{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NBMFQ5VDZIIH7SSMJVOA43R7EL","short_pith_number":"pith:NBMFQ5VD","canonical_record":{"source":{"id":"2402.06282","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-02-09T09:48:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"784531f303b2f26efc8c4a9cc183d7f0fb9c1b292c4ff0297d40c03b704b71d8","abstract_canon_sha256":"2f605ed5b3285b35e45ca52c12bb84f4c6ca85f0526d9495c1d8d090e778bcf5"},"schema_version":"1.0"},"canonical_sha256":"68585876a3ca107fca4c4d5c0e6e3f22cc955d8c99de8981e1336da4e584d3a1","source":{"kind":"arxiv","id":"2402.06282","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06282","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06282v7","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06282","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"NBMFQ5VDZIIH","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"NBMFQ5VDZIIH7SSM","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"NBMFQ5VD","created_at":"2026-07-05T11:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NBMFQ5VDZIIH7SSMJVOA43R7EL","target":"record","payload":{"canonical_record":{"source":{"id":"2402.06282","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-02-09T09:48:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"784531f303b2f26efc8c4a9cc183d7f0fb9c1b292c4ff0297d40c03b704b71d8","abstract_canon_sha256":"2f605ed5b3285b35e45ca52c12bb84f4c6ca85f0526d9495c1d8d090e778bcf5"},"schema_version":"1.0"},"canonical_sha256":"68585876a3ca107fca4c4d5c0e6e3f22cc955d8c99de8981e1336da4e584d3a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:35.718586Z","signature_b64":"3ngeiPWTto1cqUCswSLWYckc4vh8aZzZpuMbcEus+dg+aWxUGIt+LY9Gd8UkSziloTJxGgeMMC0pyKLfbV+9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68585876a3ca107fca4c4d5c0e6e3f22cc955d8c99de8981e1336da4e584d3a1","last_reissued_at":"2026-07-05T11:04:35.717993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:35.717993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.06282","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZ8UXmVgFTM03QuJhKHI9VU5f44HOyNNgTQu3i7cYHyVahOoc0aeJ02cMQXs5RJGQ9CMhdcRYdobdJfx3hhUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:03:26.347482Z"},"content_sha256":"9a205b7e7ebb03e2ece06aeff82eefe34157b44cfe396d60ce77a9ea4c1cc2a4","schema_version":"1.0","event_id":"sha256:9a205b7e7ebb03e2ece06aeff82eefe34157b44cfe396d60ce77a9ea4c1cc2a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NBMFQ5VDZIIH7SSMJVOA43R7EL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieve, Merge, Predict: Augmenting Tables with Data Lakes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"(2) Dataiku, (3) EURECOM), Aimee Coelho (2), Felix Lefebvre (1), Gael Varoquaux (1) ((1) SODA Team - Inria Saclay, Paolo Papotti (3), Riccardo Cappuzzo (1)","submitted_at":"2024-02-09T09:48:38Z","abstract_excerpt":"Machine-learning from a disparate set of tables, a data lake, requires assembling features by merging and aggregating tables. Data discovery can extend autoML to data tables by automating these steps. We present an in-depth analysis of such automated table augmentation for machine learning tasks, analyzing different methods for the three main steps: retrieving joinable tables, merging information, and predicting with the resultant table. We use two data lakes: Open Data US, a well-referenced real data lake, and a novel semi-synthetic dataset, YADL (Yet Another Data Lake), which we developed as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06282","kind":"arxiv","version":7},"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/2402.06282/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":"2026-07-05T11:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ODBOnNfbf2ou3rIedSwLdvZ3xHSZ/4v3LbSiP+dxfJNEvNoJwabZ5Vl9tmCF5OhT4/CAkA0wybfNgf0PWWCECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:03:26.348478Z"},"content_sha256":"211aafb9549e163680e8a21a711f5b6a3b811a6c1d99b225974c3a4063328751","schema_version":"1.0","event_id":"sha256:211aafb9549e163680e8a21a711f5b6a3b811a6c1d99b225974c3a4063328751"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL/bundle.json","state_url":"https://pith.science/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL/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":"2026-08-07T18:03:26Z","links":{"resolver":"https://pith.science/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL","bundle":"https://pith.science/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL/bundle.json","state":"https://pith.science/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBMFQ5VDZIIH7SSMJVOA43R7EL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NBMFQ5VDZIIH7SSMJVOA43R7EL","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":"2f605ed5b3285b35e45ca52c12bb84f4c6ca85f0526d9495c1d8d090e778bcf5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-02-09T09:48:38Z","title_canon_sha256":"784531f303b2f26efc8c4a9cc183d7f0fb9c1b292c4ff0297d40c03b704b71d8"},"schema_version":"1.0","source":{"id":"2402.06282","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06282","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06282v7","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06282","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"NBMFQ5VDZIIH","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"NBMFQ5VDZIIH7SSM","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"NBMFQ5VD","created_at":"2026-07-05T11:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:211aafb9549e163680e8a21a711f5b6a3b811a6c1d99b225974c3a4063328751","target":"graph","created_at":"2026-07-05T11:04:35Z","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/2402.06282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine-learning from a disparate set of tables, a data lake, requires assembling features by merging and aggregating tables. Data discovery can extend autoML to data tables by automating these steps. We present an in-depth analysis of such automated table augmentation for machine learning tasks, analyzing different methods for the three main steps: retrieving joinable tables, merging information, and predicting with the resultant table. We use two data lakes: Open Data US, a well-referenced real data lake, and a novel semi-synthetic dataset, YADL (Yet Another Data Lake), which we developed as","authors_text":"(2) Dataiku, (3) EURECOM), Aimee Coelho (2), Felix Lefebvre (1), Gael Varoquaux (1) ((1) SODA Team - Inria Saclay, Paolo Papotti (3), Riccardo Cappuzzo (1)","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-02-09T09:48:38Z","title":"Retrieve, Merge, Predict: Augmenting Tables with Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06282","kind":"arxiv","version":7},"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":"sha256:9a205b7e7ebb03e2ece06aeff82eefe34157b44cfe396d60ce77a9ea4c1cc2a4","target":"record","created_at":"2026-07-05T11:04:35Z","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":"2f605ed5b3285b35e45ca52c12bb84f4c6ca85f0526d9495c1d8d090e778bcf5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-02-09T09:48:38Z","title_canon_sha256":"784531f303b2f26efc8c4a9cc183d7f0fb9c1b292c4ff0297d40c03b704b71d8"},"schema_version":"1.0","source":{"id":"2402.06282","kind":"arxiv","version":7}},"canonical_sha256":"68585876a3ca107fca4c4d5c0e6e3f22cc955d8c99de8981e1336da4e584d3a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68585876a3ca107fca4c4d5c0e6e3f22cc955d8c99de8981e1336da4e584d3a1","first_computed_at":"2026-07-05T11:04:35.717993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:35.717993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ngeiPWTto1cqUCswSLWYckc4vh8aZzZpuMbcEus+dg+aWxUGIt+LY9Gd8UkSziloTJxGgeMMC0pyKLfbV+9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:35.718586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06282","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a205b7e7ebb03e2ece06aeff82eefe34157b44cfe396d60ce77a9ea4c1cc2a4","sha256:211aafb9549e163680e8a21a711f5b6a3b811a6c1d99b225974c3a4063328751"],"state_sha256":"50dc359b44617cc28322867c1a0b1ce93b9ee4aa67e5aa03b728ef1140e32b29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ayZDI3CXJIZfyUeze/5OsKxNQX5OnqD8wCi+83v/Wuw6M2N/BrOhVWkbKUeuQK1xztFG3I6m0lHcVPhX6aoDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:03:26.355848Z","bundle_sha256":"79d0ffc36795f4307543d79e1a604ce3f923a3201b73c8d30533ef6dd69e36a2"}}