{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5Y3IKVRZV7S25HFCI3NBV2OP6W","short_pith_number":"pith:5Y3IKVRZ","schema_version":"1.0","canonical_sha256":"ee36855639afe5ae9ca246da1ae9cff5b6e14aeef9ec8870d6d9ceb473522244","source":{"kind":"arxiv","id":"2310.15149","version":1},"attestation_state":"computed","paper":{"title":"Unlocking the Transferability of Tokens in Deep Models for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Le-Ye Wang, Qi-Le Zhou","submitted_at":"2023-10-23T17:53:09Z","abstract_excerpt":"Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tabular data when there are discrepancies between the feature sets of pre-trained models and the target tasks. In this paper, we propose TabToken, a method aims at enhancing the quality of feature tokens (i.e., embeddings of tabular features). TabToken allows for the utilization of pre-trained models when the upstream and downstream tasks share overlapping features, facilitating model fine-tuning even with limited train"},"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":"2310.15149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T17:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"01cf77add9e4f9fd146110eaa4450d1f51adbb6d1e9fba715f7ad820a7d8a3a9","abstract_canon_sha256":"0d858507d6fdaf8f858fb0196a51b28101bfb562c595488f6dd53fca8b1e25e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:06.709735Z","signature_b64":"1q1Hwu6Lb5YCXBVEo8UVxe22i154y61krX3Vz3sch6DdkkVF06YvTFz+8Intijxz6cITORXsOZSwr08S1XnZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee36855639afe5ae9ca246da1ae9cff5b6e14aeef9ec8870d6d9ceb473522244","last_reissued_at":"2026-07-05T07:04:06.709207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:06.709207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking the Transferability of Tokens in Deep Models for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Le-Ye Wang, Qi-Le Zhou","submitted_at":"2023-10-23T17:53:09Z","abstract_excerpt":"Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tabular data when there are discrepancies between the feature sets of pre-trained models and the target tasks. In this paper, we propose TabToken, a method aims at enhancing the quality of feature tokens (i.e., embeddings of tabular features). TabToken allows for the utilization of pre-trained models when the upstream and downstream tasks share overlapping features, facilitating model fine-tuning even with limited train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15149","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/2310.15149/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":"2310.15149","created_at":"2026-07-05T07:04:06.709269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15149v1","created_at":"2026-07-05T07:04:06.709269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15149","created_at":"2026-07-05T07:04:06.709269+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y3IKVRZV7S2","created_at":"2026-07-05T07:04:06.709269+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y3IKVRZV7S25HFC","created_at":"2026-07-05T07:04:06.709269+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y3IKVRZ","created_at":"2026-07-05T07:04:06.709269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02527","citing_title":"TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W","json":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W.json","graph_json":"https://pith.science/api/pith-number/5Y3IKVRZV7S25HFCI3NBV2OP6W/graph.json","events_json":"https://pith.science/api/pith-number/5Y3IKVRZV7S25HFCI3NBV2OP6W/events.json","paper":"https://pith.science/paper/5Y3IKVRZ"},"agent_actions":{"view_html":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W","download_json":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W.json","view_paper":"https://pith.science/paper/5Y3IKVRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15149&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y3IKVRZV7S25HFCI3NBV2OP6W/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y3IKVRZV7S25HFCI3NBV2OP6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W/action/storage_attestation","attest_author":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W/action/author_attestation","sign_citation":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W/action/citation_signature","submit_replication":"https://pith.science/pith/5Y3IKVRZV7S25HFCI3NBV2OP6W/action/replication_record"}},"created_at":"2026-07-05T07:04:06.709269+00:00","updated_at":"2026-07-05T07:04:06.709269+00:00"}