{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YQECANQJPDNQQY55IBGXIVWEYD","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":"52237989bfe2f9d02b9c67c7377f89fba6d3ce6b1b437e61a8cef3cc7d241419","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T12:56:41Z","title_canon_sha256":"1034c67585577229f33c36ca2e3318c2d6b6db96de232b13a1fd0d1331b5ed06"},"schema_version":"1.0","source":{"id":"2601.21656","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21656","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21656v3","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21656","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"YQECANQJPDNQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YQECANQJPDNQQY55","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YQECANQJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6d59c20178f7e35a84cff9a7602e8f28f96829357277c0f7f778f5fc080543d0","target":"graph","created_at":"2026-05-17T23:39:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TabClustPFN performs amortized Bayesian inference for cluster assignments and cardinality on unseen tabular data after pretraining on synthetic data from a flexible prior."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count."}],"snapshot_sha256":"3610ef08aff7512d9ad37ada2a4ca7d20ce55658998676b9a0ca8e3a29fe09c2"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Guanyang Wang, Qiong Zhang, Tianqi Zhao, Yan Shuo Tan","cross_cats":[],"headline":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T12:56:41Z","title":"TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21656","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T10:28:09.541684Z","id":"60e87dcc-2129-489e-9d70-363a3a0daeab","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"TabClustPFN clusters any new tabular dataset in one forward pass by amortizing Bayesian inference over assignments and cluster count.","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.","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."}},"verdict_id":"60e87dcc-2129-489e-9d70-363a3a0daeab"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cb7e72d7a1885f7d9c1802f8e9959fea801a1e7fe2b4215e58ddbfcfb85202ef","target":"record","created_at":"2026-05-17T23:39:16Z","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":"52237989bfe2f9d02b9c67c7377f89fba6d3ce6b1b437e61a8cef3cc7d241419","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T12:56:41Z","title_canon_sha256":"1034c67585577229f33c36ca2e3318c2d6b6db96de232b13a1fd0d1331b5ed06"},"schema_version":"1.0","source":{"id":"2601.21656","kind":"arxiv","version":3}},"canonical_sha256":"c40820360978db0863bd404d7456c4c0e7ea3a9b1f784bde4f589a642ac46093","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c40820360978db0863bd404d7456c4c0e7ea3a9b1f784bde4f589a642ac46093","first_computed_at":"2026-05-17T23:39:16.532043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.532043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mGLE5Gui49hzVOgwiWqPLm7Xu1YK1/xAERtdiSYUxtwI36tB6TVeJA/SznyE7+9049YD9cwcuhMFyRCx7k7sCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.532828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21656","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb7e72d7a1885f7d9c1802f8e9959fea801a1e7fe2b4215e58ddbfcfb85202ef","sha256:6d59c20178f7e35a84cff9a7602e8f28f96829357277c0f7f778f5fc080543d0"],"state_sha256":"6076aa7218386fa4d1b0b82302f1f2f4fb1b59d2d3c250f58ccefd0908605565"}