{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YQECANQJPDNQQY55IBGXIVWEYD","short_pith_number":"pith:YQECANQJ","schema_version":"1.0","canonical_sha256":"c40820360978db0863bd404d7456c4c0e7ea3a9b1f784bde4f589a642ac46093","source":{"kind":"arxiv","id":"2601.21656","version":3},"attestation_state":"computed","paper":{"title":"TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guanyang Wang, Qiong Zhang, Tianqi Zhao, Yan Shuo Tan","submitted_at":"2026-01-29T12:56:41Z","abstract_excerpt":"Clustering tabular data is a fundamental yet challenging problem due to heterogeneous feature types, diverse data-generating mechanisms, and the absence of transferable inductive biases across datasets. Prior-fitted networks (PFNs) have recently demonstrated strong generalization in supervised tabular learning by amortizing Bayesian inference under a broad synthetic prior. Extending this paradigm to clustering is nontrivial: clustering is unsupervised, admits a combinatorial and permutation-invariant output space, and requires inferring the number of clusters. We introduce TabClustPFN, a prior"},"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":"2601.21656","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T12:56:41Z","cross_cats_sorted":[],"title_canon_sha256":"1034c67585577229f33c36ca2e3318c2d6b6db96de232b13a1fd0d1331b5ed06","abstract_canon_sha256":"52237989bfe2f9d02b9c67c7377f89fba6d3ce6b1b437e61a8cef3cc7d241419"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.532828Z","signature_b64":"mGLE5Gui49hzVOgwiWqPLm7Xu1YK1/xAERtdiSYUxtwI36tB6TVeJA/SznyE7+9049YD9cwcuhMFyRCx7k7sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40820360978db0863bd404d7456c4c0e7ea3a9b1f784bde4f589a642ac46093","last_reissued_at":"2026-05-17T23:39:16.532043Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.532043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guanyang Wang, Qiong Zhang, Tianqi Zhao, Yan Shuo Tan","submitted_at":"2026-01-29T12:56:41Z","abstract_excerpt":"Clustering tabular data is a fundamental yet challenging problem due to heterogeneous feature types, diverse data-generating mechanisms, and the absence of transferable inductive biases across datasets. Prior-fitted networks (PFNs) have recently demonstrated strong generalization in supervised tabular learning by amortizing Bayesian inference under a broad synthetic prior. Extending this paradigm to clustering is nontrivial: clustering is unsupervised, admits a combinatorial and permutation-invariant output space, and requires inferring the number of clusters. We introduce TabClustPFN, a prior"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TabClustPFN clusters unseen datasets in a single forward pass, without dataset-specific retraining or hyperparameter tuning, and outperforms classical, deep, and amortized clustering baselines on synthetic and real-world tabular benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic datasets drawn from the flexible clustering prior sufficiently resemble the structure and heterogeneity of real-world tabular data so that the pretrained network generalizes without retraining.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TabClustPFN performs amortized Bayesian inference for cluster assignments and cardinality on unseen tabular data after pretraining on synthetic data from a flexible prior.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3610ef08aff7512d9ad37ada2a4ca7d20ce55658998676b9a0ca8e3a29fe09c2"},"source":{"id":"2601.21656","kind":"arxiv","version":3},"verdict":{"id":"60e87dcc-2129-489e-9d70-363a3a0daeab","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T10:28:09.541684Z","strongest_claim":"TabClustPFN clusters unseen datasets in a single forward pass, without dataset-specific retraining or hyperparameter tuning, and outperforms classical, deep, and amortized clustering baselines on synthetic and real-world tabular benchmarks.","one_line_summary":"TabClustPFN performs amortized Bayesian inference for cluster assignments and cardinality on unseen tabular data after pretraining on synthetic data from a flexible prior.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic datasets drawn from the flexible clustering prior sufficiently resemble the structure and heterogeneity of real-world tabular data so that the pretrained network generalizes without retraining.","pith_extraction_headline":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count."},"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":"2601.21656","created_at":"2026-05-17T23:39:16.532165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21656v3","created_at":"2026-05-17T23:39:16.532165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21656","created_at":"2026-05-17T23:39:16.532165+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQECANQJPDNQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQECANQJPDNQQY55","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQECANQJ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD","json":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD.json","graph_json":"https://pith.science/api/pith-number/YQECANQJPDNQQY55IBGXIVWEYD/graph.json","events_json":"https://pith.science/api/pith-number/YQECANQJPDNQQY55IBGXIVWEYD/events.json","paper":"https://pith.science/paper/YQECANQJ"},"agent_actions":{"view_html":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD","download_json":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD.json","view_paper":"https://pith.science/paper/YQECANQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21656&json=true","fetch_graph":"https://pith.science/api/pith-number/YQECANQJPDNQQY55IBGXIVWEYD/graph.json","fetch_events":"https://pith.science/api/pith-number/YQECANQJPDNQQY55IBGXIVWEYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD/action/storage_attestation","attest_author":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD/action/author_attestation","sign_citation":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD/action/citation_signature","submit_replication":"https://pith.science/pith/YQECANQJPDNQQY55IBGXIVWEYD/action/replication_record"}},"created_at":"2026-05-17T23:39:16.532165+00:00","updated_at":"2026-05-17T23:39:16.532165+00:00"}