{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z6SQU7VXOXSNAWS3RX7FAYSS2W","short_pith_number":"pith:Z6SQU7VX","canonical_record":{"source":{"id":"2501.06685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T02:24:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a042383c360344eea931c74b72c1e68acf103f8c8e29521068a4705c3ad9b1c8","abstract_canon_sha256":"df03a03317ca170b80881364c6c35f910045c93cc2eca47bb3d1687bde07c7f4"},"schema_version":"1.0"},"canonical_sha256":"cfa50a7eb775e4d05a5b8dfe506252d5ae0f366d01828fc527c4bdfbf528bc19","source":{"kind":"arxiv","id":"2501.06685","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06685","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06685v1","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06685","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"Z6SQU7VXOXSN","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"Z6SQU7VXOXSNAWS3","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"Z6SQU7VX","created_at":"2026-07-05T10:00:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z6SQU7VXOXSNAWS3RX7FAYSS2W","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T02:24:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a042383c360344eea931c74b72c1e68acf103f8c8e29521068a4705c3ad9b1c8","abstract_canon_sha256":"df03a03317ca170b80881364c6c35f910045c93cc2eca47bb3d1687bde07c7f4"},"schema_version":"1.0"},"canonical_sha256":"cfa50a7eb775e4d05a5b8dfe506252d5ae0f366d01828fc527c4bdfbf528bc19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:08.604808Z","signature_b64":"Wz1rAWwQvy/7BjYqDHSZmPE7yMdgpS5vX6YmZUVoDdyVk28R/oNjU3FnMVlBjvHnOY6VbOUwulCmj1IbPJJkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa50a7eb775e4d05a5b8dfe506252d5ae0f366d01828fc527c4bdfbf528bc19","last_reissued_at":"2026-07-05T10:00:08.604425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:08.604425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06685","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":"2026-07-05T10:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqFFVm/p4D29dpx9KAXzWr36npB7mFy31AIqUf2/HGle5q5OF9/kKmJTro5qYKFap0KiMA/97q1Lkaq44rENDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:43:27.083515Z"},"content_sha256":"8a245938bf03c8dc4f3f110bd2138cd18bb12a29b5e2da4397e6708b48123914","schema_version":"1.0","event_id":"sha256:8a245938bf03c8dc4f3f110bd2138cd18bb12a29b5e2da4397e6708b48123914"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z6SQU7VXOXSNAWS3RX7FAYSS2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tab-Shapley: Identifying Top-k Tabular Data Quality Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Atharv Tyagi, Lokesh Nagalapatti, Manisha Padala, Ramasuri Narayanam, Shiv Kumar Saini","submitted_at":"2025-01-12T02:24:55Z","abstract_excerpt":"We present an unsupervised method for aggregating anomalies in tabular datasets by identifying the top-k tabular data quality insights. Each insight consists of a set of anomalous attributes and the corresponding subsets of records that serve as evidence to the user. The process of identifying these insight blocks is challenging due to (i) the absence of labeled anomalies, (ii) the exponential size of the subset search space, and (iii) the complex dependencies among attributes, which obscure the true sources of anomalies. Simple frequency-based methods fail to capture these dependencies, leadi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06685","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/2501.06685/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":"2026-07-05T10:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0HRH1IATS+IdsLhFdIYPYnJpw9tp5YD4hIt+bq+IebOwhfG4IpVl43Rvzr/WL5nuNa3Fk8sfUCHqUOZQTiJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:43:27.084034Z"},"content_sha256":"414f7246c4c92017d580e3c0136a5e7604fde3d2c014044a588b018611adffbd","schema_version":"1.0","event_id":"sha256:414f7246c4c92017d580e3c0136a5e7604fde3d2c014044a588b018611adffbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W/bundle.json","state_url":"https://pith.science/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W/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":"2026-08-11T13:43:27Z","links":{"resolver":"https://pith.science/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W","bundle":"https://pith.science/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W/bundle.json","state":"https://pith.science/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6SQU7VXOXSNAWS3RX7FAYSS2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6SQU7VXOXSNAWS3RX7FAYSS2W","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":"df03a03317ca170b80881364c6c35f910045c93cc2eca47bb3d1687bde07c7f4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T02:24:55Z","title_canon_sha256":"a042383c360344eea931c74b72c1e68acf103f8c8e29521068a4705c3ad9b1c8"},"schema_version":"1.0","source":{"id":"2501.06685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06685","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06685v1","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06685","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"Z6SQU7VXOXSN","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"Z6SQU7VXOXSNAWS3","created_at":"2026-07-05T10:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"Z6SQU7VX","created_at":"2026-07-05T10:00:08Z"}],"graph_snapshots":[{"event_id":"sha256:414f7246c4c92017d580e3c0136a5e7604fde3d2c014044a588b018611adffbd","target":"graph","created_at":"2026-07-05T10:00:08Z","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/2501.06685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an unsupervised method for aggregating anomalies in tabular datasets by identifying the top-k tabular data quality insights. Each insight consists of a set of anomalous attributes and the corresponding subsets of records that serve as evidence to the user. The process of identifying these insight blocks is challenging due to (i) the absence of labeled anomalies, (ii) the exponential size of the subset search space, and (iii) the complex dependencies among attributes, which obscure the true sources of anomalies. Simple frequency-based methods fail to capture these dependencies, leadi","authors_text":"Atharv Tyagi, Lokesh Nagalapatti, Manisha Padala, Ramasuri Narayanam, Shiv Kumar Saini","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T02:24:55Z","title":"Tab-Shapley: Identifying Top-k Tabular Data Quality Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06685","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":"sha256:8a245938bf03c8dc4f3f110bd2138cd18bb12a29b5e2da4397e6708b48123914","target":"record","created_at":"2026-07-05T10:00:08Z","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":"df03a03317ca170b80881364c6c35f910045c93cc2eca47bb3d1687bde07c7f4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T02:24:55Z","title_canon_sha256":"a042383c360344eea931c74b72c1e68acf103f8c8e29521068a4705c3ad9b1c8"},"schema_version":"1.0","source":{"id":"2501.06685","kind":"arxiv","version":1}},"canonical_sha256":"cfa50a7eb775e4d05a5b8dfe506252d5ae0f366d01828fc527c4bdfbf528bc19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfa50a7eb775e4d05a5b8dfe506252d5ae0f366d01828fc527c4bdfbf528bc19","first_computed_at":"2026-07-05T10:00:08.604425Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:08.604425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wz1rAWwQvy/7BjYqDHSZmPE7yMdgpS5vX6YmZUVoDdyVk28R/oNjU3FnMVlBjvHnOY6VbOUwulCmj1IbPJJkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:08.604808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a245938bf03c8dc4f3f110bd2138cd18bb12a29b5e2da4397e6708b48123914","sha256:414f7246c4c92017d580e3c0136a5e7604fde3d2c014044a588b018611adffbd"],"state_sha256":"b9aafd17fa0097c6c25bda3973eb18ee90272f52d4a6f7f525f980d3cafecef5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VO0QtOzQrGqpWDzCmqDsnv6sQQppxxn+PDf8W/u1hqOhm1D5E3TU5LqFctkaetinlXKwZ7O3V87WwRHN27ADBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:43:27.088093Z","bundle_sha256":"4086deb5348eece852a90e95d253e81e765bfa0e7d8ed9749c9828d61e07519e"}}