{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HU4UD2MMMYNRXVTYU2W4RTI6VS","short_pith_number":"pith:HU4UD2MM","canonical_record":{"source":{"id":"2307.04217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-09T16:16:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a8193a6fb6bd358b3065d3aaf5a2367f03720d82b1fbae69afffef0a04afa53","abstract_canon_sha256":"c16b0a4e3d9d98a1b2f99027079a62e7404b03be408e8e23c4dd91c87bc5d13c"},"schema_version":"1.0"},"canonical_sha256":"3d3941e98c661b1bd678a6adc8cd1eaca38d056e4c2e77048c4e31af30d848c0","source":{"kind":"arxiv","id":"2307.04217","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04217","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04217v1","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04217","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"pith_short_12","alias_value":"HU4UD2MMMYNR","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"HU4UD2MMMYNRXVTY","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"HU4UD2MM","created_at":"2026-07-05T06:29:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HU4UD2MMMYNRXVTYU2W4RTI6VS","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-09T16:16:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a8193a6fb6bd358b3065d3aaf5a2367f03720d82b1fbae69afffef0a04afa53","abstract_canon_sha256":"c16b0a4e3d9d98a1b2f99027079a62e7404b03be408e8e23c4dd91c87bc5d13c"},"schema_version":"1.0"},"canonical_sha256":"3d3941e98c661b1bd678a6adc8cd1eaca38d056e4c2e77048c4e31af30d848c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:10.415724Z","signature_b64":"x0lV21S5c4XijzxjKjhr+lp9NL/+eR0UT5vNUUg6BcSh92JmNqxEE5vAbqk3khJhaB03wZNr+FNYubMr3uLiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d3941e98c661b1bd678a6adc8cd1eaca38d056e4c2e77048c4e31af30d848c0","last_reissued_at":"2026-07-05T06:29:10.415329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:10.415329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04217","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":"2026-07-05T06:29:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lz8wkmBHmbqIGN4+5rppe4YnLk16E2Ev5u6nJPWg7kY+WuxRJLVBr4W1Ylpwn+b4Qpij82Ouy9e74Z3VHr/3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:01:21.805142Z"},"content_sha256":"3cceeae654b469f9bf836e4beb09d40fc9c39083f9279d2180aa43050800e09e","schema_version":"1.0","event_id":"sha256:3cceeae654b469f9bf836e4beb09d40fc9c39083f9279d2180aa43050800e09e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HU4UD2MMMYNRXVTYU2W4RTI6VS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LakeBench: Benchmarks for Data Discovery over Data Lakes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aamod Khatiwada, Harsha Kokel, Horst Samulowitz, Ibrahim Abdelaziz, Julian Dolby, Kavitha Srinivas, Oktie Hassanzadeh, Subhajit Chaudhury, Tejaswini Pedapati","submitted_at":"2023-07-09T16:16:11Z","abstract_excerpt":"Within enterprises, there is a growing need to intelligently navigate data lakes, specifically focusing on data discovery. Of particular importance to enterprises is the ability to find related tables in data repositories. These tables can be unionable, joinable, or subsets of each other. There is a dearth of benchmarks for these tasks in the public domain, with related work targeting private datasets. In LakeBench, we develop multiple benchmarks for these tasks by using the tables that are drawn from a diverse set of data sources such as government data from CKAN, Socrata, and the European Ce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04217","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/2307.04217/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":"2026-07-05T06:29:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NZzSIylDuIpk6ZFuVxkLqF+Iu/8it9ik+mglmJjok0lY7XCIL4g/og06eOmBnFb8EMKJ2kVtzj3Hs3nlI4+ECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:01:21.805797Z"},"content_sha256":"ffc47bea058ad4e1a767200c8196b3f996924c1e5790fbd96036361df8a41eec","schema_version":"1.0","event_id":"sha256:ffc47bea058ad4e1a767200c8196b3f996924c1e5790fbd96036361df8a41eec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS/bundle.json","state_url":"https://pith.science/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS/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":"2026-08-10T12:01:21Z","links":{"resolver":"https://pith.science/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS","bundle":"https://pith.science/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS/bundle.json","state":"https://pith.science/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HU4UD2MMMYNRXVTYU2W4RTI6VS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HU4UD2MMMYNRXVTYU2W4RTI6VS","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":"c16b0a4e3d9d98a1b2f99027079a62e7404b03be408e8e23c4dd91c87bc5d13c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-09T16:16:11Z","title_canon_sha256":"6a8193a6fb6bd358b3065d3aaf5a2367f03720d82b1fbae69afffef0a04afa53"},"schema_version":"1.0","source":{"id":"2307.04217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04217","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04217v1","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04217","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"pith_short_12","alias_value":"HU4UD2MMMYNR","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"HU4UD2MMMYNRXVTY","created_at":"2026-07-05T06:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"HU4UD2MM","created_at":"2026-07-05T06:29:10Z"}],"graph_snapshots":[{"event_id":"sha256:ffc47bea058ad4e1a767200c8196b3f996924c1e5790fbd96036361df8a41eec","target":"graph","created_at":"2026-07-05T06:29:10Z","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/2307.04217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Within enterprises, there is a growing need to intelligently navigate data lakes, specifically focusing on data discovery. Of particular importance to enterprises is the ability to find related tables in data repositories. These tables can be unionable, joinable, or subsets of each other. There is a dearth of benchmarks for these tasks in the public domain, with related work targeting private datasets. In LakeBench, we develop multiple benchmarks for these tasks by using the tables that are drawn from a diverse set of data sources such as government data from CKAN, Socrata, and the European Ce","authors_text":"Aamod Khatiwada, Harsha Kokel, Horst Samulowitz, Ibrahim Abdelaziz, Julian Dolby, Kavitha Srinivas, Oktie Hassanzadeh, Subhajit Chaudhury, Tejaswini Pedapati","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-09T16:16:11Z","title":"LakeBench: Benchmarks for Data Discovery over Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04217","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":"sha256:3cceeae654b469f9bf836e4beb09d40fc9c39083f9279d2180aa43050800e09e","target":"record","created_at":"2026-07-05T06:29:10Z","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":"c16b0a4e3d9d98a1b2f99027079a62e7404b03be408e8e23c4dd91c87bc5d13c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-09T16:16:11Z","title_canon_sha256":"6a8193a6fb6bd358b3065d3aaf5a2367f03720d82b1fbae69afffef0a04afa53"},"schema_version":"1.0","source":{"id":"2307.04217","kind":"arxiv","version":1}},"canonical_sha256":"3d3941e98c661b1bd678a6adc8cd1eaca38d056e4c2e77048c4e31af30d848c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d3941e98c661b1bd678a6adc8cd1eaca38d056e4c2e77048c4e31af30d848c0","first_computed_at":"2026-07-05T06:29:10.415329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:10.415329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x0lV21S5c4XijzxjKjhr+lp9NL/+eR0UT5vNUUg6BcSh92JmNqxEE5vAbqk3khJhaB03wZNr+FNYubMr3uLiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:10.415724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cceeae654b469f9bf836e4beb09d40fc9c39083f9279d2180aa43050800e09e","sha256:ffc47bea058ad4e1a767200c8196b3f996924c1e5790fbd96036361df8a41eec"],"state_sha256":"2928a2a86dd295080989057962e1a80bde0a97bc37f1553214cd1445051f29b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIMQYPI/9W79myuuIG8LlmAoTa5GkaGzJugAG+xpC0CN5tO4L5BkonVuu05hctNT+FRwNSmnVwBxcm/rE1dWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:01:21.812138Z","bundle_sha256":"91a78eb4263693d7125d6195cf9150a8e5f3f51787d877f9d81f17665376eee4"}}