48260b7bdec9b6e18bd0956701969944d027"}}