{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4C4IJBVFGWWJPGTVZZY2MG5AB2","short_pith_number":"pith:4C4IJBVF","canonical_record":{"source":{"id":"2503.09159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"acf93e3ec3140f436fa910c389c7d7b375da1f9c7c8157ad5497e306edfdb768","abstract_canon_sha256":"f52fe97a92305ff78d5c5a8e686286fc6e74c7ea83586e4ac53d3ca4c8372c98"},"schema_version":"1.0"},"canonical_sha256":"e0b88486a535ac979a75ce71a61ba00e9fa397e0ad49bc2b96be154fc2aa1e16","source":{"kind":"arxiv","id":"2503.09159","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09159","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09159v1","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09159","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"4C4IJBVFGWWJ","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"4C4IJBVFGWWJPGTV","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"4C4IJBVF","created_at":"2026-07-05T10:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4C4IJBVFGWWJPGTVZZY2MG5AB2","target":"record","payload":{"canonical_record":{"source":{"id":"2503.09159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"acf93e3ec3140f436fa910c389c7d7b375da1f9c7c8157ad5497e306edfdb768","abstract_canon_sha256":"f52fe97a92305ff78d5c5a8e686286fc6e74c7ea83586e4ac53d3ca4c8372c98"},"schema_version":"1.0"},"canonical_sha256":"e0b88486a535ac979a75ce71a61ba00e9fa397e0ad49bc2b96be154fc2aa1e16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:50.277793Z","signature_b64":"QnVqPT/IHWZ89bA7lWt+brPPnW0DSRih4r5cWoDN1yjpA5JzhztbwOX52wZcO7TD9+yhwpc9fsLxbE6Ujby5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0b88486a535ac979a75ce71a61ba00e9fa397e0ad49bc2b96be154fc2aa1e16","last_reissued_at":"2026-07-05T10:29:50.277114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:50.277114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.09159","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":"2026-07-05T10:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEE/wcWxexYJ7659zXt2BPI/SD9otH2ZgzYqhLcZVQaz7zNpC8/+22Y48+DKQB8j2zDL8Of25YVOGTO5et8zDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:43:32.351178Z"},"content_sha256":"9fe5880a868b3d16e717cfd960b5f009544cbba77f43edce2e14792b1d57f714","schema_version":"1.0","event_id":"sha256:9fe5880a868b3d16e717cfd960b5f009544cbba77f43edce2e14792b1d57f714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4C4IJBVFGWWJPGTVZZY2MG5AB2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unreflected Use of Tabular Data Repositories Can Undermine Research Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrej Tschalzev, Christian Bartelt, Frank Hutter, Heiner Stuckenschmidt, Lennart Purucker, Stefan L\\\"udtke","submitted_at":"2025-03-12T08:41:49Z","abstract_excerpt":"Data repositories have accumulated a large number of tabular datasets from various domains. Machine Learning researchers are actively using these datasets to evaluate novel approaches. Consequently, data repositories have an important standing in tabular data research. They not only host datasets but also provide information on how to use them in supervised learning tasks. In this paper, we argue that, despite great achievements in usability, the unreflected usage of datasets from data repositories may have led to reduced research quality and scientific rigor. We present examples from prominen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09159","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/2503.09159/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":"2026-07-05T10:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LS3yYIoUMH8zMHWkpwIc1bEPy0rxoE4eRrrveS1b6l6KM/5V1VuRPMv1FJY39mCQ3umQLa8RPAhsSS3mmtzHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:43:32.352170Z"},"content_sha256":"31fcafc32a9c49cda4e31cc56c25022ee8966c1ff038645e2d0f87db928a0a75","schema_version":"1.0","event_id":"sha256:31fcafc32a9c49cda4e31cc56c25022ee8966c1ff038645e2d0f87db928a0a75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2/bundle.json","state_url":"https://pith.science/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2/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":"2026-08-17T17:43:32Z","links":{"resolver":"https://pith.science/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2","bundle":"https://pith.science/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2/bundle.json","state":"https://pith.science/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4C4IJBVFGWWJPGTVZZY2MG5AB2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4C4IJBVFGWWJPGTVZZY2MG5AB2","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":"f52fe97a92305ff78d5c5a8e686286fc6e74c7ea83586e4ac53d3ca4c8372c98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:41:49Z","title_canon_sha256":"acf93e3ec3140f436fa910c389c7d7b375da1f9c7c8157ad5497e306edfdb768"},"schema_version":"1.0","source":{"id":"2503.09159","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09159","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09159v1","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09159","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"4C4IJBVFGWWJ","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"4C4IJBVFGWWJPGTV","created_at":"2026-07-05T10:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"4C4IJBVF","created_at":"2026-07-05T10:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:31fcafc32a9c49cda4e31cc56c25022ee8966c1ff038645e2d0f87db928a0a75","target":"graph","created_at":"2026-07-05T10:29:50Z","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/2503.09159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data repositories have accumulated a large number of tabular datasets from various domains. Machine Learning researchers are actively using these datasets to evaluate novel approaches. Consequently, data repositories have an important standing in tabular data research. They not only host datasets but also provide information on how to use them in supervised learning tasks. In this paper, we argue that, despite great achievements in usability, the unreflected usage of datasets from data repositories may have led to reduced research quality and scientific rigor. We present examples from prominen","authors_text":"Andrej Tschalzev, Christian Bartelt, Frank Hutter, Heiner Stuckenschmidt, Lennart Purucker, Stefan L\\\"udtke","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:41:49Z","title":"Unreflected Use of Tabular Data Repositories Can Undermine Research Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09159","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":"sha256:9fe5880a868b3d16e717cfd960b5f009544cbba77f43edce2e14792b1d57f714","target":"record","created_at":"2026-07-05T10:29:50Z","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":"f52fe97a92305ff78d5c5a8e686286fc6e74c7ea83586e4ac53d3ca4c8372c98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:41:49Z","title_canon_sha256":"acf93e3ec3140f436fa910c389c7d7b375da1f9c7c8157ad5497e306edfdb768"},"schema_version":"1.0","source":{"id":"2503.09159","kind":"arxiv","version":1}},"canonical_sha256":"e0b88486a535ac979a75ce71a61ba00e9fa397e0ad49bc2b96be154fc2aa1e16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0b88486a535ac979a75ce71a61ba00e9fa397e0ad49bc2b96be154fc2aa1e16","first_computed_at":"2026-07-05T10:29:50.277114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:50.277114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnVqPT/IHWZ89bA7lWt+brPPnW0DSRih4r5cWoDN1yjpA5JzhztbwOX52wZcO7TD9+yhwpc9fsLxbE6Ujby5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:50.277793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09159","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fe5880a868b3d16e717cfd960b5f009544cbba77f43edce2e14792b1d57f714","sha256:31fcafc32a9c49cda4e31cc56c25022ee8966c1ff038645e2d0f87db928a0a75"],"state_sha256":"d41e4562b381400b877b5c654c1b7e6cec93e2245f2da012c3c41c733efab2bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRKbTCXmn0a1bjWCEV1ej0vKgEIdbCD5ha3vtxFP+nIksR4ikCUVG1v7oWQfFqvFy6EnJEdkXpsgoHG5eoXfAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:43:32.365905Z","bundle_sha256":"69d35a9ebe69e4416b4ac301ea679041d4d28ad994575788ba7b9bbd78a5930e"}}