{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WDI7B4PUVNWE6ZLTB3Z6JW5MCX","short_pith_number":"pith:WDI7B4PU","schema_version":"1.0","canonical_sha256":"b0d1f0f1f4ab6c4f65730ef3e4dbac15ea461201db5ff5adc49c7abaf94f8174","source":{"kind":"arxiv","id":"2505.13421","version":1},"attestation_state":"computed","paper":{"title":"Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han-Jia Ye, Qile Zhou, Si-Yang Liu","submitted_at":"2025-05-19T17:52:58Z","abstract_excerpt":"Tabular data, a fundamental data format in machine learning, is predominantly utilized in competitions and real-world applications. The performance of tabular models--such as gradient boosted decision trees and neural networks--can vary significantly across datasets due to differences in feature distributions and task characteristics. Achieving top performance on each dataset often requires specialized expert knowledge. To address this variability, practitioners often aggregate the predictions of multiple models. However, conventional aggregation strategies typically rely on static combination"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.13421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T17:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"e04142e5590b2560d0fc27c5370dac113d63d9fe5d07b3e75cdc57db71a01db8","abstract_canon_sha256":"ae989447bae0801e034a0dd4e6106fe228c5beffb723a040ba9ad840b12a6510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:29.848560Z","signature_b64":"g3udro+yMoS5fyqxoX8xhlrM2fsr58Dw+Ws71jzUU7IBhwwwHe7ksIxrZqMU7u8v8VTjaA3jm2QgbufqKB2ZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0d1f0f1f4ab6c4f65730ef3e4dbac15ea461201db5ff5adc49c7abaf94f8174","last_reissued_at":"2026-07-05T11:05:29.848026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:29.848026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han-Jia Ye, Qile Zhou, Si-Yang Liu","submitted_at":"2025-05-19T17:52:58Z","abstract_excerpt":"Tabular data, a fundamental data format in machine learning, is predominantly utilized in competitions and real-world applications. The performance of tabular models--such as gradient boosted decision trees and neural networks--can vary significantly across datasets due to differences in feature distributions and task characteristics. Achieving top performance on each dataset often requires specialized expert knowledge. To address this variability, practitioners often aggregate the predictions of multiple models. However, conventional aggregation strategies typically rely on static combination"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13421","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/2505.13421/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.13421","created_at":"2026-07-05T11:05:29.848114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13421v1","created_at":"2026-07-05T11:05:29.848114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13421","created_at":"2026-07-05T11:05:29.848114+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDI7B4PUVNWE","created_at":"2026-07-05T11:05:29.848114+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDI7B4PUVNWE6ZLT","created_at":"2026-07-05T11:05:29.848114+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDI7B4PU","created_at":"2026-07-05T11:05:29.848114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19662","citing_title":"When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX","json":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX.json","graph_json":"https://pith.science/api/pith-number/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/graph.json","events_json":"https://pith.science/api/pith-number/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/events.json","paper":"https://pith.science/paper/WDI7B4PU"},"agent_actions":{"view_html":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX","download_json":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX.json","view_paper":"https://pith.science/paper/WDI7B4PU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13421&json=true","fetch_graph":"https://pith.science/api/pith-number/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/graph.json","fetch_events":"https://pith.science/api/pith-number/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/action/storage_attestation","attest_author":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/action/author_attestation","sign_citation":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/action/citation_signature","submit_replication":"https://pith.science/pith/WDI7B4PUVNWE6ZLTB3Z6JW5MCX/action/replication_record"}},"created_at":"2026-07-05T11:05:29.848114+00:00","updated_at":"2026-07-05T11:05:29.848114+00:00"}