{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5DVUHPZXCWIPDH5ZO6GFMCVN72","short_pith_number":"pith:5DVUHPZX","canonical_record":{"source":{"id":"2505.21329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T15:23:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"4313554ea48ebf918d819121b0773cc77fa41bc1b56dc810df2296c3538fae6a","abstract_canon_sha256":"ad730efb7d9ea2b7b1e927ec36e3627ba79d18941890a3c0922bb8224c713255"},"schema_version":"1.0"},"canonical_sha256":"e8eb43bf371590f19fb9778c560aadfeb5c1ec1412d706ec16a9c377e5da2840","source":{"kind":"arxiv","id":"2505.21329","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21329","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21329v2","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21329","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"5DVUHPZXCWIP","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"5DVUHPZXCWIPDH5Z","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"5DVUHPZX","created_at":"2026-07-05T11:10:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5DVUHPZXCWIPDH5ZO6GFMCVN72","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T15:23:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"4313554ea48ebf918d819121b0773cc77fa41bc1b56dc810df2296c3538fae6a","abstract_canon_sha256":"ad730efb7d9ea2b7b1e927ec36e3627ba79d18941890a3c0922bb8224c713255"},"schema_version":"1.0"},"canonical_sha256":"e8eb43bf371590f19fb9778c560aadfeb5c1ec1412d706ec16a9c377e5da2840","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:58.986254Z","signature_b64":"kyl1hnhb+/mVczRhre3vUJ5NcFgSJNaK802PbzpO+Fd2XL/+pFFyuXzresic/m8k0SROYMMKmtWXWylq6tgdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8eb43bf371590f19fb9778c560aadfeb5c1ec1412d706ec16a9c377e5da2840","last_reissued_at":"2026-07-05T11:10:58.985792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:58.985792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21329","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":"2026-07-05T11:10:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oi5xgWb8vj3/eFWku56q+HZhHozuauuwXp/AFDMd2A7es5K+WuaKGw3jKneXw+Y9Xrt6cQhMaGVUNQL0tI0OAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:00:03.011752Z"},"content_sha256":"1e0f7dd2244ff34a12300516ccd3db49909a71c51549f518097e8ad3e24d773e","schema_version":"1.0","event_id":"sha256:1e0f7dd2244ff34a12300516ccd3db49909a71c51549f518097e8ad3e24d773e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5DVUHPZXCWIPDH5ZO6GFMCVN72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Something's Fishy In The Data Lake: A Critical Re-evaluation of Table Union Search Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.IR","authors_text":"Allaa Boutaleb, Bernd Amann, Hubert Naacke, Rafael Angarita","submitted_at":"2025-05-27T15:23:52Z","abstract_excerpt":"Recent table representation learning and data discovery methods tackle table union search (TUS) within data lakes, which involves identifying tables that can be unioned with a given query table to enrich its content. These methods are commonly evaluated using benchmarks that aim to assess semantic understanding in real-world TUS tasks. However, our analysis of prominent TUS benchmarks reveals several limitations that allow simple baselines to perform surprisingly well, often outperforming more sophisticated approaches. This suggests that current benchmark scores are heavily influenced by datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21329","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/2505.21329/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":"2026-07-05T11:10:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPcRont75XYH/onq4MuFWrL+hnhn+rlPqyTI/3CbsOy44hmbQKckCczmgS/OmC3j+CvU0JSrAEDtmZEvh3dKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:00:03.012352Z"},"content_sha256":"c9ed0e897ef82568f12a9061a069cbe3febb6509017dd3b540d20967437cfd8e","schema_version":"1.0","event_id":"sha256:c9ed0e897ef82568f12a9061a069cbe3febb6509017dd3b540d20967437cfd8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72/bundle.json","state_url":"https://pith.science/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72/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":"2026-08-08T07:00:03Z","links":{"resolver":"https://pith.science/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72","bundle":"https://pith.science/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72/bundle.json","state":"https://pith.science/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DVUHPZXCWIPDH5ZO6GFMCVN72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5DVUHPZXCWIPDH5ZO6GFMCVN72","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":"ad730efb7d9ea2b7b1e927ec36e3627ba79d18941890a3c0922bb8224c713255","cross_cats_sorted":["cs.AI","cs.CL","cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T15:23:52Z","title_canon_sha256":"4313554ea48ebf918d819121b0773cc77fa41bc1b56dc810df2296c3538fae6a"},"schema_version":"1.0","source":{"id":"2505.21329","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21329","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21329v2","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21329","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"5DVUHPZXCWIP","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"5DVUHPZXCWIPDH5Z","created_at":"2026-07-05T11:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"5DVUHPZX","created_at":"2026-07-05T11:10:58Z"}],"graph_snapshots":[{"event_id":"sha256:c9ed0e897ef82568f12a9061a069cbe3febb6509017dd3b540d20967437cfd8e","target":"graph","created_at":"2026-07-05T11:10:58Z","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/2505.21329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent table representation learning and data discovery methods tackle table union search (TUS) within data lakes, which involves identifying tables that can be unioned with a given query table to enrich its content. These methods are commonly evaluated using benchmarks that aim to assess semantic understanding in real-world TUS tasks. However, our analysis of prominent TUS benchmarks reveals several limitations that allow simple baselines to perform surprisingly well, often outperforming more sophisticated approaches. This suggests that current benchmark scores are heavily influenced by datas","authors_text":"Allaa Boutaleb, Bernd Amann, Hubert Naacke, Rafael Angarita","cross_cats":["cs.AI","cs.CL","cs.DB","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T15:23:52Z","title":"Something's Fishy In The Data Lake: A Critical Re-evaluation of Table Union Search Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21329","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":"sha256:1e0f7dd2244ff34a12300516ccd3db49909a71c51549f518097e8ad3e24d773e","target":"record","created_at":"2026-07-05T11:10:58Z","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":"ad730efb7d9ea2b7b1e927ec36e3627ba79d18941890a3c0922bb8224c713255","cross_cats_sorted":["cs.AI","cs.CL","cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T15:23:52Z","title_canon_sha256":"4313554ea48ebf918d819121b0773cc77fa41bc1b56dc810df2296c3538fae6a"},"schema_version":"1.0","source":{"id":"2505.21329","kind":"arxiv","version":2}},"canonical_sha256":"e8eb43bf371590f19fb9778c560aadfeb5c1ec1412d706ec16a9c377e5da2840","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8eb43bf371590f19fb9778c560aadfeb5c1ec1412d706ec16a9c377e5da2840","first_computed_at":"2026-07-05T11:10:58.985792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:58.985792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kyl1hnhb+/mVczRhre3vUJ5NcFgSJNaK802PbzpO+Fd2XL/+pFFyuXzresic/m8k0SROYMMKmtWXWylq6tgdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:58.986254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21329","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e0f7dd2244ff34a12300516ccd3db49909a71c51549f518097e8ad3e24d773e","sha256:c9ed0e897ef82568f12a9061a069cbe3febb6509017dd3b540d20967437cfd8e"],"state_sha256":"a214761b091a63364985de6972adc776993df5c16096bb5e2a06810a39892617"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmaqzQGzOEV4GmojrTCEhGIEbDiYGrDFYcz1rNtX+3Y/SOCbrqICvz0OZv3owfe2+tGK0PjFN60brLDUSdcoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:00:03.018727Z","bundle_sha256":"a0b42ac2ac6ebf80e61a2d052acd230884d3a397ae93af35dad6f7a9bf69de24"}}